no_human
This server exposes a local AI coding agent that can take a task from description to a reviewed pull request, and lets you monitor its progress.
Create tasks – File a new coding task with a title, description, and repository path; the agent plans, implements, tests, and reviews the change (opening a PR on approval).
Track status – Look up a task's full state using its ID or external ID, including status, attempt count, and the PR link once available.
Integrate with existing tools – Work with tickets from Jira, Linear, Monday.com, GitHub/GitLab issues, and notify via Slack/Teams.
Enforce quality gates – Requires a plan before coding, runs your tests locally or via CI, performs an adversarial review with a different model, and blocks tampering or weak evidence.
Automate from MCP clients – Let Claude Code or any MCP client file and check on work without leaving your current environment.
Runs test layers through CircleCI to verify changes, with optional CI gating to enforce test success before proceeding.
Imports GitHub issues as tasks by URL, and opens pull requests automatically for completed changes, with the ability to approve and land them via the no_human workflow.
Imports GitLab issues as tasks by URL and opens merge requests for completed changes, similar to GitHub support.
Runs test layers through Jenkins as part of the no_human loop, enabling CI gating to verify changes before a pull request is opened.
Integrates with Jira Cloud to pull tickets onto the no_human board via a configurable JQL filter, sync task progress back to the ticket, and comment on tickets when human input is needed.
Integrates with Linear to import issues as tasks via the GraphQL API based on team key, state types, and label filters, with optional write-back to update issue status and add pull request links.
Sends messages to Slack when a task requires human attention or feedback, keeping team members informed of blockers.
no_human
From ticket to reviewed pull request.Free and open-source, on your machine.
getnohuman.com · Quickstart · Docs · Watch it work a sprint
▶ Watch the loop — a ticket in, a reviewed pull request out; the whole loop in 57 seconds.
The AI coding factory you can trust:
A plan before any code, from the ticket plus what it finds in your repo.
An adversarial review. A different model, fresh context, read-only tools, told to refute "done". You get a pass/fail checklist citing file and line — never a numeric self-score.
A tamper guard. Deleted tests, new skips, an assertion turned into a tautology — blocked before a reviewer token is spent.
Proof the fix fixed the bug. For a bug fix, the tests offered as evidence must fail at the merge base and pass on the new tree — the reproduction gate enforces that, and you can require it for every change.
Your tests run, locally and optionally through your CI.
An honest stop. When it cannot finish, it parks with one specific question instead of inventing a plausible diff.
Install
Whichever way you install, you need a Claude credential: an OAuth token
from claude setup-token (personal subscription or enterprise), so install the
Claude Code CLI first — npm install -g @anthropic-ai/claude-code, or
curl -fsSL https://claude.ai/install.sh | bash. The desktop app also calls
that CLI for every task. To pay Anthropic directly instead, set
llm.auth_mode: "api_key" and put your ANTHROPIC_API_KEY in
~/.no_human/.env.
One line (CLI + board)
uv tool install no-human # or: pipx install no-human — the wheel ships the board
nh init && nh doctor # token, config, first repo; then prove the install is realDesktop app
Each release ships a SHA-256 alongside the artifact. Platform notes and the first-run walk-through: docs/quickstart.md.
From source
git clone https://github.com/no-human-ai/no_human.git && cd no_human
uv sync # installs the `nh` entry point into .venv
(cd web && npm install && npm run build) # builds the board (cold first install can take minutes)
uv run nh init # token, config, first repo (about 2 minutes)
uv run nh doctor # verify the install is real before relying on itThe web build is not optional if you want the board: a source checkout ships
no web/dist, so without it nh start serves the API only and renders no UI.
Needs Python 3.12+, uv, git, and Node with
npm for the board build.
