# OpenHands

🙌 OpenHands: AI-Driven Development

Repository: https://github.com/OpenHands/OpenHands
Canonical: https://ross.abutalabs.com/products/openhands
Homepage: https://openhands.dev
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent, artificial-intelligence, llm, chatgpt, claude-ai, cli, developer-tools, gpt, openai
Last push: 2026-08-27T00:11:03+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 64
- inputs: {"age_days": 903, "days_push": 7, "days_rel": 12, "gap_med": 4, "n_releases_24m": 124}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 85199, forks 11138 (observed 2026-08-28T04:12:23.043272+00:00)

## What it is
OpenHands (Agent Canvas) is a self-hosted developer control center for running AI coding agents like OpenHands, Claude Code, Codex, and Gemini across local, remote, and cloud backends. It lets developers start agent conversations and automate engineering tasks such as generating reports to Slack or decomposing GitHub issues into tasks.

## Use cases
- run AI coding agents locally or in Docker
- automate GitHub issue triage and task decomposition
- generate reports and publish them to Slack with agents
- orchestrate multiple agent backends from one control center
- self-host an always-on AI engineering team
- connect third-party agents like Claude Code and Codex

## When to choose
- you want a self-hosted hub to run and manage multiple coding agents
- you need to automate repetitive development workflows with LLM agents
- you want agents to run in containers, VMs, or your own infrastructure

## When to avoid
- you need a simple single-shot code completion inside your editor only
- you don't want to manage agent backends or self-hosted infrastructure
- your workflows require no LLM involvement

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools, workflow-automation
- domain: artificial-intelligence, developer-tools, large-language-models
- platform: cross-platform, self-hosted, cli
- tags: coding-agents, acp, ai-driven-development, agent-orchestration, self-hosted-agents, claude-code, codex, ai-agents, automation, docker, web-server

## Member repositories
- OpenHands/OpenHands (main) score 87
- OpenHands/software-agent-sdk (sdk) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:23.043272+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 2026-08-29T16:13:53.713403+00:00, confidence not recorded.
  - readme: https://github.com/OpenHands/OpenHands (fetched 2026-08-28T04:12:23.043272+00:00, sha 55b58a4575e5)
- Data as of 2026-08-30T08:39:29.467469+00:00.