48 of 51 criteria have a sourced finding; 48 were also cross-checked by a second agent. Every comparison that includes Cate links here for scope, limitations, atomic answers and sources.
Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.
Desktop installers cover macOS (arm64/x64), Windows x64 and Linux x64. No web client or phone-browser client exists; the native iPhone app is the phone route. The product-owned cate CLI is the command interface. No editor extensions for external editors exist. Desktop sessions start/steer/review/resume agent work; OS-native notifications plus iOS push; paired devices continue work across machines.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Browser, phone-browser and editor-extension routes are absent by bounded inspection; remaining findings are as cited.
9 atomic answers
Desktop os [supported] macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Sources: cate:readme, cate:electron.
Mobile apps [supported] Native SwiftUI iPhone app with agent chat, terminals, editors, browser and review views; App Store review rehearsal scripted; audit targets iPhone-only on iOS 26. Sources: cate:ios, cate:iosaudit, cate:changelog.
Browser [unsupported] No web client: the only shells are desktop Electron and iOS SwiftUI, and the site is marketing with no app UI. Sources: cate:arch, cate:site, cate:negsearch.
Mobile browser [unsupported] No phone-browser client: phone access is the native iOS app only. Sources: cate:arch, cate:ios, cate:negsearch.
Cli [supported] Product-owned cate CLI with agent, review, browser, terminal, editor and document areas, callable by agents in terminals. Sources: cate:agentapi, cate:clisurface.
Editor extensions [unsupported] No extensions for external editors: bounded search found no VS Code/marketplace plugin; connected editors share working files through terminal relations instead. Sources: cate:negsearch, cate:connected.
Task actions [supported] Start agents in new panels, prompt/steer running sessions, request changes from reviews, resume by session id after restarts. Sources: cate:readme, cate:agentapi, cate:review.
Notifications [supported] OS-native notifications, human-permission attention notifications, one subscription per open workspace, iOS push via APNs. Sources: cate:notif, cate:agentactivity, cate:arch.
Cross device continuity [supported] Paired devices share the same live workspace; a second device continues agent conversations, prompts and panels. Sources: cate:readme, cate:arch.
Seven provider CLIs are supported: Claude Code, Codex, Cursor, Grok, Kiro, OpenCode and Pi, launched as installed CLIs with native logins. No product-level model-provider catalog or custom harness adapters exist; mixed providers share one workspace through the cate CLI.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Product-level model-provider choice is not established; remaining findings are as cited.
5 atomic answers
Harnesses [supported] Claude Code, Codex, Cursor, Grok, Kiro, OpenCode, Pi with launch command, resume argv and session-store paths each. Sources: cate:registry, cate:setup.
Model providers [unknown] Model providers: no product-level catalog is established; model choice is inherited from each installed CLI login. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Custom adapters [unsupported] No custom harness adapters: the agent table is a closed total record and new agents are a compile error until every table covers them. Sources: cate:registry.
Session integration [supported] Cate launches installed provider CLIs in terminal PTYs, injects hooks per agent, and reuses native logins; it does not embed a model loop. Sources: cate:registry, cate:setup, cate:arch.
Mixed harness operation [supported] Different CLIs run side by side in one workspace and can drive each other through the shipped cate CLI. Sources: cate:readme, cate:registry, cate:agentapi.
Work reuses existing coding-agent subscriptions through native CLI logins; Cate sells nothing and stores no provider credentials. No vendor credits, local-model route, multi-account switching or provider restriction list is established; no Cate account is needed for local or LAN pairing.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Credential handling is each CLI own; credit, switching and restriction facts are as cited.
7 atomic answers
Agent subscriptions [supported] Existing supported coding-agent subscriptions work; Cate sells no tokens and stores no provider credentials. Sources: cate:readme, cate:setup.
Api accounts [supported] Agent requests use the user own account or API key under provider terms, handled inside each CLI native login. Sources: cate:privacy, cate:setup.
Vendor credits [unknown] Vendor credits: no billing or credit system appears in the checked first-party sources. Business fact. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Local models [unsupported] No product local-model route: the fixed registry holds seven vendor CLIs with vendor login flows and no local-model path. Sources: cate:registry, cate:setup.
Account switching [unknown] Account switching: no multi-account behavior is established in the checked sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Vendor account requirement [supported] No Cate account is required: local-first workspaces pair over LAN by QR/code; Cate Connect is a transport, not an account gate. Sources: cate:readme, cate:arch, cate:privacy.
Provider restrictions [unknown] Provider restrictions are provider terms, not established by Cate sources. Business fact. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Install the app and a provider CLI, authenticate it, open a folder and send a message. SSH hosts and WSL distros onboard the same way with automatic runtime install. Git-less folders, prerequisite lists beyond the above, and any managed-cloud setup are not established; no managed cloud exists.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Git-backing variants beyond the cited flows are not established; remaining findings are as cited.
7 atomic answers
First task setup [supported] Install app, install/authenticate a provider CLI via native login adapters, open a folder, pick an agent, send a message. Sources: cate:readme, cate:setup.
No git [unknown] Folders without Git: no statement on git-less workspaces is established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Local git without remote [unknown] Local Git without remote: no statement is established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Hosted git [unknown] Hosted Git backing: supported operationally via gh login for PR flows, but onboarding requirements for hosted remotes are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Prerequisite guidance [supported] Documented prerequisites: provider CLI plus its authentication, a folder, gh login for PR features; remote machines get the runtime installed automatically. Sources: cate:readme, cate:setup, cate:runtime, cate:github.
Managed cloud setup [unsupported] No managed cloud exists: Cate Connect is signaling plus TURN relay only and never executes work. Sources: cate:arch, cate:site, cate:negsearch.
Byo vps onboarding [supported] Open a folder on an SSH host or WSL distro; Cate installs the runtime there and local and remote follow the same path. Sources: cate:readme, cate:arch, cate:runtime, cate:availability.
The cate CLI covers create/inspect/steer/stop/review across agent, review, browser, terminal, editor and document areas with read/control gating. No public HTTP API, SDK, MCP server or webhooks exist. CLI callers reach only the api capability over an OS-user socket; runtime/client compatibility stays at version 1.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Network caller auth and API stability policy beyond the cited facts are unstated.
Api [unsupported] No public HTTP API: only the internal runtime capability protocol and the local cate CLI exist. Sources: cate:negsearch, cate:arch, cate:clisurface.
Sdk [unsupported] No SDK is shipped; automation goes through the cate CLI and internal TypeScript contracts. Sources: cate:negsearch, cate:clisurface.
Mcp server [unsupported] Cate exposes nothing over MCP; bounded search found only a Claude passthrough flag. Sources: cate:negsearch.
Webhooks [unsupported] No webhook emitters or handlers in the pinned release. Sources: cate:negsearch.
Authentication [partial] Local CLI callers are OS-user scoped to the api capability with read/control areas; network pairing uses device keys. Network caller auth beyond device keys is unstated. Sources: cate:arch, cate:agentapi.
Stability [partial] Runtime/client compatibility version 1 is pinned in release notes; no public API stability policy is stated. Sources: cate:release, cate:arch.
No MCP client exists (subsystem removed in 0.4.0). Official Cate IDE extensions ship through a PR-built catalog; skills install per agent from a curated catalog; the cate CLI plus panel APIs are the agent-usable tools, product-managed with read/control gating and hook modes.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Extension install flow and skill-source review gates are not established; remaining findings are as cited.
7 atomic answers
Mcp client [unsupported] No MCP client: the MCP registry and server management were removed in 0.4.0 and no MCP code remains except a Claude passthrough flag. Sources: cate:changelog, cate:negsearch.
Plugins [partial] Official Cate IDE extensions exist with a PR-based catalog published to GitHub Pages; in-product install/activation flow is not established by this pass. Sources: cate:cateext.
