Skip to main content

A structured multi-agent framework for coordinated AI collaboration

Project description

Autopoe

A multi-agent collaboration framework where lightweight AI agents work together through structured coordination to accomplish complex software development tasks.

Installation

Pick one:

uvx autopoe                       # run without installing
uv tool install autopoe           # install via uv
pip install autopoe               # install via pip

Docker

To run Autopoe in Docker, download docker-compose.yml and run:

docker compose up -d

Autopoe will be available at http://localhost:6873.

Prerequisites

  • Bubblewrap (bwrap) — required for agents to execute shell commands in a sandboxed environment. Install it before running Autopoe if you want agents to be able to run code.

Configuration

On first run, configure your LLM provider via the Settings panel (gear icon). Four API types are supported — any compatible endpoint works:

  • OpenAI-compatible — OpenRouter, Ollama, ModelScope, vLLM, LiteLLM, or any /v1/chat/completions endpoint
  • OpenAI Responses — OpenAI or compatible /v1/responses endpoints
  • Anthropic — any endpoint following the Anthropic Messages API
  • Google Gemini — any endpoint following the Gemini generateContent API

Autopoe stores instance data in ~/.autopoe/ by default, including settings.json, workspace snapshots, and image assets. You can override that app data directory before startup with AUTOPOE_APP_DATA_DIR=/path/to/data or autopoe --app-data-dir /path/to/data. The system working_dir can be changed at runtime from Settings without restarting.

Development

# Clone the repo
git clone https://github.com/ImFeH2/autopoe.git
cd autopoe

# Backend (API + WebSocket only, http://localhost:8000)
uv sync
uv run fastapi dev app/dev.py

# Frontend (hot reload, http://localhost:6873, separate terminal)
cd frontend
pnpm install
pnpm dev

In development, open http://localhost:6873. The Vite dev server proxies /api and /ws to the backend on http://localhost:8000. In production, the backend serves the built frontend from app/static on http://localhost:6873.

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

autopoe-0.2.13-py3-none-any.whl (1.0 MB view details)

Uploaded Python 3

File details

Details for the file autopoe-0.2.13-py3-none-any.whl.

File metadata

  • Download URL: autopoe-0.2.13-py3-none-any.whl
  • Upload date:
  • Size: 1.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for autopoe-0.2.13-py3-none-any.whl
Algorithm Hash digest
SHA256 79bb02f6c89052afabac5238fdae20df4780ab171a43b6c1674bca0ef712f3e6
MD5 96415f53ad55ef59f30d7df1641eba03
BLAKE2b-256 0f59774bf55ca23f76e963918483cd2ae3f74e03dfa5228c50dd627d75e8a128

See more details on using hashes here.

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