Omneum runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 29 Oct 2026.
Text-blind context control plane for AI agents. Select high-utility context under token budgets.
What the code does
We read the source, 2 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
result = subprocess.run(['runuser', '-u', ACCOUNTS[0], '--', str(RUNTIME / 'venv/bin/python'), '-I', '-B',
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.
result = subprocess.run(
subprocess.run([cmd, "--version"], check=True, capture_output=True, shell=True)
env=dict(os.environ.items()), # Convert to list of tuples for env update
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Omneum and you get told the day something new turns up.
Alternatives to Omneum
same job, measured the same wayToken and context budget for AI agents. Tracks spend and gates the session.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Project memory and a control plane for AI coding agents.
Fetch public web pages as clean, token-budgeted text for AI agents.
AI agents compare and sign up for Texas utility plans: electricity, internet, gas, water, trash.
AI agents compare and sign up for Texas utility plans: electricity, internet, gas, water, trash.
Self-hostable policy control plane for AI coding agents.
Git-backed platform for skills, tools, and context for AI agents
Omneum — questions
Answers built from our own checks of this server.