Custom tools [supported] Agents in terminals call the cate CLI to drive browsers, read terminals, manage panels and start or prompt agents; skills add catalog tools per agent. Sources: cate:clisurface, cate:agentapi, cate:skills.
Instructions import [supported] Skills install from a curated catalog into per-agent target dirs under the open Agent Skills SKILL.md standard. Sources: cate:skills.
Authentication [partial] Tool access is gated by CLI read/control areas and device pairing keys; third-party skill sources are GitHub repos with no stated review gate. Sources: cate:agentapi, cate:arch, cate:skills.
Permission scope [supported] Read vs control areas separate observation from steering; the local CLI token reaches only the api capability. Sources: cate:agentapi, cate:arch.
Integration owner [supported] Product-managed: hook injection modes, skill installer, setup adapters and panel APIs ship with Cate; MCP inheritance does not apply. Sources: cate:agentactivity, cate:skills, cate:setup, cate:clisurface.
Desktop is Electron with a React shell; mobile is a native SwiftUI app with a headless shared core. No hybrid framework is used. Evidence is official architecture plus pinned source and build targets.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
No hybrid implementation exists by bounded inspection.
4 atomic answers
Desktop implementation [supported] Electron desktop app with React UI; hardened runtime, notarized mac builds. Sources: cate:arch, cate:electron.
Mobile implementation [supported] Native SwiftUI iOS app; the shared client core runs headless in a WKWebView. Sources: cate:arch, cate:ios.
Hybrids [unsupported] No hybrids: exactly two shells exist (Electron desktop, SwiftUI mobile); Tauri/React Native are absent. Sources: cate:arch, cate:electron, cate:ios.
Implementation evidence [supported] Official architecture document plus pinned source and build configuration establish both implementations. Sources: cate:arch, cate:electron, cate:ios.
Work starts from user prompts (with file/photo attachments) or by opening a folder; agents in terminals take the prompts. No external tracker import, chat/Git triggers, sync or round-trips exist; the workspace document is the local authority and panel relations are not issues.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Tracker-shaped questions are answered negatively by bounded inspection; prompts are the only intake.
9 atomic answers
Local creation [supported] Opening a folder creates a workspace; prompts in terminals create agent sessions. Sources: cate:readme, cate:agentapi.
Prompt intake [supported] Prompts with file or photo attachments go to agent panels immediately or into the shared per-panel queue. Sources: cate:readme, cate:agentapi.
External import [unsupported] No tracker import exists: PR checkouts create worktrees but import no ticket state. Sources: cate:negsearch, cate:worktrees, cate:relations.
Chat git triggers [unsupported] No chat or Git triggers start work; no schedules, events or webhooks exist. Sources: cate:negsearch.
Authoritative tracker [unsupported] No external tracker relationship: the workspace document is the local authority for panels and relations. Sources: cate:arch, cate:relations.
Stable ids [unsupported] No external issue IDs exist; panels carry document IDs that are not issue identifiers. Sources: cate:relations, cate:arch.
Sync [unsupported] No synchronization with any external tracker exists in the pinned release. Sources: cate:negsearch, cate:relations.
Supported edits [unsupported] No external-tracker edits exist; edits apply to panels, files and review notes. Sources: cate:relations, cate:reviewapi.
External roundtrips [unsupported] No round-trips: GitHub contact is read/create-PR via the host gh login, not tracker sync. Sources: cate:github, cate:gitops.
Review panels hold a spec with a git/recorded-edits comparison, linked files and notes, and sessions persist across restarts with resume. Acceptance criteria, plan editors, revision history and mid-run amendment are not established.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only the review-spec findings are established; remaining plan questions are gaps.
7 atomic answers
Plans [partial] Review panels hold a spec plus comparison, files and notes; general task plans with lifecycle do not exist. Sources: cate:review, cate:reviewapi.
Acceptance criteria [unknown] Acceptance criteria: no field or gate is established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Editors [unknown] Plan editors: who can edit a review spec is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Revisions [unknown] Revision history for plans/specs is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Implementation links [partial] Reviews link the comparison, listed files, source terminal and follow-up agent sessions; task-level links do not exist. Sources: cate:review, cate:reviewapi, cate:agentapi.
Amendment [unknown] Amending a plan while work runs is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Restart persistence [supported] Reopening restores terminals with scrollback and reattaches each agent with its resume command. Sources: cate:readme.
Nested canvases and dock trees give visual grouping without epic semantics. No epics, blockers, readiness, enforcement, state propagation, task-to-epic growth or workflow constraints exist; relations carry context, not dependencies.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Hierarchy is visual only; all coordination semantics are absent by bounded inspection.
Hierarchy [partial] Nested canvas panels and dock trees provide visual parent/child grouping with no epic semantics attached. Sources: cate:arch, cate:readme.
Blockers [unsupported] No blocker concept exists; relations express context/use/verify intents, not blocking. Sources: cate:relations, cate:negsearch.
Workflow constraints [unsupported] No mandatory workflow or preset is required; opening a folder and prompting is enough. Sources: cate:readme, cate:negsearch.
Relation context and per-agent skill dirs feed turns; project docs are plain files; agent CLIs persist their own sessions with resume. Provenance, citation, correction/deletion and staleness controls are not established; a joining device inherits the full live context.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Memory is CLI-owned; context governance questions are gaps.
Skills [supported] Curated skill catalog installs per agent target dir under the SKILL.md standard. Sources: cate:skills.
Project docs [supported] Project docs are ordinary repo files agents read with filesystem tools; drafts persist as files surviving restarts. Sources: cate:connected, cate:arch.
Memory [partial] Each CLI persists its own sessions with resume stamps; no product-level cross-session memory exists. Sources: cate:registry, cate:readme.
Scope [unknown] Memory/context scope rules are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Provenance [unknown] Provenance of shared context is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Correction [unknown] Correction of shared context is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Deletion [unknown] Deletion of shared context is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Freshness [unknown] Staleness controls are not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Takeover continuity [supported] A joining client renders the same runtime document, panels, conversations and layout. Sources: cate:arch, cate:presence.
Ripgrep search, file/photo attachments, in-app browser panels and editor conflict detection exist. Indexing, external knowledge, citations, API retrieval and review-time enforcement are not established; review checks stay optional.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Retrieval depth questions are gaps; enforcement is absent.
10 atomic answers
Code search [supported] Ripgrep search across the workspace plus Cmd+K file/panel/command search. Sources: cate:readme.
Indexing [unknown] Repository indexing beyond live search is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
External knowledge [unknown] External knowledge retrieval is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Multimodal inputs [partial] Prompts accept file/photo attachments; browser, image, PDF and DOCX panels render rich content. Sources: cate:readme, cate:agentapi.
Freshness [unknown] Source freshness for retrieved context is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Access scope [unknown] Access scope of retrieval across worktrees is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Api retrieval [unknown] API-aware retrieval is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Citations [unknown] Citation of sources in agent output is not established. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Conflict detection [partial] Connected editors detect external writes and conflicting unsaved edits; neither version is discarded. Sources: cate:connected.
Review enforcement [unsupported] No review-time conformance enforcement exists; agent review is optional and merges are manual. Sources: cate:review, cate:flows.
No native issue management exists: no create/edit/discuss/prioritize/label/assign/search/filter/archive/reopen, no idea parking, no dispatch, no task/session separation, no durable issue states. Panels and relations are not issues and no external tracker is required for any issue workflow.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Project epic views [unsupported] No project/epic views exist; the canvas shows panels, not issues. Sources: cate:readme, cate:relations.
Idea parking [unsupported] No idea parking without starting an agent exists. Sources: cate:negsearch, cate:readme.
Explicit dispatch [unsupported] No dispatch queue exists; prompts go to panels immediately or into per-panel queues. Sources: cate:agentapi, cate:negsearch.