Related MCP server: github-mcp
Run one task
Run nh with no arguments for the shell: your lanes, a live event tail, and an
intake you describe a task to in plain English. Every command below still works.
nh # the shell
nh start # board + worker on 127.0.0.1:8420
nh task add https://github.com/org/repo/issues/42 --repo ~/git/repo
nh status # needs-you / working / waiting / done
nh review <id> # the reviewer's evidence checklist
nh diff <id> # the diff it wants to ship
nh approve <id> # your approval squash-lands the PR (git.approve_identity)
nh reject <id> --reason "..." # send it back with feedbackIntegrations
Point no_human at the tracker you already use and it pulls the tickets to your board — a tracker's filter lives in your config, never in a task's own text, and a transport error logs and retries on the next tick instead of crashing the pool.
Tracker | How tickets arrive | Filter you configure |
Jira Cloud | Polled via REST |
|
Linear | Polled via the GraphQL API |
|
monday.com | Polled via GraphQL v2 |
|
With write-back on (write_back, off by default), the ticket moves with the
task — matched by status category, type, or the label you name, never a
hard-coded transition id — and gets the PR link; a task that needs a human is commented on, never
transitioned. GitHub and
GitLab issues import as tasks by URL, and PRs or MRs open on your own host;
Slack and Teams get a message when a task needs you; Jenkins and CircleCI can
run your test layers and gate the loop. Setup for each:
docs/adapters.md.
Watch the Jira flow end to end — tickets synced from a Jira board, scoped, implemented, and delivered as a review-passed pull request (click for the full video with every step):

MCP server — hand it work from the agent you are already in
no_human ships an MCP (Model Context Protocol) server: a stdio bridge, built on the official Python MCP SDK, that lets Claude Code, Cursor or any MCP client file work with your local no_human and check on it.
nh mcp-serve # the MCP server, over stdioTwo tools, and no more:
Tool | What it does |
| Files a task. no_human then plans it, writes the change, runs your tests, has a second model review it, and opens the pull request. |
| Returns that task's current state — status, attempts, the PR link once there is one. |
It talks to your own no_human at http://127.0.0.1:8420 and nothing else: no
auth, because that address is localhost, and no service of ours in between. For
Claude Code, the same server ships as a plugin — point it at
plugins/no-human/ and the two tools appear in your
session.
// .mcp.json
{ "mcpServers": { "no_human": { "command": "nh", "args": ["mcp-serve"] } } }Docs
Zero to first task, per platform | |
Every setting and default | |
The gates, the bounded loop, the limits | |
Auth boundary, the never-merge rule, guards | |
Escalation, wake watcher, | |
Intake, context, VCS and CI backends | |
Golden set, replay scoring, shadow mode | |
What changed, per release |
Development
uv sync
uv run pytest -q
uv run nh --helpIssues and pull requests welcome; run uv run pytest -q before submitting.
If no_human saved you a review cycle, a star helps other people find it:
License
MIT — see LICENSE. The licence covers the code, not the name: TRADEMARK.md is the policy on using "no_human" and the logo. Packaging a binary carries obligations the source tree does not, listed in THIRD-PARTY-NOTICES.md.
Maintenance
Tools
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables end-to-end automation of developer workflows from Jira issue tracking to GitHub pull requests through natural language, allowing developers to search issues, create branches, commit changes, and manage PRs directly from their IDE.2MIT
- AlicenseAqualityDmaintenanceLocal MCP server for safe GitHub developer workflows. Enables pulling main, creating feature branches, pushing them, and opening ready-for-review pull requests via tools like github_create_feature_branch and github_create_pull_request.6111MIT
- FlicenseNot gradedqualityCmaintenanceAutonomous AI software development pipeline that transforms tickets into production-ready code through planning, coding, testing, reviewing, and delivery stages.
- FlicenseNot gradedqualityAmaintenanceA review handoff tool for agent-driven coding sessions that captures worktree diffs, creates shareable review URLs, and streams reviewer feedback back to the agent.1
Related MCP Connectors
Autonomous dev team steered from chat: plain-English requests in, tested merged PRs out.
Pull change requests from your Amendor board into your coding agent to build and open PRs.
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management.…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/no-human-ai/no_human'
If you have feedback or need assistance with the MCP directory API, please join our Discord server