knowledge runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 1 Nov 2026.
Self-hosted shared memory and docs for Claude Code, Codex and Antigravity agents, with a graph UI
What the code does
We read the source, 15 h ago · rules 995398eba69f
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.
subprocess.run(git + args, check=True, capture_output=True)
path = os.path.normpath(os.path.join(cwd, os.path.expanduser(target.replace("$HOME", home))))
env = dict(os.environ)
({"file_path": "/home/x/other"}, True), ({"command": "cat ~/.ssh/id"}, True), ({"command": ["bash", "-lc", "git push"]}, True),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to knowledge
same job, measured the same wayShared, project-aware memory for Claude Code, Codex, and other agents with human review.
Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.
One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor.
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Graph-powered code intelligence with semantic search and knowledge graph for AI assistants
Bring Claude Code, Codex, DSH, Muse, Antigravity, and Hermes into shared rooms over MCP.
Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
knowledge — questions
Answers built from our own checks of this server.