Category leader in multi-agent orchestration — 69,352 stars (verified), $18.8M Series A, AMD hardware partnership, 455 contributors, 1M downloads/month PyPI (3.4M all-time). SWE-Bench Verified 72% with Claude 4.5 Extended Thinking (updated 2026-03-19), Multi-SWE-Bench #1 across 8 languages. Gap to #2 is enormous on every axis.
88/100
Trust
69K+ ↑12%
Stars
11
Evidence
283.2 MB
Repo size
Videos
Reviews, tutorials, and comparisons from the community.
OpenHands + Devstral = A Fully Local Coding Agent
Build Apps With Prompts! - OpenHands
OpenHands: Open-source AI Software Development Agents
Repo health
15h ago
Last push
330
Open issues
8,698
Forks
459
Contributors
Editorial verdict
Category leader. No other tool has the combination of open-source community (69K stars, 455 contributors), real download volume (1M/month), venture backing ($18.8M), hardware partnerships (AMD), and benchmark leadership (SWE-bench Verified 72%). Gap to #2 is enormous.
Source
GitHub: OpenHands/OpenHands
Docs: docs.openhands.dev
Public evidence
Cloud coding agents that solve 87% of bug tickets same day. 77.6% SWE-bench Verified. New software-agent-sdk v1.0 architecture.
Only multi-agent platform with a major hardware vendor partnership for local inference. Advances agent performance and enterprise readiness utilizing AMD Lemonade Server.
Engineers at AMD, Apple, Google, Amazon, Netflix, TikTok, NVIDIA, Mastercard, and VMWare have cloned or forked the repository. Series A gives runway for cloud product development.
Early enterprise adopters report reducing code-maintenance backlogs by up to 50% and cutting vulnerability resolution times from days to minutes. Transition from research tool to production platform.
Listed among top 18 open-source AI agent projects by GitHub stars. Positioned as the leading autonomous software engineering agent.
Peer-reviewed conference paper at ICLR 2025. Evaluated across 15 benchmarks including SWE-bench and WebArena. Documents 2.1K+ contributions from 188+ contributors.
One tester reports agent completed half a test-writing task but cost $50 in API credits. Maintainer acknowledges it's 'useful for a handful of one-off tasks' but not yet mission-critical.
Tested on real project (Quarto blog migration). Found it effective but not fully autonomous — 'saved me time and mental energy' but needed 'a bit of human guidance.' Transparent about both strengths and limitations.
Used OpenHands as scaffolding framework to generate 67K trajectories for fine-tuning. Describes OpenHands as 'one of the most widely adopted open-source agent scaffolding frameworks.' Achieved 61.7% SWE-bench Verified.
Head-to-head comparison. OpenHands wins on enterprise features (RBAC, audit logs, CI/CD), web UI, and team collaboration. SWE-agent wins on benchmark credibility and academic foundation.
Stars confirm community traction far beyond any competitor in the autonomous coding category. Consistently ranked #1 open-source Devin alternative across multiple independent roundups.
How does this compare?
See side-by-side metrics against other skills in the same category.
Growth
GitHub stars over time.
GitHub Stars
Where it wins
68,800+ stars (verified), 455 contributors — largest open-source community by 10x
4M+ downloads, accelerating
$18.8M Series A (Madrona-led) + AMD Lemonade collaboration
ICLR paper accepted 2025 — peer-reviewed research backing
MIT license, model-agnostic, self-hostable — only serious option for air-gapped deployment
Planning Agent v1.5.0 (Mar 2026) — Plan/Code mode toggle
Biweekly releases (v1.5.0 on 2026-03-11)
Where to be skeptical
SWE-bench Verified 72% with Claude 4.5 Extended Thinking — strong benchmark result
No disclosed revenue or paying customer count
HN engagement low (70 pts) compared to peers
Enterprise adoption evidence thin beyond logo slides
Ranking in categories
Know a better alternative?
Submit evidence and we'll run the full pipeline.
Similar skills
Aider
91Open-source AI pair programming CLI. The only tool in the coding CLI category with a fully verifiable, independent download number: 191,828/week PyPI installs, 5.7M lifetime, 15B tokens/week (homepage stat). Multi-model, git-native, no vendor lock-in. v0.86.2 released 2026-02-12.
Claude Code
90Anthropic's official agentic coding CLI. Terminal-native, tool-use-driven, with deep file system and shell access. #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue (fastest enterprise SaaS to $1B ARR). 8M+ npm weekly downloads. Opus 4.6 with 1M context.
n8n
83179,860 GitHub stars — largest OSS repo in adjacent workflow-automation space by 2×. 3,000+ enterprise customers, ~200,000 active users, $60M Series B. 1,100+ ready-to-use integrations, native AI Agent node, MCP client/server support. Best for orchestrating SaaS integrations and processes with AI nodes — not for building agent systems in code.
LangGraph
78#1 Python agent framework by production evidence — 40.2M PyPI downloads/month, Fortune 500 deployments (LinkedIn, Uber, Replit, Elastic, Klarna, Cloudflare, Coinbase), ~400 LangGraph Platform companies, LangSmith rated best-in-class observability. Stable v1.x API, model-agnostic, MCP support.
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
<a name="readme-top"></a>
<div align="center"> <img src="https://raw.githubusercontent.com/OpenHands/docs/main/openhands/static/img/logo.png" alt="Logo" width="200"> <h1 align="center" style="border-bottom: none">OpenHands: AI-Driven Development</h1> </div> <div align="center"> <br/> <!-- Keep these links. Translations will automatically update with the README. --><a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=de">Deutsch</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=es">Español</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=fr">français</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ja">日本語</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ko">한국어</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=pt">Português</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=ru">Русский</a> | <a href="https://www.readme-i18n.com/OpenHands/OpenHands?lang=zh">中文</a>
</div> <hr>There are a few ways to work with OpenHands:
The SDK is a composable Python library that contains all of our agentic tech. It's the engine that powers everything else below.
Define agents in code, then run them locally, or scale to 1000s of agents in the cloud.
Check out the docs or view the source
The CLI is the easiest way to start using OpenHands. The experience will be familiar to anyone who has worked with e.g. Claude Code or Codex. You can power it with Claude, GPT, or any other LLM.
Check out the docs or view the source
Use the Local GUI for running agents on your laptop. It comes with a REST API and a single-page React application. The experience will be familiar to anyone who has used Devin or Jules.
Check out the docs or view the source in this repo.
This is a deployment of OpenHands GUI, running on hosted infrastructure.
You can try it for free using the Minimax model by signing in with your GitHub or GitLab account.
OpenHands Cloud comes with source-available features and integrations:
Large enterprises can work with us to self-host OpenHands Cloud in their own VPC, via Kubernetes. OpenHands Enterprise can also work with the CLI and SDK above.
OpenHands Enterprise is source-available--you can see all the source code here in the enterprise/ directory, but you'll need to purchase a license if you want to run it for more than one month.
Enterprise contracts also come with extended support and access to our research team.
Learn more at openhands.dev/enterprise
Check out our Product Roadmap, and feel free to open up an issue if there's something you'd like to see!
You might also be interested in our evaluation infrastructure, our chrome extension, or our Theory-of-Mind module.
All our work is available under the MIT license, except for the enterprise/ directory in this repository (see the enterprise license for details).
The core openhands and agent-server Docker images are fully MIT-licensed as well.