Fagan runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 18 Sep 2026.
Autonomous coding pipeline: frontier models plan and review, a local model implements, gated by TDD.
We read the source, 2 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
pr = subprocess.run(cmd, check=False, shell=True, cwd=cwd,
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run( # noqa: PLW1510 (check=False would break test fakes with fixed signatures; see backend.py test suite)
pr = subprocess.run(cmd, check=False, shell=True, cwd=cwd,
return dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
A coding and development harness on local models or hosted APIs: code, review, research, ops.
Local-first MCP server for task tracking and coordination of autonomous AI coding agents.
CroweLM tiers and frontier engines by name, metered per Crowe Logic plan. Ask, list models, account.
Local proof facts for AI coding clients: intent, tests, Graph Ops, and review evidence.
Review coding-agent plans on demand with peer models, attributed findings, and a structured verdict.
Delegate complete coding tasks to the local OMP default model and inspect the result.
Answers built from our own checks of this server.