Task session separation [unsupported] No task/session separation exists; an agent session lives in its terminal panel. Sources: cate:relations, cate:presence.
External tracker requirement [unsupported] No external tracker is required; there is no issue workflow to attach one to. Sources: cate:relations, cate:negsearch.
Agents operate on panels, files, reviews and conversations through the cate CLI, but no shared issue records exist, so no agent-native issue operations (read/create/update, claim, assign, state changes, dependencies, children, results, attribution, permissions, conflicts) apply.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
No living product specifications exist: requirements do not persist across tasks, no human/agent editing with revisions or approvals, no requirement links, retrieval, drift detection or review integration. Review specs are single-review artifacts.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
9 atomic answers
Persistent requirements [unsupported] No persistent requirements exist across tasks or releases. Sources: cate:negsearch, cate:review.
Drift detection [unsupported] No drift detection exists. Sources: cate:negsearch.
Review integration [unsupported] Review specs serve one review and are not consulted as product requirements later. Sources: cate:review, cate:negsearch.
Independent agent sessions run concurrently in separate terminals, one per worktree branch, with running/waiting/finished states visible on the canvas. No concurrency quotas are documented and concurrent execution was not witnessed in a fixture.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Quotas and witnessed concurrency are not established.
5 atomic answers
Concurrent sessions [supported] Each agent runs in its own terminal panel session; five agents on five branches stay visibly separate. Sources: cate:readme, cate:presence.
Concurrent tasks [supported] Parallel terminals carry independent prompts and conversations per worktree. Sources: cate:readme, cate:agentapi, cate:worktrees.
Quotas [unknown] Concurrency quotas: none documented. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Observed concurrency [unknown] No installed-product fixture was run, so concurrent execution was not witnessed. Search gap: e2e specs not executed.
Status visibility [supported] Panels show running, waiting-for-input and finished; the Usage button and presence show live state. Sources: cate:readme, cate:presence, cate:usage.
Work is not assigned: every paired client has full access and there are no claims, routing or ownership enforcement. Per-panel prompt queues hold pending and failed prompts visibly for all clients.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Assignment semantics are limited to panel placement and shared queues.
7 atomic answers
Human assignment [unsupported] No human assignment exists; collaborators share the whole workspace with full access. Sources: cate:arch, cate:readme.
Agent assignment [partial] Agents are started into chosen panels/worktrees by users or by other agents via cate agent start; no assignment records exist. Sources: cate:agentapi.
Queues [partial] Each panel holds a shared prompt queue of pending and failed prompts visible to all connected clients. Sources: cate:readme, cate:agentapi.
Routing [unsupported] No routing or duplicate-work prevention exists. Sources: cate:arch, cate:negsearch.
Duplicate prevention [unsupported] No duplicate-work prevention exists. Sources: cate:arch, cate:negsearch.
Ownership enforcement [unsupported] No ownership enforcement exists; D3 deliberately keeps no roles or per-client permissions. Sources: cate:arch.
Any agent in a terminal can start, message, read and wait on other agent sessions through the shipped cate CLI, with live progress and retained results. Effort control stays CLI-side and cross-harness use is possible but only through that CLI.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Roles are informal and effort control is CLI-side; remaining findings are as cited.
12 atomic answers
Roles [partial] Coordinator and worker are terminal sessions distinguished by who called cate agent start; no formal role records exist. Sources: cate:agentapi, cate:arch.
Model harness effort [partial] The agentId can be chosen per start; model and effort stay inside each CLI. Sources: cate:agentapi, cate:registry.
Messages [supported] cate agent send delivers prompts to a chosen panel queue; read prints its conversation. Sources: cate:agentapi.
Cross harness [partial] A session of one CLI can prompt a session of another through the product CLI; no harness-bridging beyond that exists. Sources: cate:agentapi, cate:registry.
Orchestration owner [supported] Product-owned: the cate CLI, relation context and review flows ship with Cate; provider subagents are only displayed, never orchestrated. Sources: cate:clisurface, cate:relations, cate:review.
Activation [partial] Delegation activates by running the CLI in a terminal; hook injection modes auto/on/off gate per-agent tracking. Sources: cate:agentapi, cate:agentactivity.
Authentication [partial] CLI read/control areas and device pairing keys gate access; per-delegate credentials do not exist. Sources: cate:agentapi, cate:arch.
Live progress [supported] Running/waiting/finished panel states plus conversation sync show live progress on every client. Sources: cate:presence, cate:readme.
Retained results [supported] Conversations, scrollback, review notes and worktree branches persist for later reads. Sources: cate:readme, cate:review, cate:worktrees.
Followup [supported] Follow-up prompts can be sent to the same panel; resume commands reattach sessions after restarts. Sources: cate:agentapi, cate:registry.
Invocation [supported] Invocation is the cate agent start command from any terminal, agent or human. Sources: cate:agentapi.
No unattended triggers exist: no schedules, event triggers, recurring tasks, completion conditions, scheduler location, overlap handling or retries. Polling-style automation would be a manual integration, of which none is documented.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
8 atomic answers
Schedules [unsupported] No schedules exist in the pinned release. Sources: cate:negsearch.
Events [unsupported] No event triggers exist. Sources: cate:negsearch.
Recurring tasks [unsupported] No recurring tasks exist. Sources: cate:negsearch.
Completion conditions [unsupported] No completion conditions exist. Sources: cate:negsearch.
Scheduler location [unsupported] No scheduler exists, so no location applies. Sources: cate:negsearch.
Overlaps [unsupported] No overlap handling exists. Sources: cate:negsearch.
Retries [unsupported] No trigger retries exist. Sources: cate:negsearch.
Client independence [unsupported] Nothing can start work without a human; closing the client only matters for work already running. Sources: cate:negsearch, cate:availability.
Turns stop via per-CLI interrupt keys, sessions resume by id, prompts steer running work, permission waits raise attention notifications, and history is retained. Pause, escalation and a separate chat surface do not exist.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Pause and escalation are absent by bounded inspection.
10 atomic answers
Pause [unsupported] No pause exists; interrupt keys end the turn while keeping the prompt session. Sources: cate:registry, cate:negsearch.
Stop [supported] Interrupt keys stop a turn; panels and workspaces stop via close and Availability choices. Sources: cate:registry, cate:availability.
Notifications [supported] OS-native notifications plus waiting-for-input attention pings and iOS push. Sources: cate:notif, cate:agentactivity, cate:arch.
Pending decisions [supported] Permission prompts surface as pending decisions with per-CLI evidence rules. Sources: cate:agentactivity.
Escalation [unsupported] No escalation path exists. Sources: cate:negsearch.
Visible errors [supported] Turn failures, review failures and command errors surface as text in panels and flows. Sources: cate:review, cate:flows, cate:agentapi.
Chat terminal parity [unsupported] No separate chat surface exists; terminals are the sole agent interface, so parity does not apply. Sources: cate:arch.
Retained history [supported] Scrollback, conversations, review notes and layout persist across restarts. Sources: cate:readme, cate:review.
The canvas shows parallel streams on colored worktree territories with running/waiting attention states, but there is no epic model, dependency view, history, workload view or fixture-witnessed navigation.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Fleet visibility is canvas-only; navigation is unwitnessed.
8 atomic answers
Fleet fixture [partial] The canvas plus worktree territories display several parallel streams; epic states like blocked or delivered do not exist. Sources: cate:readme, cate:worktrees.
Parent child [partial] Nested canvases, dock trees and worktree branch links show grouping; dependency and ownership links do not exist. Sources: cate:arch, cate:worktrees, cate:agentapi.
Attention [supported] Waiting-for-input rings, badges and notifications mark panels needing attention. Sources: cate:readme, cate:notif.
