---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/kandev-vs-podium/"
data_url: "https://podium.do/compare/agents/kandev-vs-podium/data.json"
generated_at: 2026-11-22
last_checked_at: 2026-11-13
last_cross_checked_at: 2026-11-21
oldest_checked_at: 2026-11-06
publisher: "Podium"
---

# kandev vs Podium

> Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. Sourced findings follow the same evidence rules for Podium and its competitors. Facts labeled Podium team research come from Podium's own team and have no linked source. None of this removes the conflict of interest.

> Based on data from adecomparison.com by Podium (https://adecomparison.com; source repository https://github.com/madeinorbit/ade-comparison, snapshot 4322f0c of 2026-11-22), used under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Source links and check dates are kept. Podium arranges the findings into pairs, applies its publication checks, and added its own research where marked "Podium team research". Data license terms: https://github.com/madeinorbit/ade-comparison/blob/4322f0c035f303791413639d1462a138443d8c1e/DATA-LICENSE.md

48 criteria sourced for both products; 37 criteria also agent cross-checked for both. 50 criteria with a sourced finding for at least one product. "Sourced" findings passed publication validation. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. Humans approve the rubric, templates and prototype; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent.

Each row gives the finding's status, support, check date and answer. Scope, limitations, atomic answers and sources for every finding are in each product's document, under the criterion ID. Judgment rules are in the rubric.

- kandev source checks: 2026-11-13. Details: https://podium.do/compare/agents/products/kandev/index.md
- Podium source checks: 2026-11-06. Details: https://podium.do/compare/agents/products/podium/index.md
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Canonical HTML: https://podium.do/compare/agents/kandev-vs-podium/
- Machine-readable JSON: https://podium.do/compare/agents/kandev-vs-podium/data.json
- Methodology: https://podium.do/compare/agents/methodology/

## Access and agent choice

### ACC-01: Client access

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Browser is the primary client (served at localhost:38429, also reachable from phones over VPN/tunnel); Tauri desktop ships macOS arm64/x64, Linux x64/arm64 and Windows x64 installers; kandev launcher CLI runs and manages the backend; no native mobile app or editor extension exists in this release.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium ships desktop, CLI and browser clients, including phone-browser control. The native iPhone app is private beta; the complete download offering contains no native Android app.

### ACC-02: Agent and model choice

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. About 25 named ACP/CLI harnesses (Claude Code, Codex incl. experimental app-server, Copilot, Gemini, OpenCode, Pi, Cursor, Grok, Antigravity and more) launched with native logins; any CLI can also run via PTY passthrough; per-step profiles allow mixing harnesses in one workflow.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium launches the native Claude Code, Codex, Grok, OpenCode, Cursor and Pi CLIs in persistent terminals on machines you control. The 0.2.0 release calls Pi fully supported. Models come from each harness catalog, and capabilities differ per harness: Pi declares no quota, handoff or hooks. Mixed-harness operation was not exercised.

### ACC-03: Subscriptions, API keys and vendor credits

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Bring your own agent subscription via native CLI login; API keys via executor secrets/env (e.g. OPENAI_API_KEY) and PATs for external clients; no Kandev vendor credits, billing or local-model route; multiple profiles hold distinct credentials.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions (via native login or a managed setup-token) and local ChatGPT/Codex login are supported paths, alongside Anthropic and OpenAI API keys. Docs list billing and hosted metering as not implemented product claims.

### ACC-04: Onboarding and project prerequisites

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Install via Homebrew/Scoop/npm, add a local repo, configure an agent profile and start a first task; local and GitHub-backed repos supported; repository-free tasks exist; SSH plus service guides cover own-server onboarding; no managed-cloud path exists.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Docs describe a first-run flow (install, podium, register a Git repository, confirm a detected logged-in harness) and a headless VPS installer with machine joining. Setup time and failure rate were not measured, and no self-serve managed cloud setup is documented. The current README and installation guide use podium.do/download and podium.do/install.sh as the canonical stable entrypoints.

