Tirith

Coordination server for parallel coding agents: claims, contracts, notices, and memory notes.

OtherRustv1.2.0
Tirith

Tirith

Coordination server for parallel coding agents.
Claims, a task board, interface contracts, change notices, a decisions log, path-scoped memory notes, and agent messages, over MCP.

Run five or ten coding agents on one repository and they edit the same files, rename things others depend on, and build both sides of an interface to different shapes. Tirith is a small daemon they all talk to: an agent claims files before editing, gets the notices, contracts, decisions, and notes for those files back with the claim, and publishes the shape of an interface before either side implements it.

It works with anything that speaks MCP, over stdio or HTTP: Claude Code, Cursor, Codex, LangGraph, CrewAI, or a plain script.

It also remembers. Agents leave notes scoped to repository paths, so what one agent learned about a file reaches the next agent that claims it. Tirith stores no conversation history and no embeddings.

Status: v1 shipped. Every primitive, the CLI, persistence, and the dashboard are built and tested, against the definition in ADR-0013; tool schemas follow semantic versioning.

Install

macOS and Linux:

curl -LsSf https://eabz.github.io/tirith/install.sh | sh

Windows (PowerShell):

irm https://eabz.github.io/tirith/install.ps1 | iex

With cargo (the package is tirith-mcp, the binary is tirith):

cargo install tirith-mcp

Already installed? tirith update replaces the binary in place with the latest release. Prebuilt binaries for macOS, Linux, and Windows on x86_64 and ARM64 are on the releases page; every option is in docs/1-about/05-installation.md.

Listed in the MCP Registry: mcp-name: io.github.eabz/tirith.

Quick start

Register tirith stdio with your client, the same way as any other stdio MCP server. It starts the repository's daemon the first time a session needs it, replaces a daemon of another version, and proxies to it after that; nothing has to be started by hand.

ClientSetup
Claude Codeclaude mcp add tirith -- tirith stdio
Cursor.cursor/mcp.json: { "mcpServers": { "tirith": { "command": "tirith", "args": ["stdio"] } } }
Codexcodex mcp add tirith -- tirith stdio
LangGraph, CrewAI, curlconnect over HTTP, see docs/2-examples/02-client-setup.md

The daemon serves MCP at http://127.0.0.1:7477/mcp and a live dashboard at http://127.0.0.1:7477/. State is written to .tirith/ in your repository: contracts, notices, decisions, and memory notes are meant to be committed; .tirith/runtime/ (claims, tasks, messages) is gitignored by a .gitignore Tirith writes itself.

Every agent passes a stable agent name with each call. That is the only convention it has to follow.

What it does

PrimitiveToolsPurpose
Claimsclaim, release, renew, claims_listLease files or directories before editing. Overlaps are refused with the owner, reason, and expiry, or waited out server-side with wait_secs. Leases expire if the agent dies, and the agent is told on its next call.
Task boardtask_create, task_pull, task_update, task_listTasks with priority, owner, and dependencies. Agents pull the next unblocked task, skipping tasks another agent holds, and can wait server-side for one with wait_secs; a task whose owner goes silent returns to the board.
Contractscontract_publish, contract_get, contract_listInterface shapes published and versioned before implementation. A new version notifies its consumers automatically.
Change noticesnotice_publish, notice_list"Renamed X to Y, these paths are affected." Dependents get them in the brief that comes back with a claim, once each.
Decisions logdecision_record, decision_listSettled choices with rationale, so nothing is decided twice.
Memory notesmemory_write, memory_read, memory_search, memory_deleteLessons, traps, and handoffs scoped to repository paths. Committed Markdown, searchable, and delivered to whoever claims the paths a note is about.
Messagesmessage_send, message_listShort notes between agents, delivered on the recipient's next call, so any MCP client can take part. Runtime only.
StatusstatusCounts, persistence and load problems; verbose adds who holds what.
GuideguideWhat Tirith is for, the working loop, and which tool a situation calls for; topic narrows it to one primitive.

Twenty-three tools, each with a description of every parameter, MCP annotations, and an output schema. Every result is JSON with a status field, lists are paged, and any result may carry lost (a lease that ended) or inbox (messages waiting). The full reference, the single source of truth for tool schemas, is docs/1-about/04-primitives.md.