History [unsupported] No fleet history view exists; history lives inside individual terminals and reviews. Sources: cate:negsearch, cate:readme.
Workload [unsupported] No workload view exists; the Usage button reports cost, not workload. Sources: cate:usage, cate:negsearch.
Navigation errors [unknown] Navigation behavior was not fixture-tested. Search gap: no installed-product run. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Fixture mode [unknown] No fixture was run. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Any prompt can start work with no mandatory workflow; canvases grow with worktrees while keeping panel relationships. Agent choice and hook modes are configurable per run, discovery runs through Cmd+K and pairing is a QR scan, but presets, natural-language configuration and model/effort control do not exist.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Configuration depth is CLI-side; presets and NL configuration are absent.
10 atomic answers
Quick task [supported] A quick task is one prompt in a terminal; no workflow selection is required. Sources: cate:readme, cate:agentapi.
Growing epic [partial] Work grows by adding worktrees and panels on the canvas; no epic identity carries the growth. Sources: cate:readme, cate:worktrees.
Presets [unsupported] No workflow or preset selection exists; saved layouts are window arrangements, not workflows. Sources: cate:negsearch, cate:readme.
Natural language [unsupported] No natural-language configuration of workflows exists; prompts are work content, not configuration. Sources: cate:negsearch, cate:agentapi.
Agent configuration [partial] AgentId choice per start plus hook injection modes; model and effort stay CLI-side. Sources: cate:agentapi, cate:agentactivity.
Live roles [partial] Calling vs started sessions are visible as panels with agent titles; no formal role display exists. Sources: cate:agentapi, cate:registry.
Retained relationships [partial] Worktree links, source-terminal links and ordered document ops persist; dependency links do not exist. Sources: cate:worktrees, cate:review, cate:arch.
Discoverability [partial] Cmd+K palette plus CLI help surface actions; no guided workflow discovery exists. Sources: cate:readme, cate:agentapi.
Auth friction [partial] Pairing is a QR/code scan with no accounts; CLI logins follow each provider native flow. Sources: cate:readme, cate:arch, cate:setup.
Work executes locally or on user-owned SSH/WSL machines whose runtimes Cate installs; self-hosted always-available workspaces are supported. No vendor cloud execution exists. The runtime survives client disconnects per workspace Availability and any paired device continues the same live workspace.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Resource, region facts are gaps; managed cloud and hybrid are absent.
12 atomic answers
Local [supported] Local execution on the machine holding the workspace files. Sources: cate:arch, cate:readme.
Byo remote [supported] SSH hosts and WSL distros run the workspace with an auto-installed runtime. Sources: cate:arch, cate:runtime, cate:readme.
Self hosted [supported] Self-hosted: the MIT runtime runs on user machines with Stay-available persistence and no vendor account. Sources: cate:arch, cate:availability, cate:license.
Managed cloud [unsupported] No vendor cloud execution exists; Cate Connect is signaling plus TURN relay and never runs work. Sources: cate:arch, cate:site, cate:negsearch.
Hybrid [unsupported] No hybrid mode exists: one workspace runs on exactly one runtime machine. Sources: cate:arch.
Provisioning [partial] Runtime tarballs install automatically on remote machines; compute itself is user-provisioned. Sources: cate:runtime, cate:readme.
Payer [supported] The user pays for their own machines; Cate bills nothing and sells no compute. Sources: cate:license, cate:site, cate:privacy.
Resources [unknown] Compute resource specifications are undocumented. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Region [unknown] Regions are unstated; relay geography is not documented. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Expiry [partial] Finish/Stay-available/Stop-with-Cate per workspace; a stopped workspace cannot be started remotely. Sources: cate:availability.
Client disconnect [supported] Work continues after the controlling client disconnects, subject to the Availability choice. Sources: cate:availability, cate:readme.
Other device continuation [supported] Any paired device reconnects to the same live workspace from anywhere. Sources: cate:readme, cate:arch.
Workspaces are plain folder checkouts with git worktree isolation per branch; device links are Noise-encrypted with pinned keys. No container, VM or OS-sandbox workload isolation exists, and process boundaries, secret management and hostile-code containment are not established as product guarantees.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Isolation is worktree-level; stronger boundaries are absent by bounded inspection.
12 atomic answers
Checkout [supported] A workspace is a folder checkout opened as a project. Sources: cate:readme, cate:arch.
Worktree [supported] One command creates a git worktree with its own colored canvas territory per branch or PR. Sources: cate:readme, cate:worktrees.
Container [unsupported] No container isolation exists; only Electron/webview sandboxing, which is not workload isolation. Sources: cate:negsearch, cate:arch.
Vm [unsupported] No VM or microVM isolation exists. Sources: cate:negsearch.
Os sandbox [unsupported] No OS-sandbox workload isolation exists. Sources: cate:negsearch, cate:arch.
Filesystem [partial] Worktrees separate files; the local transport is OS-user scoped; per-agent filesystem boundaries are unstated. Sources: cate:worktrees, cate:arch.
Process [unsupported] No process isolation boundary is documented; terminals share the runtime machine. Sources: cate:arch, cate:negsearch.
Network [partial] Device traffic is Noise-encrypted between paired keys; per-agent network controls do not exist. Sources: cate:arch.
Disconnects, restarts and expiry follow the Availability choice with transcript reload and session resume. Crash specifics, context loss, duplicate actions and manual repair are not established; multi-day work relies on Stay-available runtimes.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Failure edge-cases beyond the cited restore paths are gaps.
12 atomic answers
Client disconnect [supported] Disconnects are safe: the runtime keeps running per Availability and clients resync the shared document. Sources: cate:availability, cate:arch.
Worker crash [partial] Terminals restore with scrollback and agents reattach by resume; crash specifics are unstated. Sources: cate:readme, cate:registry.
Service restart [supported] Reopening a project restores terminals, scrollback, layout and agent resume. Sources: cate:readme.
Expiry [partial] Stop-with-Cate expires idle workspaces after 5 minutes; Finish and Stay-available persist instead. Sources: cate:availability.
Transcript reload [supported] Scrollback and conversations reload with the restored panels. Sources: cate:readme, cate:release.
Process reconnect [supported] Processes reconnect through per-agent resume commands keyed by session id. Sources: cate:registry, cate:readme.
Task resume [partial] Agent turns resume by session id; stale stamps fall back to a fresh shell rather than a wrong session. Sources: cate:registry.
State reconstruction [partial] The client core mirrors the runtime document and resyncs on reconnect; deeper reconstruction is unstated. Sources: cate:arch.
Context loss [unknown] Context-loss behavior is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Duplicate actions [unknown] Duplicate-action behavior after failures is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Manual repair [unknown] Manual repair procedures are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Multi day continuity [partial] Stay-available runtimes plus idle auto-updates carry multi-day work; a stopped workspace needs a local or SSH restart. Sources: cate:availability, cate:readme.
Only the remote runtime install is product-automated; CLIs install through vendor flows and project dependencies are agent work in terminals. Caches, snapshots, services, ports, collision handling and automatic repair are not established as product behavior.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Environment reliability beyond remote runtime install is agent-side or unstated.
10 atomic answers
Dependencies [partial] Provider CLIs install via vendor adapters; project dependencies are installed by agents, not by Cate automation. Sources: cate:setup, cate:readme.
Caches [unknown] Cache handling is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Snapshots [unknown] Snapshots are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Services [unknown] Auxiliary services are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Ports [unknown] Port allocation is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Secrets [partial] Terminals inherit the runtime environment and host logins; no product secret injection exists. Sources: cate:agentactivity, cate:github, cate:setup.
Duplicate installs [unknown] Deduplication across workspaces is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Collisions [unknown] Collision handling is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Remote setup [supported] Remote setup is product-owned: the runtime tarball installs onto SSH/WSL machines automatically. Sources: cate:runtime, cate:readme.