### ACC-05: Programmable access

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Complete WebSocket action API plus REST /api/v1, versioned Go/npm plugin SDK, external MCP (streamable HTTP + SSE) for create/manage from outside agents, incoming authenticated webhooks and outgoing notification webhooks; launcher CLI covers run/service management.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The podium CLI covers issue create, show, update, claim, dependencies, artifacts, session send/status/read/stop and review actions, and the server exposes the same issue commands as a bearer-token MCP tool endpoint. No documented public HTTP API, SDK or webhooks were found.

### ACC-06: External tools and extensions

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Workspace MCP definitions (remote, managed npm, existing executables over stdio/HTTP/SSE) selectable per repository/profile/task/session; built-in packages with workspace policy; plugin marketplace plus sideloading; utility agents, custom and saved prompts; MCP/tool policy caveats documented.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Podium gives agents its own issue tools over CLI and MCP, and agent profiles import and export Claude Code agent files. No Podium documentation for user-configured MCP clients, plugins or custom tools was found.

### ACC-07: Client implementation

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Desktop is a Tauri shell (Rust launcher, system WebView) over the backend-served SPA; mobile clients are the responsive web app plus a shipped PWA manifest; no native mobile or Electron client exists.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Desktop releases use a Tauri 2 shell that serves the Podium web UI; mobile source uses Expo and React Native. A native iPhone release is described as private beta.

## Planning and context

### PLAN-01: Intake and external tracker relationship

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Native task creation plus prompt intake (Quick/Config chat), provider issue/MR import and watches from GitHub, GitLab, Jira, Linear, Sentry and Azure; Kandev tasks own workflow state while provider links are retained; PR-open/PR-merged triggers shipped, push/CI triggers in progress.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium issue records are native and authoritative with stable references, CLI creation and editing, and agent-driven filing from conversation. The in-product assistant has Linear search, create and move tools when a key is configured, but no import or two-way tracker sync was found.

### PLAN-02: Durable task plans

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. One structured Markdown plan per regular task with Plan panel, version history, compare/revert, plan-mode Implement flow, human and agent (task-MCP) editing, and persistence across restarts; amendment while running is supported via moves and wait steps.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Issue brief, acceptance criteria, state paragraph and todos persist on the durable issue record. Release 0.3.0 removed the separate design and notes fields and appended their text to the brief. On the human issue page the title, description and acceptance are editable and the brief is read-only; agents edit the brief and other fields through issue commands.

### PLAN-03: Hierarchy, dependencies and evolving scope

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. One-level subtasks with workspace inheritance choice, stored blocker/dependency relations with cycle rejection and a dependency-graph view, WIP-gated moves, and workflow changes that preserve task identity; arbitrary-depth trees and epic promotion are Office-only in-progress work.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium supports persistent parent and child issues, phases and typed dependency links, including reparenting an existing issue without replacing its identity. Since 0.3.0 issue types are task, phase and decision: epic and other kinds are retired, and any issue with children acts as a parent. Dependency types are fixed to blocked-by, related, discovered-from, supersedes and duplicates. Cycles are refused and docs list an open blocker as a reason an issue cannot start. No mandatory workflow preset applies in the baseline.

### PLAN-04: Shared context and memory

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Workflow/custom prompts, per-task documents with revisions, retained session conversations with resume-time history injection, utility-agent summaries for handoff, and takeover that preserves context; no product-managed cross-session memory outside experimental Office.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. v0.3.0 routes Podium issue instructions and relay environment through terminal and engine session launch. Claude stream sessions use appended instructions and boundary callbacks; Codex server sessions use developer instructions, Grok ACP uses rules, and OpenCode uses the prompt system field. Claude and Codex boundary hooks can re-prime after compaction. Transcript mirroring is on by default; full-text indexing needs the command-palette flag, which defaults off. Agent profiles can carry markdown instructions. Curated memory, skills and memory correction or deletion controls remain unestablished. No instruction-delivery or compaction scenario was run.

### PLAN-05: Architecture and API awareness

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Agents work with full repo checkouts and provider-linked context (issues, PRs, Sentry) while Kandev itself provides diff/review surfacing, divergence detection and human gates; no product-owned code index, semantic retrieval, citation model or spec-conformance enforcement exists.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Not established. Podium mirrors daemon transcripts by default, keeps a full-text index only when the command-palette flag is on, and stores session attachments. No repository code search, architecture awareness or API retrieval feature was found.