Example

Two agents, one directory. The second is refused with enough information to decide what to do next:

tirith claim --agent alice --reason "refactor session handling" src/auth/
# ok       alice  src/auth  expires 04:14:34Z

tirith claim --agent bob --reason "fix login redirect" src/auth/login.rs
# conflict src/auth/login.rs overlaps src/auth (alice: "refactor session handling", expires 04:14:34Z)

A note left for whoever edits a path next. Alice writes it once; it comes back on Bob's claim without anyone searching, as an excerpt, never a body:

tirith memory write --agent alice "Session ids are opaque" -k gotcha --path src/auth/ <<'NOTE'
Tokens are opaque strings. Compare them, never parse them.
NOTE

tirith release --agent alice
tirith claim --agent bob --reason "fix login redirect" src/auth/login.rs
# ok       bob  src/auth/login.rs  expires 04:14:34Z
# memory:
#   session-ids-are-opaque gotcha   04:04:34Z  paths src/auth  Session ids are opaque: Tokens are opaque strings. Compare them, never parse them.

The full walkthrough, with contracts, notices, and the same calls over raw MCP, is docs/2-examples/01-two-agents-demo.md; the script is examples/demo.sh.

CLI

Every tool has a subcommand; the CLI uses the same MCP path agents do.

tirith serve                               # run the repo's daemon by hand
tirith stdio                               # per-session shim clients spawn; starts the daemon if needed
tirith update                              # replace the binary with the latest release
tirith status                              # counts, and who holds what
tirith guide [topic]                       # what Tirith is for, and which tool fits
tirith claim | release | renew | claims
tirith task     create | pull | update | list
tirith contract publish | get | list
tirith notice   publish | list
tirith decision record | list
tirith memory   write | read | search | delete   # body from --body, --file, or stdin
tirith message  send | list                # talk to other agents; the inbox shows on any result
tirith lead log                            # the swarm lead and its policy's decisions
tirith lead human                          # items waiting for you, most agents blocked first
tirith lead human done <id> [--reply TEXT] # answer one; the reply reaches its sender
tirith tray                                # macOS only: menu bar icon listing every daemon
tirith tools                               # list tools with descriptions
tirith call <tool> '<json>'                # call any tool directly

--agent sets your name, --json prints the raw result, and non-ok outcomes exit with status 1.

Swarm lead and escalations

The session that spawns other agents claims the reserved path .tirith/lead and becomes the swarm lead; status and the dashboard show who holds it. The daemon then handles routine escalations with fixed rules, without spending an LLM turn:

  • What escalates: a task set to blocked (its note is the reason), or the third refusal of the same claim within 360 s. A message to the lead is never an escalation.
  • Where it goes: while there is a lead, to the lead's inbox as a message from tirith, tagged "may need the human" when it mentions credentials, permissions, spending, or destructive steps. Nothing reaches you on its own: the lead relays what needs you with message_send to human, written for you. While there is no lead, escalations go to your queue.
  • Your queue: the dashboard's "Needs you" list, tirith lead human, /api/human on the dashboard port, and the macOS tray, which lists each item's sender and first line and notifies you of new ones. Answer with the dashboard's Done button or tirith lead human done <id> --reply "..."; the reply reaches the sender as a message from human.

Claim grants, refusals, waits, releases and lease ends, notice pushes, and escalations are appended to the lead decision log: tirith lead log, or /api/lead on the dashboard port. Design: ADR-0027; per tool: 04-primitives.md.

Documentation

SectionContents
1-aboutPurpose, architecture, project structure, tool reference, installation
2-examplesThe demo and client setup for every supported framework
3-testsTesting strategy
4-styleRust rules and their sources, git conventions
5-decisionsArchitecture decision records
6-agent-workflowHow agents work on this repo: Serena, memory, Tirith on itself
7-releaseRelease process and version bumping
index.htmlThe landing page at eabz.github.io/tirith

Contributing

Coding agents must read AGENTS.md first. This repository is coordinated with Tirith itself: a daemon runs for the repo and agents claim files through it before editing. The skills in .agents/skills/ say how.

License

MIT

Setup from the maintainer

This listing does not have a supported local package template. Use the maintainer’s documentation for its hosted endpoint, authentication, and client-specific setup. No install command has been inferred.

Package

tirith-mcpother

Compatible MCP Clients

Tirith works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More