# openonion/connectonion

The Best AI Agent Framework for Agent Collaboration.

Repository: https://github.com/openonion/connectonion
Canonical: https://ross.abutalabs.com/products/connectonion
Homepage: https://docs.connectonion.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, agentic-ai, llm, openonion
Last push: 2026-08-26T18:34:18+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 28
- inputs: {"age_days": 401, "days_push": 7, "days_rel": 8, "gap_med": 1, "n_releases_24m": 98}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1470, forks 212 (observed 2026-08-28T04:04:49.157958+00:00)

## What it is
ConnectOnion is a Python framework for building production-ready AI agents with tools, plugins, event hooks, and multi-agent collaboration. It ships with a CLI (`co`) that scaffolds working agent templates, provides a built-in AI coding assistant, debugging, and deployment to managed or owned infrastructure.

## Use cases
- build an ai agent in python with tool calling
- scaffold an agent project from a working template
- create multi-agent collaboration workflows
- deploy an llm agent to a server
- debug llm agent tool calls interactively
- build a browser automation agent
- run an agent without managing api keys

## When to choose
- you want a batteries-included Python agent framework with scaffolding, hosting, and debugging built in
- you prefer starting from a working template instead of assembling a stack
- you need sub-agents, plugins, and event hooks for complex agent behavior

## When to avoid
- you need a minimal, unopinionated library with no CLI or hosted-service coupling
- you require a non-Python language
- you want a mature ecosystem comparable to LangChain or CrewAI

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, cli, chatbot, prompt-engineering
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: ai-agents, agent-collaboration, template-first, tool-calling, sub-agents, cli-scaffolding, hosted-llm-keys, automation

## Member repositories
- openonion/connectonion (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:49.157958+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:50.583734+00:00, confidence not recorded.
  - readme: https://github.com/openonion/connectonion (fetched 2026-08-28T04:04:49.157958+00:00, sha 18a99f75f05f)
  - homepage: https://docs.connectonion.com (fetched 2026-08-29T11:42:48.357002+00:00, sha 432a45822db3)
  - site_page: https://docs.connectonion.com/quickstart (fetched 2026-08-29T11:42:48.366227+00:00, sha 14e46fdcc677)
  - site_page: https://docs.connectonion.com/agent (fetched 2026-08-29T11:42:48.368291+00:00, sha 863813d969a3)
  - registry_pypi: https://pypi.org/pypi/connectonion/json (fetched 2026-08-29T11:42:48.370148+00:00, sha f2758c5411ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.