### PLAN-06: Native issue management and idea backlog

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Full native task lifecycle on kanban/pipeline boards (create, edit, discuss, assign, search, archive, reopen, workflow views, dispatch control, task/session separation, durable states) without any external tracker; labels and full dependency editing are Office-surface in progress.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes native issue creation with an optional start flag, separate dispatch, editing, comments, labels, assignment, search, board filters, archive, sibling ordering and an issue tree. Issue records have their own identity separate from sessions and stages are durable. The idea-to-mission scenario was not run. v0.3.0 refuses an agent close or done update while issue sessions are computing unless --confirm-interrupt is supplied; guidance says to request review and close only on user instruction.

### PLAN-07: Agent-native issue operations

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Agents read, create, update, move, link and report on the same durable task IDs humans use through documented task-MCP tools, with attribution, workspace policy and cycle/permission guards; direct stop and cross-task message tools are scoped accordingly.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. CLI and MCP address the same canonical issue records for reads, creation, edits, claims, state, dependencies and artifacts. Relayed agents have worker capability scoped to their issue subtree, with --outside-scope confirmation for other existing issues. attachSession is not subtree-gated, but direct rehoming from a real issue is refused and an agent attach naming a Proposed target is refused. That does not make every Proposed subtree inert: operator attachment or spawn-time cwd binding can leave a session attached to a Proposed issue; newSubissue without targetId then bypasses the proposed-parent guard, creates a human-audience backlog child and attaches the existing session. This path remains at v0.3.0 source and was not exercised live. Concurrent-edit handling remains unknown.

### PLAN-08: Living product specifications

- **kandev**: Agent cross-checked (agent-cross-checked); support: unsupported. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Per-task plans and documents with revisions exist, but no persistent cross-task product-specification system with attributable upkeep, implementation links, retrieval, drift detection or review integration was found in the pinned release.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The spec CLI and service (living specs under pspec with stable SP IDs) are in v0.3.0. Specs is an experimental, default-off feature listed on the edge channel: the flag controls the Specs UI, the spec line in CLI help and whether agents are told about the spec CLI. The podium spec command itself is dispatched, and the server specs service has no flag check, so direct CLI use does not need the flag. This agrees with the docs, which call specs not baseline rather than blocked. Not run end to end.

## Coordination and automation

### COORD-01: Parallel work

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Independently running named sessions share a task environment while multiple tasks run in parallel; automation concurrency caps and one-active-run semantics bound load; boards, stats and Inbox expose running, waiting, failed and finished work.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Docs and release notes describe many sessions running as independent terminals, one worktree per issue, and several paired machines under one server, with session and issue state visible on the flight deck, board and CLI. Agent-initiated spawns are limited to 10 per target issue per UTC day. Achieved concurrency is unmeasured.

### COORD-02: Ownership and dispatch

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Human and agent assignees, automation queues with concurrency limits, compatibility routing for profiles/executors, and cycle guards; ownership is assignment-based with takeover-by-reassign and no exclusive lock or duplicate prevention beyond documented checks.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues carry an assignee, claim sets assignee and in_progress, a coordinator session can be set per issue, sessions have seats, and work can be placed on a chosen machine or agent profile. claim has no exclusivity check of its own, locks are advisory leases and Podium does not serialize agents editing one worktree, so exclusive ownership is not enforced.

### COORD-03: Inspectable delegation and communication

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Product task-MCP (spawn/message/stop scoped tools) lets sessions delegate to other sessions with attribution; coordinator-led teams are shipped for kanban delegation while persistent cross-harness Office teams remain experimental.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium orchestrates delegation itself: podium agent spawn starts a full child session on an issue with a chosen harness, model, effort or agent profile, mail carries messages, and bounded await reports the child result. Children are real sessions shown as seats on the flight deck. Agent-initiated spawns take a daily budget per issue. A complete delegated task with retained child findings was not run.