Automatic repair [unknown] Automatic repair is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Wait timeouts (5-60s) and CLI timeouts bound product calls; token/subscription limits are displayed, not enforced; spend limits do not exist. Retry and provider-failure specifics beyond stale-guard rails are not established.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Limit coverage is display plus timeouts; the rest are gaps.
8 atomic answers
Time limits [unknown] Time limits on work are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Turn limits [unknown] Turn limits are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Token limits [partial] Token and subscription limits are inspected and displayed (Claude/Codex); enforcement stays CLI-side. Sources: cate:usage, cate:agentactivity.
Spend limits [unsupported] No spend limits or enforcement exist; usage is display-only. Sources: cate:usage.
Retries [unknown] Retry behavior is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Provider failures [partial] Stale completion/approval guards and reviewer-exit failure marking exist; wider provider-failure handling is unstated. Sources: cate:agentactivity, cate:review.
Enforcement [partial] Wait timeouts stop cleanly; limits displays do not stop anything. Sources: cate:agentapi, cate:usage.
Terminals, conversations, failure text, per-agent usage stats and reconnect-consistent shared state exist. Usage export, project stats, performance figures and responsiveness claims are not established.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Statistics are usage-centric; export and performance facts are gaps.
13 atomic answers
Logs [supported] Terminal scrollback and readable agent conversations serve as logs. Sources: cate:readme, cate:agentapi.
Traces [partial] Agent tool steps are tracked in conversations; no distributed tracing exists. Sources: cate:release.
Failure reasons [partial] Command errors, review failure states and stale-guard rejections explain failures; no failure taxonomy exists. Sources: cate:flows, cate:review, cate:agentactivity.
Usage export [unknown] Usage export is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Task stats [partial] Usage aggregates by agent and time rather than by task; tasks are not entities. Sources: cate:usage, cate:relations.
Agent stats [supported] Usage overview breaks tokens and API-equivalent cost down by agent and model. Sources: cate:readme, cate:usage.
Project stats [unknown] Project-level statistics are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Time stats [supported] Usage is bucketed per day and hour. Sources: cate:usage.
Failure status [supported] Finished, failed and waiting states are visible on panels and reviews. Sources: cate:readme, cate:review, cate:presence.
Approval status [partial] Waiting-for-input states mark pending approvals; approver records do not exist. Sources: cate:agentactivity.
Reconnect consistency [supported] Agent, panel and board state resync from the runtime document on reconnect. Sources: cate:arch.
Performance method [unknown] No performance figures are published by the product. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Responsiveness [unknown] Responsiveness claims are unstated and were not measured. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Workspace token usage and API-equivalent cost by time, agent and model are visible, with subscription-limit display; billed-charge reconciliation, per-task/per-child accounting, compute costs, alerts, export and drill-down are not established.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Cost visibility is aggregate estimates; accounting depth is absent or unstated.
14 atomic answers
Task cost [unsupported] No per-task cost exists; tasks are not entities and usage aggregates by agent and time. Sources: cate:usage, cate:relations.
Session cost [partial] Per-agent/per-model usage implies session cost but no per-session figure is shown. Sources: cate:usage.
Harness aggregation [supported] Usage aggregates across all seven harness CLIs by agent and model. Sources: cate:usage.
Billed vs estimated [partial] API-equivalent costs are estimates and subscription limits are shown; billed charges stay provider-side. Sources: cate:usage, cate:readme.
Tokens [supported] Token usage is tracked and shown. Sources: cate:readme, cate:usage.
Subscription allowance [supported] Claude Code and Codex subscription limits are inspected and shown. Sources: cate:usage.
Provider reconciliation [unknown] Reconciliation against provider bills is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Compute cost [unsupported] No compute cost tracking exists; execution is the user own machines with no vendor billing. Sources: cate:arch, cate:site.
Refresh delay [unknown] Refresh timing is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Alerts [unknown] Budget alerts are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Export [unknown] Cost export is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Drilldown [unknown] Drill-down from summaries is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
No compute-aware scheduling exists: no concurrency limits, queues, CPU/RAM controls, backpressure, host awareness or check dedup. Turn cancellation via interrupt keys is the only bounded control.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Only cancellation is established; the rest are absent or unstated.
12 atomic answers
Concurrency [unsupported] No concurrency limits are documented or coded. Sources: cate:negsearch, cate:arch.
Queues [unsupported] No scheduling queues exist; prompt queues are per-panel inboxes, not schedulers. Sources: cate:negsearch, cate:agentapi.
Cpu ram [unsupported] No CPU/RAM limits exist. Sources: cate:negsearch.
Backpressure [unsupported] No backpressure exists. Sources: cate:negsearch.
Check reuse [unsupported] No check reuse exists. Sources: cate:negsearch.
Check deduplication [unsupported] No check deduplication exists. Sources: cate:negsearch.
Bounded tests [unknown] Bounded-test behavior is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Cancellation [supported] Turns cancel via per-agent interrupt keys; panels and workspaces close explicitly. Sources: cate:registry, cate:availability.
Fairness [unsupported] No fairness policy exists. Sources: cate:negsearch.
Recovery [unsupported] No scheduler recovery exists; restore is session-level, not schedule-level. Sources: cate:readme, cate:negsearch.
Shared limits [unsupported] No shared limits across epics exist. Sources: cate:negsearch.
Collaborators share one live workspace with presence and simultaneous prompting through shared queues; no in-product discussion or comments exist. No roles, ordering, conflict or plan rules govern co-steering; the original owner need not stay online.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Simultaneous prompting is shared-queue only; governance questions are gaps or absent.
11 atomic answers
Visibility [supported] Every connected client sees the same live panels, conversations, layout and presence. Sources: cate:readme, cate:arch, cate:presence.
Comments [unsupported] No commenting exists outside review findings on diffs. Sources: cate:negsearch, cate:review.
Presence [supported] Presence shows who else is connected; devices hold full shared control. Sources: cate:readme, cate:arch.
Coprompting [partial] Several people can send prompts into the same agent work via shared queues; no co-prompting protocol exists. Sources: cate:readme, cate:agentapi.
Ordering [unknown] Prompt ordering across simultaneous humans is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Conflicts [unknown] Conflict handling for simultaneous input is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Attribution [unknown] Human attribution for actions is unstated; D3 keeps no identities. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Permissions [unsupported] No co-steering permissions exist; every paired device has full access. Sources: cate:arch.
Plan restrictions [unknown] Plan restrictions: no plans exist, so none are stated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Owner online [supported] The original owner need not stay online: the runtime persists per Availability without any client. Sources: cate:availability, cate:arch.
No organization, project or task roles and no SSO or provisioning exist. Membership is device pairing with immediate revocation; unauthorized devices cannot connect thanks to pinned keys.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Membership is pairing-only; roles and SSO are absent.
9 atomic answers
Organization roles [unsupported] No organization roles exist. Sources: cate:arch.
Project roles [unsupported] No project roles exist. Sources: cate:arch.
Membership [partial] Membership is pairing: QR/code joins remember the workspace; removal is the membership lifecycle. Sources: cate:readme.
Sso [unsupported] No SSO is documented or coded. Sources: cate:negsearch.
Provisioning [unsupported] No provisioning exists. Sources: cate:negsearch.
Unauthorized access [partial] Only known devices connect: Noise handshake with pinned keys; unpaired devices are refused. Sources: cate:arch.
Revocation [supported] Removing a device revokes its access and disconnects it immediately. Sources: cate:readme, cate:privacy.
Plan scope [unknown] Plan scoping: no plans exist, so none is stated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Cate enforces no command, tool, network or secret approvals itself: agent CLIs own their permission policies. Delivery is gated by review completion (assigned agent only) and device access ends on removal; defaults are full access with hook-mode and CLI-area controls.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Approvals are CLI-owned; product enforcement covers CLI areas, reviews and pairing.
