Lians Agent Memory MCP server

Recover the task. Reject stale state. Block unsupported done.

Quickstart · Why Lians · ContinuityBench · Install · Docs · Issues

Lians Guard

The current-state and completion guard for AI coding agents.

Lians recovers interrupted agent work, rejects stale task state, and blocks done until the current task is ready for human review.

Your agent can forget the chat. It cannot forget what is finished, what

changed, or what still has to pass.

Codex sessions.

• Recover. Resume a bounded current task across supported Claude Code and

so old evidence is not silently reused.

• Reject stale state. Bind checkpoints to current repository and task state

and keep the gate closed while work is missing, unknown, failed, or blocked.

• Guard completion. Separate measured evidence from an agent's own claims

claim that the work is correct, approved, or safe to deploy.

• Require review. READY FOR HUMAN REVIEW is a handoff to a person, never a

provider API key.

• Stay local. The free recovery path needs no Lians account, AI password, or

Lians works with your existing AI account and editor. It does not replace your model, Git, CI, repository instructions, or human review.

Two layers, one agent loop

The open-source Lians Guard layer lives inside Codex through MCP, skills, hooks, and repository state. It remembers corrections and exposes evidence without taking over the model. The optional Lians Mission Control beta is the local control layer: give it one mission, let it choose a bounded Codex route, and require a real verifier before it returns PASS.

On supported Codex versions, one Mission Control mission now uses one Codex app-server thread instead of starting a new process and replaying a summary for every stage. Codex still owns authentication, tools, sandboxes, and execution; Lians owns the durable mission, usage policy, and receipt. App-server is currently experimental, so the one-shot adapter remains available.

Inspect the Mission Control source, read the bridge boundary, or follow the external proof-gate protocol.

One clear result after every agent session

RECOVERED
Task: Fix OAuth callback handling
Next: Re-run the callback integration test

STALE
Reason: The authentication requirement changed after this checkpoint

BLOCKED
Missing: OAuth callback integration test
Untrusted: "tests passed" was reported by the agent, not measured

READY FOR HUMAN REVIEW
Measured locally: callback tests passed
Measured by CI: required checks passed

Shortened. The full README is on GitHub.