### COORD-04: Unattended triggers

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Schedule (@every/cron presets), authenticated webhook and GitHub PR triggers create hidden or normal-task runs from the backend with concurrency limits and retry policy; fixed-cron timezones are not honored and push/CI triggers are stubs.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The server owns a scheduler for cron and one-time automations that spawn agent sessions, skipping overlaps and not backfilling occurrences more than an hour late. The Automations UI is an edge-visibility feature that defaults off and docs list automations as non-baseline. Agents can subscribe to issue and session events.

### COORD-05: Intervention and attention

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Stop/resume/steer (with queued messages), clarification and permission questions with attachments, Inbox history, failure alerts and desktop notifications, plus retained SQLite history; generic pause and escalation chains are not established.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Chat and native CLI views share a session. v0.3.0 defaults human controller chat to steer and immediately types it into running Claude Code, Codex, Grok and OpenCode TUIs that declare native busy-input queuing; undeclared harnesses wait for a boundary, and compaction waits. Mail and automation keep when-ready delivery. Stop, resume, questions, decision issues and offers remain available. This is inspected implementation, not a cross-harness runtime parity result.

### COORD-06: Fleet and epic management UI

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Multi-workflow kanban/pipeline boards with step counts, PR badges, dependency-graph view, Inbox attention, stats workload and guarded move-error handling; blocked/failed/awaiting states are visible per task while cross-epic roll-ups stay experimental.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Release 0.3.0 ships a flight deck showing a whole mission in one view: phases, every task and its state, who works on what, what is blocked and by what, and proposals. Done work stays visible. The CLI prints the same snapshot. The waterfall source is dormant and the Timeline view was deleted, so per-task timeline history is not shown. The shared 12-task UX scenario has not been run.

### COORD-07: Workflow flexibility and orchestration visibility

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Quick tasks, subtask-grown scope with identity-preserving workflow changes, templates, configuration-chat natural language, per-agent configuration, in-run move options, live session roles and retained relationships are all shipped; discoverability is docs plus command palette and external auth needs PAT setup.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. A quick task can be an interactive session or an issue; an issue can grow into a mission by gaining children while keeping its identity; no mandatory workflow preset applies in the baseline. Per-agent harness, model and effort are chosen at spawn or through agent profiles, and the deck shows seats. The coordinator-with-two-reviewers scenario was not run.

## Execution and reliability

### RUN-01: Laptop-independent execution

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Local host, worktrees, Docker, Kubernetes, SSH and Sprites executors with a self-hostable control plane (binary, service, Docker, k8s example); no vendor cloud exists; backends run as persistent services so any device can reconnect and work survives client disconnects.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. The published Podium execution choices are local user machines and a user-owned VPS or paired machine. No vendor-operated agent host is in the complete download offering.

### RUN-02: Workspace and process isolation

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Worktree-per-task file isolation plus Local checkout, container (Docker/Kubernetes) boundaries and SSH-remote hosts with documented trust limits; no VM or OS-sandbox boundary; network/secret/process limits are executor-specific, never a hostile-code sandbox claim.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.

### RUN-03: Recovery, expiry and continuity

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. SQLite-persisted state with lazy session recovery (native ACP resume or history injection) after restarts, reconnect-safe clients, backup snapshots, and documented caveats on summarization loss and non-idempotent creation; provider sandbox expiry stays provider-owned.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies; a stopped session keeps its transcript, branch and resume reference. Release 0.2.0 says a failed update rolls back and running sessions keep running through the upgrade; database rollback remains a manual restore. Terminal reattachment goes through the driver adopt contract with process-identity and observation-lease checks. Worker-crash and multi-day behavior were not tested.

### RUN-04: Development environment reliability

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Prepare scripts, ignored-file seeding, secret injection, port forwarding and per-profile remote setup are shipped with backup snapshots; product-level cache management, install dedup and collision handling are not established.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Only machine setup is documented: the installer installs missing runtime tools and pairs a host, and the state directory holds server-managed secrets. Dependency caching, services, ports and automatic repair for project environments were not found.