14 atomic answers
Command [unsupported] No product command approvals exist; CLIs enforce their own policies. Sources: cate:agentactivity.
Tunnels [unsupported] No product tunnels or temporary shared access exist beyond the relayed workspace transport. Sources: cate:arch, cate:negsearch.
Defaults [supported] Default is full access for every paired device. Sources: cate:arch.
Safer modes [partial] Hook injection auto/on/off and CLI read/control areas are the available safer settings. Sources: cate:agentactivity, cate:agentapi.
Enforcement [partial] CLI read/control areas and review-agent-only completion are enforced; model-behavior policy is not. Sources: cate:agentapi, cate:review.
Conversations, permission states, connected edits and review findings persist across users, sessions and restarts, but unattributed: no identities exist. No discussion threads, export or integrity model exist; retention beyond in-memory registrations is workspace files.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
History is retained but unattributed; export and integrity are gaps or absent.
11 atomic answers
Actions [partial] Agent actions persist as conversations and tool steps; human attribution is absent. Sources: cate:release, cate:arch.
Approvals [partial] Waiting states and review completions persist; approver identities do not. Sources: cate:agentactivity, cate:review.
Edits [partial] Connected-edits autosave and review notes persist; an edit ledger does not exist. Sources: cate:connected, cate:review.
Discussion [unsupported] No discussion history exists. Sources: cate:negsearch.
Decisions [partial] Review findings with severity and resolution persist as decision records. Sources: cate:review, cate:reviewapi.
Cross user persistence [supported] History persists across users in the shared runtime state. Sources: cate:arch.
Cross session persistence [supported] History persists across sessions and restarts. Sources: cate:readme.
Export [unsupported] No history export exists. Sources: cate:negsearch.
Mutability [unknown] Mutability of history is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Retention [partial] Connection registrations live in memory and vanish on disconnect; workspace data persists on disk. Sources: cate:privacy, cate:arch.
Integrity [unknown] No integrity model is stated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Review panels show diffs, files, notes and evidence with comments, request-changes and shipping via merge/PR flows; keyboard shortcuts are rebindable and the iPhone app (with a review view) serves narrow screens. Pending-review discovery, effort and missed-evidence facts are not established.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Discovery and effort facts are gaps; guidance is flow-level.
13 atomic answers
Pending reviews [partial] Reviews live as panels on the canvas with working/failed/complete states; no pending queue exists. Sources: cate:review.
Change understanding [supported] Side-by-side diffs, file lists and recorded edits show the change. Sources: cate:readme, cate:review.
Evidence navigation [supported] Inspect prints the comparison, files and notes for navigation. Sources: cate:reviewapi.
Comments [supported] Findings attach to diff lines with severity and resolve by id. Sources: cate:review, cate:reviewapi.
Request changes [supported] Request-changes sends open findings to the source or a new agent. Sources: cate:review.
Shipping guidance [partial] Merge-worktree and PR-create flows are the next actions; no guided ship checklist exists. Sources: cate:flows, cate:gitops.
Effort [unknown] Review effort is unstated and was not measured. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Missed evidence [unknown] Missed-evidence handling is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Keyboard [supported] Shortcuts are rebindable in Settings; Cmd+K drives commands, panels and files. Sources: cate:readme.
Narrow screen [supported] The iPhone app follows conversations and panels and ships a review view. Sources: cate:readme, cate:ios.
Context switching [partial] The sticky review target and canvas layout preserve review context across panels. Sources: cate:reviewapi, cate:readme.
Roles [partial] Source agent vs reviewer sessions are distinguished; human roles do not exist. Sources: cate:review, cate:arch.
Retained context [supported] Comparison, notes and panel state persist for the review lifetime. Sources: cate:review.
A second paired person takes over the same live task with full session history, decisions, artifacts and runtime context, including after the first person disconnects; ownership and attribution do not exist as concepts. Harness transfer means prompting a different CLI in the same workspace.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Takeover is total but identity-free; migration is manual.
12 atomic answers
Ongoing takeover [supported] A second authorized person works in the same live workspace with full control. Sources: cate:readme, cate:arch.
Same task [supported] Takeover keeps the same panels, conversations and worktrees. Sources: cate:arch, cate:readme.
Session history [supported] Scrollback and agent conversations are shared live. Sources: cate:readme, cate:presence.
Decisions [supported] Review findings and states are shared. Sources: cate:review.
Artifacts [supported] Files, panels, layouts and worktrees are shared. Sources: cate:readme, cate:connected.
Permissions [unsupported] No takeover permissions exist; every device already has full access. Sources: cate:arch.
Runtime context [supported] No transfer is needed: the runtime context is the shared workspace itself. Sources: cate:arch.
Owner disconnect [supported] Takeover survives the first person disconnecting; the runtime persists per Availability. Sources: cate:availability, cate:arch.
Ownership [unsupported] No ownership transfer exists; there is no owner record. Sources: cate:arch.
Context loss [supported] No takeover context loss is established; state is shared live, not copied. Sources: cate:arch, cate:presence.
Harness transfer [partial] Transfer to another model/harness is starting or prompting a different CLI in the same workspace; no transcript migration exists. Sources: cate:agentapi, cate:registry.
Diffs, file previews, browser panels, test output in terminals and reviewer findings persist per workspace and across restarts, with revision-linked review comparisons. No artifact gallery, recordings, task links or build links exist; prompt-leakage handling is unstated.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Artifacts are panel-local; gallery and link depth are absent or unstated.
13 atomic answers
Diffs [supported] Side-by-side diffs with git badges plus review comparisons. Sources: cate:readme, cate:review.
Documents [partial] Monaco editors plus image/PDF/DOCX viewers; editing beyond text is view-focused. Sources: cate:readme, cate:connected.
Screenshots [unknown] Screenshot capture of panels is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Recordings [unsupported] No session recordings exist; conversations persist as text. Sources: cate:release, cate:negsearch.
Previews [supported] Browser panels and file previews render live workspace content. Sources: cate:readme, cate:browserapi.
Test outputs [partial] Test output shows in terminals but is not captured as structured artifacts. Sources: cate:readme.
Reviewer outputs [supported] Reviewer findings and completion states persist in review panels. Sources: cate:review.
Gallery [unsupported] No artifact gallery or cross-task retrieval UI exists. Sources: cate:negsearch, cate:readme.
Task links [unsupported] No task links exist; tasks are not entities. Sources: cate:relations.
Revision links [partial] Reviews link comparisons and files; commit links are terminal-side git, not product links. Sources: cate:review, cate:gitops.
Persistence [supported] Workspace data persists on the runtime machine across sessions. Sources: cate:arch, cate:readme.
Child findings [supported] Agent reviewer findings persist in the parent review panel. Sources: cate:review.
Prompt leakage [unknown] Prompt-leakage handling across artifacts is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
No tests, lint, type, CI, spec or required checks gate delivery; the optional agent review with request-changes is the only verification flow, and nothing blocks merges on failure. Enforcement policy beyond CLI areas does not exist.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Verification is an optional flow; gates do not exist.
11 atomic answers
Tests [unsupported] No product test gates exist; agents run tests in terminals. Sources: cate:negsearch, cate:readme.
Lint [unsupported] No lint gates exist. Sources: cate:negsearch.
Types [unsupported] No type gates exist. Sources: cate:negsearch.
Independent review [partial] Optional read-only agent review with request-changes exists but is never required. Sources: cate:review.
Spec checks [unknown] Spec conformance checks are unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Failure blocking [unsupported] Failures block nothing: review completion does not gate merges. Sources: cate:review, cate:flows.
Requirement conflicts [unknown] Requirement-conflict handling is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Configured policy [unsupported] No verification policy is configurable. Sources: cate:negsearch.
