OpenHands
Open-source AI coding agent platform for autonomous software development
About OpenHands
OpenHands (formerly OpenDevin) is an open-source platform for building and deploying AI coding agents that can autonomously write code, run commands, browse the web, and interact with APIs. Designed as a cloud-native software engineering assistant, OpenHands enables developers and teams to automate complex development tasks — from bug fixes and code reviews to test generation, documentation, and legacy code refactoring. The platform is model-agnostic, supporting any LLM backend, and deploys in secure sandboxed environments via Docker or Kubernetes. With over 65,000 GitHub stars and $18.8M in funding, OpenHands is the leading open-source AI coding agent, consistently ranking at the top of SWE-bench benchmarks with a 72% resolution rate.
Pros & Cons
Pros
- Fully open source under MIT license with massive community (65K+ stars)
- Model-agnostic — not locked into a single LLM provider
- Free cloud tier lets you try without infrastructure setup
- Top-tier benchmark performance (72% on SWE-bench Verified)
- Flexible deployment: local, cloud, or self-hosted in VPC
- Rich agent capabilities: code, shell, browser, and planning combined
Cons
- Requires LLM API keys which add variable cost based on usage
- Self-hosted setup requires Docker/Kubernetes expertise
- Growth plan at \u0024500/month may be steep for small teams
- Agent output quality depends heavily on underlying LLM choice
- Complex tasks may still need human review and intervention
Key Features
Autonomous AI coding agent that writes, tests, and debugs code
Model-agnostic — works with Claude, GPT-4, open-source LLMs, and more
Secure sandboxed execution in Docker or Kubernetes environments
Built-in web browser, shell, editor, and task planner
Git-native with GitHub and GitLab integrations
72% resolution rate on SWE-bench Verified benchmark
Open source with MIT license and 65K+ GitHub stars
Automated code review and PR summarization
Use case
Bug fixing and issue resolution
Use case
Test generation and coverage expansion
Use case
Documentation generation from code
Use case
Legacy code refactoring and modernization
Use case
Security vulnerability detection and fixes
Use case
Production issue triage
Use case
GitHub integration
Integration
GitLab integration
Integration
Slack integration
Integration
Jira integration
Integration
CI/CD pipelines integration
Integration
Docker integration
Integration
Kubernetes integration
Integration
MCP (Model Context Protocol) integration
Integration
Pricing
- Full OpenHands agent locally
- MIT licensed
- Community support
- Single-user design
- Bring your own LLM key
- Hosted cloud access
- Desktop and mobile access
- Bring your own LLM keys
- At-cost LLM provider option
- Web GUI and CLI
- Shared team workspace
- Multiple users
- Git integrations
- Jira and Slack integrations
- Cloud Agent SDK and MCP support
- Self-hosted in your VPC
- Unlimited concurrent conversations
- SAML/SSO authentication
- Large Codebase SDK
- Priority support and dedicated Slack
- Named Customer Engineer
Featured In
7 Best AI Agents for Autonomous Software Development (2026)
Best open-source autonomous agent — the top choice for teams that need full control over models, infrastructure, and data while matching proprietary tools on benchmark performance.
7 Best AI Coding Tools for Terminal-First Developers (2026)
Best for engineering teams that want autonomous AI agents integrated into their CI/CD pipeline. The open-source, sandboxed architecture is ideal for production-grade automated development workflows.