### RUN-05: Limits and failure handling

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Automation concurrency caps, one-active-run semantics, experimental Office/coordinator spend ceilings, retry policies and provider-failure surfacing bound load; generic turn/token/time caps and scheduler SLAs are not established.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium exposes retryable errors, optional auto-continue with backoff, bounded waits and provider quota. Claude stream and hosted headless drivers enforce a supplied turn deadline, with no deadline when timeoutMs is absent. The one-shot headless server runner supplies its budget, default ten minutes. Agent spawns have a daily per-issue budget. Operator-configurable task-wide turn, token and spend caps remain unestablished; quota display is not enforcement.

### RUN-06: Truthful status and operational statistics

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Boards, session states, Inbox, lifecycle messages, background-work history, debug logs, database views, OTLP tracing and workspace stats (task/agent/repo/time, failure and approval states) keep status consistent from the database; stats are on-demand with no realtime push.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Podium offers local logs and crash export, structured session status, issue stats, a usage and analytics sheet with hourly list-price cost, per-task costs and host load panels. The 0.3.0 notes report a vendor benchmark of about 330 MB server memory against about 1.2 GB for an earlier Podium build, and 8 to 52 percent faster start; the method is published in the repository and was not reproduced here. Usage export and cross-reconnect consistency were not established.

### RUN-07: Per-task API and compute cost

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Token/spend visibility comes from chat footers, workspace stats and optional session-cost/provider-usage plugins plus experimental Office budgets; per-child/per-epic roll-ups, billed reconciliation, alerts beyond experimental ceilings, export and drill-down are limited or absent.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Since 0.2.0 Podium shows what each task costs, on the task header and the usage sheet, with per-session rows and descendant rollups. The 0.3.0 deck adds a mission cost chip. Figures are token estimates at public model list prices, not subscription invoices or provider bills.

### RUN-08: Compute-aware scheduling and verification

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Parallel sessions/tasks with automation concurrency limits, automation queueing, exact-run cancellation and resume/retry recovery are shipped; host-aware limits, check reuse/dedup, fairness, backpressure and merge queues are not established.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium reports host memory, load and disk, auto-hibernates idle sessions under pressure, and provides named advisory resource leases. The merge-queue panel was removed; a shipping queue remains behind the Shipping flag. Concurrency limits and bounded test queuing were not established.

## Human collaboration and control

### TEAM-01: Live human collaboration

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Shared boards, task conversations, comments and takeover (reassign plus continue) let successive colleagues direct the same work with attribution; simultaneous co-prompting with ordering/conflict handling and presence are not established.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share handlers and a Members settings section with invites and admin or member roles exist; they do not establish a finished human collaboration workflow. Docs say small teams can share an instance but the interface prioritizes one operator.

### TEAM-02: Roles and access boundaries

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Admin/member/guest plus instance-operator and org-admin tiers, unit-based workspace reach, invite/disable lifecycle and revocation are documented on the experimental path; SSO is explicitly local-only for now and SCIM-style provisioning does not exist.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Podium defines member/admin instance roles and admin-only membership management. The released client authentication uses password-backed sessions and paired-device tokens without enterprise SSO.

### TEAM-03: Approvals and temporary access

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Agent permission requests (allow/deny per tool use), per-decision confirmation sheets with secret redaction, human-gated workflow steps and provider-enforced PR merge gates; revocation via user/token disable, tunnel stop and session stop; defaults and safer modes are operator-chosen.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Agent-session management requests go through an operator approval broker with approve and deny; the privacy docs say lifecycle commands and automation requests may require operator approval. Harness permission prompts appear as a Permission needed state; credential copying during pairing is a per-grant opt-in. Command-level policy enforcement beyond the harness own modes was not established.

### TEAM-04: Decision and activity history

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Attributed actions, approvals, plan revisions, discussion and immutable lifecycle templates persist across users and sessions with gist-based sharing and backup portability; no formal audit model, retention schedule or history export is established.
- **Podium**: Sourced (sourced); support: partial. Checked 2026-11-06 (16 days old); not separately cross-checked. Issue actions, approval steps, comments and mail are recorded server-side. Issue activity events, including approval steps, are pruned by the server's janitor once they are older than 14 days or fall outside the newest 50,000 rows. That policy does not define all content retention, export or tamper-evident audit guarantees.

