claudeers.
// Automation & Workflows

hivemill

A self-hosted software factory of Claude Code agents with review, QA and a judge merge gate.

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up hivemill (claude-plugin project) into my current project.
Found on https://claudeers.com/hivemill
Repo: https://github.com/volekerb/hivemill
Homepage/docs: https://github.com/volekerb/hivemill#readme
Detected install method: claude-plugin → /plugin install hivemill@volekerb/hivemill
Category: automation. Platforms: cli, web.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or install directly (claude-plugin)

⚠ Unverified / not recently updated — review before pasting a run-this config.

/plugin marketplace add volekerb/hivemill
/plugin install hivemill@volekerb/hivemill
// or clone
git clone https://github.com/volekerb/hivemill

// compatibility

Platformscli, web
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguagePython

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

Hivemill

Hivemill is a self-hosted software factory of Claude Code agents,
with separate review, QA and a judge that decides the merge.

Quickstart · Docs · Examples · Adopt with Claude · Security · Discussions

https://github.com/user-attachments/assets/dfec91f4-de05-4592-aaec-3662ce674c4a

how it was made · seeded demo data only

The overview page of the web UI: live agents, open PRs, goals, items waiting on the owner and usage

What you get

You describe what you want built to one boss agent. A director staffs a team, and a chain of coders, QA, reviewers and a judge ships it as pull requests. The agent that writes a change never reviews, tests or merges it. Hivemill's CLI is factory.

Fixed roles
Each role has its own prompt and permissions, enforced by hooks rather than by trust.
Independent review
A separate reviewer and QA check every pull request against a real test run.
A judge merges
Only on passing reviewer and QA verdicts. Anything else goes back with findings.
One source of truth
Goals, tasks, messages and verdicts are rows in SQLite with an append-only log.
Small-box friendly
A spawn gate queues agents until RAM, load and Claude process count allow.
A read-only web UI
Goals, agents, throughput and quality, in light and dark.

One change, five steps

  1. You ask. Describe what you want to the boss. It becomes a goal with success criteria.
  2. A team forms. A director staffs a lead, who plans tasks. Each task gets its own worktree and branch.
  3. A coder builds. It opens a pull request and stops. It cannot merge or review.
  4. Two others check. A reviewer reads the diff. QA runs the tests against the acceptance criteria.
  5. A judge decides. Both pass, it merges. Either fails, it goes back with findings. Every verdict is stored.

The roles and the merge gate as diagrams are under How it works.

The factory runs on herdr, the terminal multiplexer that hosts the agent panes (source, pinned release v0.9.5).

Quickstart

Install

Needs a fresh Debian or Ubuntu machine and a logged-in Claude Code. In Claude Code:

/plugin marketplace add volekerb/hivemill
/plugin install hivemill
/hivemill:setup

The full guide, with the installer options and the manual steps, is docs/SETUP.md.

Look around without installing

Seeded fictional data, nothing real runs (docs/demo-data.md). Run from the repository root:

export TRIAL=$(mktemp -d)
python3 ci/demo_seed.py --home "$TRIAL/demo" --now 2026-10-25T12:00:00+01:00
HOME=$TRIAL/demo/home FACTORY_HOME=$TRIAL/demo bin/factory serve --bind 127.0.0.1 --port 18624

Open http://127.0.0.1:18624/ to see the read-only web UI on the demo data. In another shell, put HOME=$TRIAL/demo/home FACTORY_HOME=$TRIAL/demo in front of factory goal list to see the demo goals as a table.

A task's life in commands

Three walkthroughs with full output on the demo data: from a goal to a merged PR, handling a rejection, the digest and scorecard.

How it works

  • Separation of roles. Each role has its own prompt and its own permission settings, enforced by hooks rather than by trust.
  • Evidence over claims. A task is done when a reviewer and QA have checked the PR diff and a real test run, not when an agent says so.
  • Resource-aware on a small box. A spawn gate watches RAM, load and the number of Claude processes, and queues new agents until there is room. The whole factory runs on one modest VM.
  • Everything auditable. Goals, plans, tasks, messages, verdicts and decisions are rows in SQLite with an append-only event log, exported to readable markdown every minute.
flowchart TB
    owner([owner]) <--> boss
    boss <--> director
    director <--> lead["team leads (lead)"]
    lead --> pm
    lead --> coder
    lead --> qa
    lead --> reviewer
    lead --> judge
    director --> cleaner

    subgraph infra [Infrastructure]
        direction LR
        tick["tick (systemd timer, every minute)"]
        herdr["herdr panes (one per agent)"]
        db[("SQLite DB + factory CLI")]
        web["web UI (read-only)"]
    end

    tick -->|"reap, spawn, nudge, export"| herdr
    herdr -->|"hosts every agent"| boss
    boss -.->|"factory CLI"| db
    director -.->|"factory CLI"| db
    lead -.->|"factory CLI"| db
    db --> web
    tick --> db

The merge gate, for every change:

flowchart LR
    coder["coder opens PR"] --> reviewer["reviewer: diff verdict"]
    coder --> qa["qa: test and acceptance verdict"]
    reviewer --> judge{"judge"}
    qa --> judge
    judge -->|"both pass"| merge["merge to main"]
    judge -->|"any fail"| retry["back to coder with findings"]
    merge --> cleaner["cleaner removes worktree and branch"]

Details: docs/lifecycle.md, docs/verdict-gates.md, docs/db-layout.md.