Branches, worktrees, PR creation/listing/context and merge-back flows are product-owned via the host gh login; commits, comments and rebases stay agent/terminal-side. CI response surfacing and product-held PR state do not exist.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Git depth is worktree/PR-shaped; commit and CI depth are terminal-side or absent.
9 atomic answers
Branches [supported] Branch names derive from work descriptions; panels switch checkouts. Sources: cate:worktrees, cate:flows.
Merges run through product worktree flows and PR creation, but approval, release and deployment do not exist as product capabilities; exact-revision discipline and authority enforcement are absent.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Shipping authority is the user; product gates do not exist.
6 atomic answers
Approve [partial] Review completion approves the review only; merge approval is the user own git action. Sources: cate:review, cate:flows.
Merge [partial] Worktree-to-base merges run in product UI; authority is the user, not a product gate. Sources: cate:flows.
Release [unsupported] No release flow exists. Sources: cate:negsearch.
Deploy [unsupported] No deployment flow exists. Sources: cate:negsearch.
Exact revision [partial] Reviews compare exact working state, but merges apply to a moving branch, not a pinned revision. Sources: cate:review, cate:flows.
Authority enforcement [unsupported] No merge/release authority enforcement exists; D3 keeps no roles. Sources: cate:arch, cate:negsearch.
Worktree-PR links, delivery states and retained conversations/notes exist; commit, build and deployment links, rollback, revert and stale-approval invalidation do not.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Delivery traceability is naming- and state-level only.
9 atomic answers
Commit links [unsupported] No task-to-commit links exist; tasks are not entities. Sources: cate:relations.
Pr links [partial] Worktree folders encode PR numbers and PR context is readable; links are naming-level, not tracked. Sources: cate:worktrees, cate:github.
Build links [unsupported] No build links exist. Sources: cate:negsearch.
Deployment links [unsupported] No deployment links exist. Sources: cate:negsearch.
Delivery status [partial] Panel running/waiting/finished plus review working/failed/complete states mark delivery; shipment records do not exist. Sources: cate:presence, cate:review.
Retained evidence [supported] Conversations, notes, scrollback and comparisons persist across restarts. Sources: cate:readme, cate:review.
Stale approval invalidation [unknown] Stale-approval invalidation is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
No batch review queue, summaries, grouping, filters, dependency queues or check dedup exist; request-changes and per-review findings with linked artifacts carry high-volume work instead, without stale-approval rules.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Batch review is per-panel, not queue-driven.
12 atomic answers
Review queue [unsupported] No review queue exists; reviews are canvas panels. Sources: cate:review, cate:negsearch.
Summaries [unsupported] No product summaries exist; summaries are agent output. Sources: cate:review, cate:negsearch.
Grouping [unsupported] No grouping exists. Sources: cate:negsearch.
Risk size filters [unsupported] No risk/size filters exist. Sources: cate:negsearch.
Findings [supported] Open findings with severity persist per review. Sources: cate:review.
Artifacts [partial] Diffs, files and notes link into each review; cross-review navigation does not exist. Sources: cate:reviewapi.
Request changes [supported] Request-changes routes findings to the source or a new agent. Sources: cate:review.
Exact revision approval [partial] Completion approves the reviewed comparison; revision pinning is unstated. Sources: cate:review.
Dependency queues [unsupported] No dependency queues exist. Sources: cate:negsearch.
Next actions [partial] Merge and PR-create flows follow reviews; no guided next-action list exists. Sources: cate:flows, cate:gitops.
Stale approval invalidation [unknown] Stale-approval invalidation is unstated. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Check deduplication [unsupported] No check dedup exists. Sources: cate:negsearch.
The whole application repository is MIT-licensed public source at the pinned tag; the hosted Cate Connect service is a separate closed component whose parity is not established, and the extensions repository publishes no license.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Extensions licensing and hosted parity are not established.
6 atomic answers
Client license [supported] MIT license covers the desktop client in the root LICENSE. Sources: cate:license, cate:repometa.
Server license [supported] MIT covers the runtime daemon: same repository, same license, same build. Sources: cate:license, cate:arch.
Hosted extensions [unknown] The extensions repository publishes no license file; its terms are not established. Business fact. Checked https://github.com/0-AI-UG/cate-extensions 2026-11-12.
Source visibility [supported] All application source is public at 0-AI-UG/cate. Sources: cate:repometa.
Source revision [supported] Pinned tag v2.1.0-beta.14 with commit hash and dated release notes. Sources: cate:release.
Hosted parity [unknown] Hosted Cate Connect lives in its own separate repository and its parity with local behavior is not established. Closed component. Architecture 7.7; checked 2026-11-12.
Self-hosting is the default: MIT software runs on user machines with no vendor account, LAN pairing and on-disk workspace state. GitHub (updates), provider CLIs and the optional Connect relay are the vendor dependencies; no product export/import format exists beyond plain files.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Portability is file-level, not format-level.
8 atomic answers
Self hosting [supported] Core runs on user-controlled machines; no vendor account or service is required. Sources: cate:license, cate:arch, cate:readme.
Vendor dependencies [partial] Update checks hit GitHub; remote pairing can use the Connect relay; agent work needs user-installed provider CLIs. Sources: cate:privacy, cate:arch, cate:setup.
Export [partial] No product export exists; workspaces are plain files plus a data directory on the runtime machine. Sources: cate:arch, cate:negsearch.
Import [supported] Import is opening a folder, SSH host path or WSL path as a workspace. Sources: cate:readme, cate:runtime.
Formats [partial] Plain files plus .cate/ skills/tmp/worktree checkouts; no portable standard format. Sources: cate:arch.
Cancellation [unknown] No accounts exist to cancel; hosted-service cancellation terms are unstated. Business fact. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Account independence [supported] Fully usable without any vendor account over LAN pairing. Sources: cate:readme, cate:arch.
History portability [partial] Conversations live in CLI session stores and workspace data as files; no portable history format exists. Sources: cate:registry, cate:arch.
Local-first: files and sessions stay on the runtime machine, telemetry and crash reports are always-on and undisablable, and agent traffic goes to user-configured providers under their terms. Retention, residency and training facts are partly unstated.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Telemetry is undisablable; retention detail, residency and training are gaps.
15 atomic answers
Code data [supported] Files and sessions are stored on the computer running the runtime; paired devices access them remotely. Sources: cate:privacy, cate:arch.
Prompts [partial] Prompts including code excerpts go to the configured provider; usage events exclude AI messages. Sources: cate:privacy, cate:analytics.
Credentials [partial] Provider and gh credentials live in CLI/host logins; Cate stores none of its own. Sources: cate:setup, cate:github, cate:privacy.
Logs [partial] Diagnostics cover launches, installs, updates and feature use with technical context; contents and paths are excluded. Sources: cate:privacy, cate:analytics.
Artifacts [supported] Artifacts live in workspace state on the runtime machine. Sources: cate:arch.
Retention [partial] Connection registrations are in-memory and vanish on disconnect; install ids persist; schedule detail is unstated. Sources: cate:privacy.
Deletion [partial] Device removal revokes access; deletion requests are described with the mobile supplement covering push data. Sources: cate:privacy, cate:iosaudit.
Training [unknown] Training use of data is unstated by Cate sources; provider training is provider terms. Business fact. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Residency [partial] Hosting and network providers process relay traffic; regions are unstated. Sources: cate:privacy.
Subprocessors [partial] Sentry, analytics hosting, network providers and GitHub updates are the named processors. Sources: cate:privacy, cate:sentry.
Telemetry disclosure [supported] The policy discloses Sentry crash reporting and self-hosted analytics with event scope. Sources: cate:privacy.
Telemetry controls [unsupported] No control exists: always on from 1.3.1, cannot be disabled; the notice is informational only. Sources: cate:privacy, cate:welcome.