### TEAM-05: Review experience and guidance

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Board review columns with PR badges, diff/Changes panels, walkthroughs, plan comments, feedback-to-agent and re-review loops, keyboard shortcuts and an extensively documented narrow-screen phone flow; no formal next-action engine or effort metrics.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Review is a documented loop: issue stage review, diff and checks, artifacts, offers with merge or send-back buttons, and a Tray of review-ready work. Release 0.3.0 adds quoting text from a reply or review finding into the next message and a full-height reading view with an outline. The board has a key map with a help sheet. Guided-review quality and narrow-screen use were not measured.

### TEAM-06: Colleague takeover and continuity

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Takeover is reassign plus continue with no lock: successors keep task, session history, decisions, artifacts and executor context, with attribution and documented summarization/idle-boot caveats; cross-harness transfer works via profile handoff.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The durable issue, session transcript, artifacts and mail persist for any later agent, and a live session can be handed to another machine in an edge feature. Colleague takeover by a second person was not established.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Diffs, task documents, walkthroughs, plans, previews, tunnels and PR evidence persist with tasks and sessions; image/file attachments supported; no recordings, no cross-task gallery, no test-report collection.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Artifact commands store immutable server-side copies of issue-linked files, including images, video, HTML and documents, which render in the issue sidebar and offers and stay readable after the worktree is gone. Each task has an artifacts page grouped into screens, documents and reports, with filters and search. Revision linking remains untested.

### SHIP-02: Verification and spec gates

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Tests/lint/CI surface through provider checks and agent runs with human gates and provider-enforced merge blocking; agent assertions never count as gates; no product-run verification and no persistent-spec conformance checks exist.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. In the experimental Shipping path a configured validation profile runs before landing (default argv bun run test with a 10 minute timeout) and a failed validation holds the order. Lint, type, CI and spec conformance gates and independent review requirements were not found as product-enforced policy.

### SHIP-03: Git and pull request workflow

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Integrated Changes-panel Git (stage/commit/push/pull/rebase/merge with guards) plus agent-shell Git, full GitHub PR lifecycle with auto-fix rounds, GitLab MR support, Azure create-only PRs, and divergence-safe compare/publish/restore flows.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Issues own branches and worktrees, and issue actions rebase, open a pull request with gh (pr create --fill) and merge, subject to a merge-style setting (ff-only by default, with auto-rebase before merge). Podium does not resolve branch conflicts, and PR review comments and CI response were not established.

### SHIP-04: Merge and deployment authority

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. PR/MR approvals submittable where permitted, provider-gated merges from the task panel, exact-revision head checks; no release management, no deployment authority and no deployment rollback exist.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The operator accepts work through offers and runs the merge action under a branch merge-lock; in the experimental Shipping path approval is frozen to an exact head and delivery lands on a local target branch by default. Release and deployment are not product features found in the sources.

### SHIP-05: Completion evidence and rollback

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Task-to-commit/PR links, Done states, retained conversations/diffs/lifecycle records and guarded publish/restore with recovery branches; no deploy rollback and no general approval-invalidation model.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Shipping orders record approved base and head SHAs, tested integration SHA, landed ref and validation result in a durable delivery receipt, and stale approvals hold the order. Shipping is experimental. The pr action records a PR URL on the issue. Build and deployment links and rollback were not found.

### SHIP-06: Batch review and high-volume shipping

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Boards, grouping, stats and per-task request-changes/exact-revision flows support volume; no batch review queue, risk filters, cross-task findings roll-up, merge queue or check dedup exist.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. The shipping service records revision-specific approval, configured validation and delivery receipts. The Shipping panel is an experimental edge toggle, off by default; the separate Queues panel was removed.

