Agentplane is the agent-agnostic evidence layer

Use any repository-capable coding agent. Agentplane records the evidence that makes its work reviewable: task scope, approved plan, role ownership, verification, branch handoff, closure, and Agent Change Record.

Comparison matrix

Surface	Best at	Missing by itself	Agentplane adds
Agent-agnostic codegen	Generating and editing code	Durable task evidence	Lifecycle records and ACR
AGENTS.md / rules	Instructions and policy	State, approvals, verification	Commands, gates, artifacts
Git	Diffs and history	Intent, plan, verification	Evidence around the diff
CI	Automated checks	Task context and closure state	Verification evidence and ACR gate
Hosted agent dashboards	Central status or remote execution	Repo-local source of truth	Durable Git-owned evidence

Coding agents

Coding agents are responsible for changing files. Agentplane is responsible for making that work traceable after the session is gone.

Use Agentplane when you need a reviewer to answer:

• What was the task?
• Which plan constrained the work?
• What evidence proves verification happened?
• Which commit represents the work?
• Is the ACR merge-ready?

AGENTS.md and CLAUDE.md

Instruction files describe policy. They do not record whether a specific agent task followed that policy.

Agentplane keeps the policy gateway, then adds task state, plan approval, verification, finish metadata, PR artifacts, and ACR.

Git-only workflows

Git remains the source of truth for content and history. Agentplane does not replace it.

The gap is that a commit hash does not describe the agent's task, plan, verification, or policy decisions. Agentplane stores those records beside the commit so review and revert have enough context.

CI

CI proves that configured checks ran. It usually does not know why the agent changed the files or which task evidence belongs to the pull request.

Agentplane can record verification as task evidence and use agentplane acr check <task-id> --mode ci as an ACR readiness gate.

Hosted agent platforms

Hosted runtimes and dashboards are useful when you need remote execution, central queues, or sandbox management.

Agentplane OSS CLI is not a hosted agent runtime or sandbox API. It is a local-first Git evidence layer for AI work in repositories.

Hosted dashboards are useful for team visibility, shared history, alerts, and governance. Agentplane OSS keeps the durable evidence record in Git, so Cloud can sync and collaborate around the record without becoming the only source of truth.

When to use Agentplane

Use Agentplane when:

• your coding agent changes real repositories;
• reviewers need task intent, plan, verification, and closure evidence;
• AI-written code changes need a repeatable review contract;
• you want durable artifacts in Git instead of transient chat history.

Do not use Agentplane when:

• you only need a prompt playground;
• you want a hosted sandbox runtime;
• you want an agent framework to choose models and tools;
• you do not use Git-based review.

Agent-agnostic by design

Agentplane does not depend on a specific model, editor, hosted runtime, or agent product. Git stores the diff. CI runs checks. Agentplane records the evidence around the work.

Summary

Use any coding agent. Keep the evidence in Git.