Features

FeatureWhat it doesDocs
Run it
Setup and operationsInstall, boot units, reboot recovery, identity rulesSETUP, operations
Adopt with ClaudeAn instruction file your own Claude Code follows to install itADOPT
Ship safely
Verdict gatesThe judge merges only on passing reviewer and QA verdictsverdict-gates
Goal lifecycleFrom request to goal to done, with plan and success criteriagoal-lifecycle
Contain agents
Worker guardHooks that block actions outside a role's jobworker-guard
Worker sandboxNamespaced spawn for workers, with its known limitsworker-sandbox
Stopping a workerStop one agent cleanly without losing its workstopping-a-worker
See it
Web UIRead-only pages for goals, tasks, agents, throughput and qualityweb-ui
State branchMarkdown exports and a DB dump pushed to the state branchstate-branch

Each feature has its own file under docs/ (all pages: docs/README.md). Also: tests and CI, lessons, per-role plugins, updating persistent agents, boss mail.

back to top

How it compares

One Claude Code sessionHand-run subagentsHivemill
Role separationOne agent plans, writes and judges its own workYou choose the roles each timeFixed roles with their own prompts and permissions, enforced by hooks (worker-guard)
Independent reviewThe author reviews itselfOnly if you start a reviewerA separate reviewer and QA check every PR (verdict-gates)
Merge gateYou merge by handYou merge by handThe judge merges, gated on reviewer and QA (verdict-gates)
State and auditThe chat transcriptWhatever you wrote downGoals, tasks, messages and verdicts in SQLite with an append-only event log (db-layout)
Resource gateNoneNoneA spawn gate queues agents until RAM, load and Claude process count allow (spawn-queue)
Recovery after rebootStart overStart overBoot units resume the headquarters and active teams (operations)

Works with: Claude Code, herdr, gh, systemd user units and the Moshi phone app.

The web UI

A read-only web UI shows goals, tasks, live agents, throughput and quality, in light and dark themes. Start it with factory serve (docs/web-ui.md). The screenshots come from fictional demo data only (docs/demo-data.md); click one for the full-size light image.

The overview page: a needs-you list, system gauges, goals with progress, live agents, shipped changes and quality
Overview: agents, PRs, goals and usage
The goals page: goals grouped by status with progress bars and priority
Goals: status and priority
The tasks page: tasks grouped by status with goal, assignee, PR and CI state
Tasks: status, assignee and PR
The agents page: live agents by role and team with model and uptime
Agents: live agents by role and team
The throughput page: merges per day and spawn-to-merge times as charts
Throughput: merged changes over time
The quality page: merge, rejection, retry and CI pass-rate cards with per-team scores
Quality: rejections and retries per team
The goal detail page: a goal's intent, plan, teams, tasks and progress
Goal detail: intent, plan, teams and tasks

Status and limits

  • Every agent is a Claude Code session, so it uses your Claude usage.
  • It is built for a single box, not a cluster. State is one SQLite file.
  • Agent isolation is a tripwire, not a sandbox. Hooks and permission settings stop honest mistakes and make bypasses visible; they do not contain a determined adversary. Read SECURITY.md for the threat model and the known limits before you point it at anything you cannot afford to lose.
  • The worker sandbox, which would add real containment, is in progress.
  • The web UI is read-only and has no authentication; bind it to an address you trust.

Not affiliated with Anthropic. Claude and Claude Code are products of Anthropic.

Use it from your phone

Install Moshi on your phone, connect to your box over SSH, and run herdr there to reach the boss's pane. Moshi is a third-party app, not part of Hivemill.

Resources

Contributing

Read CONTRIBUTING.md first. A feature PR adds or edits its docs/.md page and does not edit this README. Small, well-scoped places to start are in docs/STARTER_ISSUES.md. Report vulnerabilities as described in SECURITY.md.

License

MIT. Third-party notices: THIRD_PARTY.md.

back to top

// faq

What is hivemill?

A self-hosted software factory of Claude Code agents with review, QA and a judge merge gate.. It is open-source on GitHub.

Is hivemill free to use?

hivemill is open-source under the MIT license, so it is free to use.

What category does hivemill belong to?

hivemill is listed under automation in the Claudeers registry of Claude-compatible tools.

8 views
★ 19 stars
unclaimed
updated 10 days ago

// embed badge

hivemill on Claudeers
[![Claudeers](https://claudeers.com/api/badge/hivemill.svg)](https://claudeers.com/hivemill)

// retro hit counter

hivemill hit counter
[![Hits](https://claudeers.com/api/counter/hivemill.svg)](https://claudeers.com/hivemill)

// reviews

// guestbook

0/500

// related in Automation & Workflows

🔓

The agent that grows with you

// automationNousResearch/⟨Python⟩★ 264,763◷ MIT[ claude ]
🔓

The API to search, scrape, and interact with the web at scale. 🔥

// automationfirecrawl/⟨TypeScript⟩★ 199,533◷ AGPL-3.0[ claude ]
🔓

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

// automationbrowser-use/⟨Python⟩★ 121,235◷ MIT[ claude ]
🔓

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

// automationLeonxlnx/⟨JavaScript⟩★ 110,676◷ MIT[ claude ]
→ see how hivemill connects across the ecosystem