MCP server CLEO

CLEO

CLEO is the work, evidence, memory and docs layer for AI coding agents. Agents (and you) drive it through one CLI, cleo <command>, and every call returns a single JSON envelope on stdout, so any agent harness can read it. CLEO keeps each change traceable from task to pull request to release, demands evidence before a task counts as done, remembers what was learned across sessions, and keeps documentation from rotting.

What it does

Area	What you get	Start with
Tasks	Sagas, epics and tasks with acceptance criteria, dependencies and ready waves; sessions that survive interruptions	cleo add, cleo next, cleo focus <id>
Evidence	A task is done only when its gates are proven: commits and files, CI or test runs, lint and typecheck, linked to each acceptance criterion	cleo done <id> --plan
Pull requests	A PR names its tasks (Closes: T#### AC1,AC2); an independent reviewer records a verdict per criterion; merging on green CI closes the task	cleo done --from-merge <pr> --dry-run, cleo review packet
Docs	One canonical home per doc, stable names, published mirrors and drift checks (see below)	cleo docs query, cleo docs update
Memory (BRAIN)	Observations, decisions and lessons kept across sessions and searchable	cleo memory observe, cleo memory find, cleo briefing
Code intelligence (Nexus)	A symbol graph of your repo: callers, blast radius, impact before you edit	cleo nexus analyze, cleo nexus impact <symbol>
Release	One command tags the newest commit on main with green CI and publishes from changesets	cleo release cut <version> --dry-run

Run cleo <command> --help for the full flags of any command.

Quick start

npm install -g @cleocode/cleo

cd your-project
cleo init
cleo session start --scope global --name "first session"

# Work is a tree: a saga at the root, epics under it, tasks under those.
cleo saga create --title "Ship the auth hardening" --acceptance "login is rate limited|sessions expire"
cleo add "Auth hardening" --type epic --parent T001 --acceptance "rate limit shipped|session expiry shipped"
cleo add "Rate-limit the login endpoint" --parent T002 \
  --acceptance "returns 429 after 5 failed attempts|a test covers the limit"

cleo next          # what to work on
cleo focus T003    # identity, blockers, docs and memory for one task

Then do the work and close it.

• With a pull request (the normal path): work on a branch, open a PR whose body says Closes: T003 AC1,AC2, check it with cleo done --from-merge <pr> --dry-run, get a per-criterion review (cleo review packet <pr> --task T003, then cleo review verdict), and merge on green CI. The merge sweep records the evidence and closes the task.
• Without a pull request: cleo done T003 --plan names the evidence each gate needs; record it with cleo verify, then cleo complete T003.

Finish with cleo memory observe "<what you learned>" --title "<short title>" and cleo session end --note "<handoff>". The next session starts with cleo briefing.

Docs that don't rot

AI agents write a lot of documentation, and most of it rots. An agent that cannot find the existing doc writes a new one; names carry task ids and dates; two copies drift apart; nobody can tell which one is current. After a few months the docs folder is a pile of near-duplicates that agents keep extending.

CLEO Docs fixes this at the source:

• One canonical home per doc. The store is the source of truth; files in docs/ are published mirrors. Find before you write (cleo docs query "<topic>"), and update the existing doc (cleo docs update <slug>) instead of adding a second one. cleo docs add is for genuinely new docs.
• Stable names. Every doc name and slug is lowercase kebab-case with no task id, session id or date; task and decision links live in metadata. A CI gate (cleo check canon docs) refuses new violators.
• One kind per folder. docs/adr, docs/spec, docs/plan, docs/research, docs/guide, docs/concept, docs/reference, docs/migration, docs/release and docs/note.
• Drift is visible. cleo docs status compares each published mirror with the store, cleo docs rot flags docs whose covered code changed after them, and cleo docs doctor repairs the store.
• Messy folders can be migrated. cleo docs modernize <folder> plans a kind, a stable name and keep/rename/merge/delete for every file, and applies it with a receipt you can roll back.

The how-to is docs/guide/cleo-documentation-sop.md.

Packages

The CLI is @cleocode/cleo; it depends on the rest. The main packages:

Package	Purpose
@cleocode/cleo	The cleo command-line interface
@cleocode/core	The SDK: tasks, sessions, evidence, docs, memory, orchestration, release
@cleocode/contracts	Shared types and operation contracts
@cleocode/lafs	The JSON envelope format every call returns
@cleocode/nexus	Code intelligence and the cross-project registry
@cleocode/caamp	Provider registry and agent package management
@cleocode/adapters	Provider adapters (Claude Code, Codex, Cursor, Gemini, Kimi, OpenCode and more)
@cleocode/skills	The ct-* skills that teach agents how to use CLEO
@cleocode/cant	The CANT agent-definition language

Development

Requires Node.js >= 24.16.0 and pnpm.

git clone https://github.com/kryptobaseddev/cleo.git
cd cleo
pnpm install
pnpm run build

Repository rules (package boundaries, architecture gates, evidence) are in AGENTS.md; see CONTRIBUTING.md to contribute. Every change lands through a pull request that names its tasks; releases are cut from main with cleo release cut.

The story of CLEO

CLEO began as one developer's refusal to keep losing the thread: powerful agents that forgot too easily, ambitious projects that died on the shelf. The Founding Story tells it from the builder's side, and The Awakening Story from CLEO's.

Support

If CLEO helps your workflow, consider supporting development:

License

MIT License - see LICENSE for details.

Star History