Skip to main content

CLI-first orchestration platform for autonomous agents with Git-backed task, run, and memory state

Project description

Agent Hive

Agent Hive is a repo-native control plane for autonomous work. Use Codex, Claude Code, or local/manual execution to do the work. Use Hive to supervise tasks, runs, memory, policy, and approvals from one place.

mellona-hive is the distribution you install from PyPI or Homebrew. Mellona is the package family. Agent Hive is the current product. The install gives you the hive and hive-mcp commands.

Install

Pick the installer you already trust:

uv tool install mellona-hive
pipx install mellona-hive
python -m pip install mellona-hive
brew tap intertwine/tap
brew install intertwine/tap/mellona-hive

Then verify:

hive --version
hive doctor

The full install matrix, lane chooser, and maintainer split live in docs/START_HERE.md.

If you want optional extras:

  • Observe console: uv tool install --upgrade 'mellona-hive[console]'
  • MCP adapter: uv tool install --upgrade 'mellona-hive[mcp]'
  • Homebrew currently ships the base CLI only, so add extras through uv tool, pipx, or pip

If you are testing before the first tagged public release lands on PyPI and Homebrew, use the git install:

uv tool install --from git+https://github.com/intertwine/hive-orchestrator.git mellona-hive

First Run

Start in an empty directory:

mkdir my-hive
cd my-hive
git init
hive onboard demo --title "Demo project" --objective "Ship one governed slice."

That gives you a real workspace, a starter project, a conservative PROGRAM.md, and a first task chain with one ready task. If you want the observe-and-steer console, install mellona-hive[console] first, then run hive console serve.

Fresh onboarded projects may start with the placeholder local-smoke evaluator so the loop works immediately. Replace it with a real repo-specific evaluator before you trust autonomous promotion.

Then use the normal loop:

hive next --project-id demo
hive work <task-id> --owner <your-name>
hive finish <run-id>

Optional extras stay intentionally small:

  • mellona-hive[console] adds the observe-and-steer console
  • mellona-hive[mcp] adds the thin search + bounded local execute adapter

Choose The Right Guide

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mellona_hive-2.2.3.tar.gz (317.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mellona_hive-2.2.3-py3-none-any.whl (341.8 kB view details)

Uploaded Python 3

File details

Details for the file mellona_hive-2.2.3.tar.gz.

File metadata

  • Download URL: mellona_hive-2.2.3.tar.gz
  • Upload date:
  • Size: 317.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mellona_hive-2.2.3.tar.gz
Algorithm Hash digest
SHA256 16eb769b3469ea67d217270d33e849dc1ce44e5f8051fe0e61e4ab64ea423580
MD5 5acb149d4e86e56cd581c21ca3217fde
BLAKE2b-256 a01a7563e3ef11aee3bfc27f3238d2947468b2b71ec85f7fa6ce1d6df9065bec

See more details on using hashes here.

Provenance

The following attestation bundles were made for mellona_hive-2.2.3.tar.gz:

Publisher: release.yml on intertwine/hive-orchestrator

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mellona_hive-2.2.3-py3-none-any.whl.

File metadata

  • Download URL: mellona_hive-2.2.3-py3-none-any.whl
  • Upload date:
  • Size: 341.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mellona_hive-2.2.3-py3-none-any.whl
Algorithm Hash digest
SHA256 d782805e529d89d36a28ebb1dedea97ad6dee32df7a74c80ecae6b933fcb6bd9
MD5 a611e21da86396ee3e5a42f12402d681
BLAKE2b-256 1334ccbd559fdc0ba37aab8e555746a506a587bae1a64523307efb3acb506f31

See more details on using hashes here.

Provenance

The following attestation bundles were made for mellona_hive-2.2.3-py3-none-any.whl:

Publisher: release.yml on intertwine/hive-orchestrator

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page