Consent prompt [partial] A first-run notice links the policy but offers no choice. Sources: cate:welcome, cate:privacy.
Provider separation [supported] Orchestration-vendor policy is separated from model-provider terms in the policy text. Sources: cate:privacy.
Cate is MIT open source and free to download, with no paid plan found; it runs agents on the user own existing agent subscriptions and sells no tokens. No priced dimensions (currency, seats, overages, taxes) are stated.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Priced dimensions are absent because no paid plan exists in the checked sources; no purchase or billing test was run.
12 atomic answers
Currency [unknown] No first-party source states currency for a paid plan. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Interval [unknown] No first-party source states billing interval. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Seats [unknown] No first-party source states seats. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Seat minimum [unknown] No first-party source states a seat minimum. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Workspace fees [unknown] No first-party source states workspace fees. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Included usage [unknown] No first-party source states included usage. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Credits [unsupported] No credits are sold or mentioned; agent spend is provider-side. Sources: cate:privacy, cate:negsearch.
Trial [unknown] No trial is stated; the product is free. Checked: cate.cero-ai.com, 0-AI-UG/cate releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Overages [unknown] No first-party source states overages. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Taxes [unknown] No first-party source states taxes treatment. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE/releases. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Model cost [supported] Agent cost is the user own existing subscriptions or API accounts, handled provider-side. Sources: cate:readme, cate:privacy.
Compute cost [unknown] No first-party source states compute cost; execution is user machines. Checked: cate.cero-ai.com, 0-AI-UG/cate README/LICENSE. Business/hosted-service fact not established by the checked first-party sources. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Desktop releases ship as versioned betas (2.1.0-beta.14 on 2026-11-12) with near-daily cadence; iOS builds are versioned while App Store review is pending. Support channels, response commitments, status history and deprecation/export options are not established.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
beta
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Support and status facts are gaps; deprecation absence is not a finding.
8 atomic answers
Release stage [supported] Beta desktop releases plus versioned iOS builds; no GA claim is made. Sources: cate:release, cate:changelog.
Access restrictions [partial] Public GitHub releases for desktop; iOS distribution channel is pending App Store review. Sources: cate:release, cate:iosaudit.
Support [unknown] Support channels are unstated. Business fact. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Response commitments [unknown] Response commitments are unstated. Business fact. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Release activity [supported] Beta.14 and iOS 0.1.2 shipped 2026-11-12; beta cadence is near-daily since mid-October. Sources: cate:release, cate:changelog.
Status history [unknown] No status page or history was found. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Deprecation [unknown] No deprecation or shutdown notice exists; absence is not a finding. Checked README, architecture, docs/, CHANGELOG and the pinned source at v2.1.0-beta.14; no installed-product fixture was run.
Export options [partial] No product export; workspace files and data persist on disk for manual retrieval. Sources: cate:arch.
The MIT desktop download is a free, ongoing tier for macOS, Windows and Linux with no paid plan, card or evaluation purchase; agent spend stays provider-side. Trial, caps and paid-evaluation questions do not apply to a free product and are answered negatively; iOS ships beta builds pending store review.
Scope
Surfaces: Cate desktop app (macOS, Windows, Linux), Cate Mobile for iPhone, Cate workspace runtime daemon (local, SSH, WSL) · Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-12 (10 days old)
Agent cross-check
2026-11-12
Provider-side subscription limits still apply to agent work. No purchase test was run.
10 atomic answers
Ongoing free [supported] Free MIT-licensed desktop downloads with no paid tier in the checked sources. Sources: cate:license, cate:readme, cate:site.
Trial [unsupported] No trial exists; the product itself is free. Sources: cate:license, cate:site.
Self host cost [partial] No license cost; the user provides their own machines and provider subscriptions. Sources: cate:license, cate:readme.
Paid only [unsupported] Not paid-only: the application downloads free of charge. Sources: cate:license, cate:readme.
Early access [partial] Desktop ships beta releases and iOS builds are versioned pre-approval; no gated early-access program is stated. Sources: cate:release, cate:iosaudit.
Free scenarios [supported] Two-person collaboration, BYO subscriptions, remote compute, mobile pairing, worktrees and review all work on the free download. Sources: cate:readme, cate:arch.
Card required [unsupported] No card is required; no billing exists. Sources: cate:site, cate:negsearch.
Usage caps [unsupported] No product usage caps exist; provider CLIs enforce their own limits. Sources: cate:usage, cate:negsearch.
Paid evaluation [unsupported] No paid evaluation exists; evaluation is the free download. Sources: cate:license, cate:site.
Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Kind
documented
Locator
Install table; What is inside; Shared workspaces and remote access
The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Beta.14 and iOS 0.1.2 (22) shipped 2026-11-12; near-daily beta cadence since 2.1.0-beta.1 (2026-10-17). Version 0.4.0 removed the bundled MCP registry and the AI-config/MCP-server subsystem.
Kind
documented
Locator
2.1.0-beta.14 and iOS 0.1.2 (22) entries 2026-11-12; 0.4.0 entry
Engineering readiness review 2026-11-03 (not a guarantee of Apple approval): iPhone-only device family, iOS 26.0 deployment target, production signing matching App Store Connect, in-app Privacy Policy and Support links. Store description frames iPhone support.
Kind
documented
Locator
Device support; SDK and packaging; Privacy policy access
Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Workspace notification contracts cover events, gating and per-setting control with one subscription per open workspace. Human permission prompts raise waitingForInput attention notifications; display is OS-native.
Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Kind
documented
Locator
Hero; download buttons; footer nav (rendered page)
The product-owned cate CLI exposes agent, review, browser, terminal, editor and document areas to callers in a Cate terminal (including agents), gated by read/control areas. Network pairing and device keys are covered by the architecture transport rules.
Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Kind
source-inspected
Locator
Grep across src/**, docs/**, ios/** at the pinned commit
Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Kind
source-inspected
Locator
AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Kind
source-inspected
Locator
gh auth status; pull-request listing and PR context
Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
The workspace runtime ships as per-architecture tarballs staged with the app and installed onto SSH or WSL machines when a workspace opens there, so local and remote follow the same path.
cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
cate browser drives workspace browser panels: list tabs, open/switch/close tabs. localhost in a browser panel means the runtime machine, routed through the workspace connection.
Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Skills install from a curated catalog into per-agent target dirs following the open Agent Skills SKILL.md folder standard; installs are recorded per workspace and uninstall cleanly. Relation context reaches turns via the per-agent promptContextHook (additional-context, plain-text or endpoint).
Kind
source-inspected
Locator
writeSkill/uninstall; registry/skills-index.json curated catalog; Agent Skills SKILL.md standard
Official Cate IDE extensions: new extensions land by PR; CI builds artifacts and publishes the catalog to GitHub Pages. Pushed 2026-10-11. No license file is published in that repository.
Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Kind
source-inspected
Locator
Usage record pricing; subscription-limit types; README Usage button
Owner 0-AI-UG; description An infinite zoomable canvas for coding; homepage cate.cero-ai.com; 2235 stars observed 2026-11-12; MIT license; default branch main; pushed 2026-11-12; not archived or disabled. Task URL github.com/eneskirca/cate returns HTTP 404; the live repository is 0-AI-UG/cate.
Anonymous telemetry posts to analytics.cero-ai.com; only packaged builds send; no file paths, project names, workspace contents, hostnames or account data. Payload carries a random install id plus app version/platform/arch/locale.
Sentry crash reporting is always on in packaged builds (dev only with SENTRY_DSN). sendDefaultPii is false; home paths are scrubbed and navigation breadcrumbs keep only the origin.
First-run welcome shows a privacy notice stating Cate collects usage data and crash reports, informational only: there is no choice, just the privacy-policy link. Shown once per TELEMETRY_NOTICE_VERSION.