UNITARES MCP server

Accountability infrastructure for long-running AI agents.

Give every process an identity. Keep claims, evidence, reviews, and outcomes connected. Recover work across restarts, context loss, and handoffs.

An agent reports that its fix is done and the tests pass. By morning its session has restarted, its context is gone, and another process has taken over the task. Who said it? What supports it? Who challenged it? What happened? Each run leaves its own log, and the answers scatter across them.

UNITARES is self-hosted accountability infrastructure for operators running multiple AI agents. Its single-operator federation kernel connects independent runtimes to one operator-controlled server over MCP or HTTP, where they share a durable record while keeping their own models, tools, and runtimes. They interoperate with each other over their own transports or A2A; UNITARES is the record behind them, not the transport between them.

UNITARES preserves accountability across discontinuities in agent identity, context, process, and time. Agent work remains attributable, reviewable, and recoverable even when the process that started it is gone.

What UNITARES gives you

came from. This is a record for attribution, not a credential; platform workload identity remains the credential layer.

• Identity and lineage — know which process acted and where inherited work

provenance outside any one context window.

• Claims and evidence — retain important findings, corrections, and their

part of the work record.

• Governed review — preserve disagreement, conditions, and resolution as

happened.

• Outcome grounding — connect predictions and check-ins to what later

checkpoints in an agent's loop.

• Runtime policy — return an action, reason, and next step at meaningful

continue earlier work.

• Reconstruction — give a successor the records needed to understand and

The claim ledger gives the evidence status of each measured result.

Together, these form an operator-owned accountability layer across coding agents, research agents, background agents, and custom runtimes. What it adds to a record of what happened is adjudication: disagreement, conditions, and outcomes bound to the process that made the claim.

Install

With Git, curl, and Docker Compose installed, one command starts the latest verified release of the local operator stack:

v=$(curl -fsSL https://raw.githubusercontent.com/cirwel/unitares/master/PUBLISHED_VERSION) && git clone --branch "v$v" --depth 1 https://github.com/cirwel/unitares.git && cd unitares && docker compose up -d --wait

Connect MCP clients at http://localhost:8767/mcp/ or open the dashboard at http://localhost:8767/dashboard. If port 8767 or 8788 is taken, set GOVERNANCEHOSTPORT and LEASEPLANEHOST_PORT; see Docker quickstart.

Shortened. The full README is on GitHub.