## Ownership, privacy and economics

### OWN-01: Source and license

- **kandev**: Agent cross-checked (agent-cross-checked); support: supported. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. AGPL-3.0 covers the main application (backend, web, CLI, desktop, plugin SDK) in one public repository at the pinned commit; no proprietary or source-available component split was found; 1126 stars measure attention, not license parity.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. The public repository is licensed Apache 2.0, and the website presents Podium as an open-source agent development environment. Hosted extensions and hosted-service terms are not established.

### OWN-02: Hosting and exit

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Fully self-hostable (binary, service, Docker, k8s example, source) with SQLite/Postgres data, backup download/restore, workflow YAML portability and git-held code; no vendor account exists so nothing is held hostage; per-task portable export is limited.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Local desktop and self-hosted installs run on user-controlled machines with a documented state directory. The docs describe stopped full-state backup and automatic pre-migration database-only snapshots retaining three copies. Those snapshots omit artifacts, transcripts, uploads, configuration and secrets; no portable structured export/import contract was established.

### OWN-03: Data handling and telemetry

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Self-hosted data stays local with encrypted secret store, scoped credential leases and redacted sharing; no telemetry is collected so no opt-out or consent prompt exists; provider-side model data use follows the CLI vendors, not Kandev.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Docs state repositories and native harness credentials stay on machines you control and server state lives in a documented directory. Since 0.2.0 a daily usage report is on by default and can be turned off; crash reports stay opt-in. Usage reports carry an install id, schema version, Podium version, OS, architecture, bucketed install age and machine count, session counts per harness and whether issues were used. Crash reports carry the same install id, versions, OS and architecture, a fixed error type and up to 20 stack frames, each with a Podium source file path, line and function when there is one; error messages and frames outside Podium are dropped. Neither tier sends prompts, transcripts, your code or paths outside the Podium source tree. Model-provider handling is the harness own. Hosted analytics and website analytics are separate paths.

### OWN-04: Price and included usage

- **kandev**: Agent cross-checked (agent-cross-checked); support: supported. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. The ADE itself is free of charge: AGPL-3.0 open source, no pricing page, no plans, seats, trials, overages or taxes; model and compute spend goes to third parties chosen by the operator.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. No Podium price is published: podium.do/pricing returns 404 and the docs list billing as not implemented. The software is open source and free to download; model and compute costs are the user's own.

### OWN-05: Scenario cost and controls

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Fixed ADE cost is $0 for one, two and five developers including collaboration, review and remote-execution features; variable model/provider/Sprites spend is operator-paid and unstated by Kandev; stats and optional cost plugins reconcile observed use.
- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-06: Availability and support

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. Public pre-1.0 releases (v0.101.0 on 2026-11-11, active main-branch commits), no access gate, community support via Discord and GitHub issues with no SLA, no status page, and backup/workflow portability for exit.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is pre-1.0. Stable v0.3.1 (2026-11-06), an update fix, follows v0.3.0 (2026-11-05), v0.2.0 (2026-10-11) and v0.1.0 (2026-08-21), with edge and dev prerelease channels. Windows and Linux desktop are Experimental, the native iPhone app is in private beta and hosted Podium is unconfirmed. Support runs through GitHub issues, Discord and private vulnerability reporting.

### OWN-07: Enterprise assurance

- **kandev**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-08: Useful free tier and evaluation access

- **kandev**: Agent cross-checked (agent-cross-checked); support: supported. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. The whole product is free and open source indefinitely (self-hosted, no card, no sales approval); every scenario including two-person collaboration, BYO subscriptions, remote compute, mobile browser, issue management and review works at $0 ADE cost with provider-side caps only.
- **Podium**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Podium is open-source Apache-2.0 software, and the download page calls it free and open source. Download links for macOS, Linux and Windows redirect to GitHub release assets without a login (observed by HTTP requests; not installed). No Podium charge is documented for self-hosting; agent provider usage is separate. The native iPhone app is private beta and hosted access is unconfirmed.

### OWN-09: Pricing transparency

- **kandev**: Agent cross-checked (agent-cross-checked); support: partial. Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-14. ADE-side pricing is fully stated ($0, no units, limits, overages, markups, commitments or sales unknowns); third-party model/compute pass-through is correctly outside Kandev pricing.
- **Podium**: No sourced public finding (not-published); support: not-published. No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
