UNITARES runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 7 Nov 2026.
Accountability infrastructure for long-running AI agents. Shared memory is a provenance graph.
What the code does
We read the source, 1 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.
File.exists?("/.dockerenv")
subprocess.Popen(
case System.cmd("git", ["-C", __DIR__, "rev-parse", "--short", "HEAD"],
path = os.path.join(sock_dir, name)
return yaml.load(text, Loader=_StrictLoader) # noqa: S506 - SafeLoader subclass
BEAM-owned dialectic session creation: guarded INSERT into `core.dialectic_sessions` + immediately start a liveness watcher, so a session
<script src="https://d3js.org/d3.v7.min.js"></script>
# Install build dependencies for pgvector. Use $PG_MAJOR (set by the upstream # postgres base image) so the dev headers always match the base PG version. USER root
sys.exit(run(dict(os.environ)))
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 UNITARES
same job, measured the same wayPersistent memory infrastructure for AI agents. Identity, knowledge graph, and search.
Local shared memory for AI coding agents: SQLite notes with writer provenance, undo, search.
Geniffy is the memory infrastructure for AI applications and agents.
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
Persistent, structured project memory for AI coding agents, stored locally in SQLite.
Long-term memory for AI agents: graph memory with Hebbian learning, shared by Claude, Codex and co.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
UNITARES — questions
Answers built from our own checks of this server.