Open-source, model-agnostic platform for autonomous cloud coding agents that can modify code, run commands, fix bugs, and open pull requests â with 65K+ GitHub stars and a free hosted cloud tier.
Open-source, model-agnostic platform for autonomous coding agents that fix bugs, implement features, and open pull requests.
OpenHands (formerly OpenDevin) is an open-source platform for deploying AI coding agents that perform real software engineering work â editing code, running terminal commands, browsing documentation, and managing git workflows. With over 65,000 GitHub stars and $18.8M in funding from All Hands AI, it has become one of the most actively developed open-source coding agent projects.
The platform's core differentiator is model agnosticism. Unlike proprietary coding agents locked to specific LLMs, OpenHands works with any model provider â Anthropic Claude, OpenAI, Google Gemini, open-source models via Ollama, or custom endpoints. This lets teams optimize for cost, privacy, or capability depending on the task. AMD has partnered with OpenHands for local agent execution on Ryzen AI hardware.
OpenHands agents operate in sandboxed Docker or Kubernetes environments with full terminal access, file system manipulation, web browsing, and API interaction capabilities. The platform includes a web-based GUI, a terminal UI, a CLI, and a Cloud SDK for programmatic agent orchestration. Agents can be triggered from GitHub issues, GitLab merge requests, Slack messages, Jira tickets, or via API calls.
The hosted cloud service (OpenHands Cloud) offers a free Individual tier with 10 daily conversations using bring-your-own-key or at-cost model access through OpenHands' provider. Enterprise deployments support self-hosted VPC installation, SAML/SSO, multi-user RBAC, unlimited concurrent conversations, and a Large Codebase SDK for working with enterprise-scale repositories.
Real-world adoption includes Flextract (CTO reports 87% of bug tickets fixed same-day) and C3 (using OpenHands for remote autonomous coding at scale). The platform excels at automated code review, test generation, documentation creation, legacy code modernization, and dependency vulnerability remediation.
Was this helpful?
Works with any LLM provider including Anthropic, OpenAI, Google, open-source models via Ollama, or custom API endpoints, letting teams choose models based on cost, privacy, or task requirements.
Use Case:
A security-conscious enterprise runs OpenHands with a self-hosted Llama model for proprietary code, while using Claude for open-source contributions where privacy is less critical.
Agents execute in isolated Docker or Kubernetes containers with full terminal access, file system manipulation, web browsing, and API interaction â all auditable and controllable.
Use Case:
Running autonomous dependency upgrades in an isolated environment where the agent can test changes, run the full test suite, and verify nothing breaks before pushing to the repository.
Native integration with GitHub and GitLab for issue-driven agent workflows, plus Slack and Jira connectivity for triggering agent tasks from existing team communication channels.
Use Case:
A team labels a GitHub issue as 'openhands' and the agent automatically picks it up, creates a branch, implements the fix, and opens a PR with a description of changes made.
Cloud SDK and APIs enable running thousands of parallel agent instances for batch operations like codebase-wide refactoring, mass dependency updates, or large-scale test generation.
Use Case:
An engineering leader kicks off parallel OpenHands agents across 50 microservice repositories to update a shared library version and fix any resulting test failures.
Agents scan dependencies for known vulnerabilities, propose fixes, run tests to verify compatibility, and open reviewable pull requests â automating the security maintenance loop.
Use Case:
A DevSecOps team configures OpenHands to automatically create PRs for critical CVE patches across all repositories within hours of vulnerability disclosure.
Free
month
Free
month
Custom pricing â contact sales
Ready to get started with OpenHands?
View Pricing Options âWe believe in transparent reviews. Here's what OpenHands doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
Development
AI-native code editor (VS Code fork) with Tab autocomplete, Agent mode, and Composer multi-file edits. Used by 1M+ developers and 53% of Fortune 500 companies as of 2025. Free tier includes 2,000 completions; Pro is $20/month.
Developer Tools
An open-source autonomous AI coding assistant for VS Code with Plan/Act modes, terminal execution, file editing, and Model Context Protocol for custom tools.
Coding Agents
AI pair programming tool that works in your terminal, editing code files directly with sophisticated version control integration.
Coding Agents
Open-source autonomous coding agent from Princeton and Stanford researchers that resolves GitHub issues, detects cybersecurity vulnerabilities, and implements code changes using GPT-4o, Claude, or local LLMs â achieving state-of-the-art performance on SWE-bench benchmarks.
AI Code Generation
Bolt.new is an AI-powered web application builder that generates, edits, and deploys full-stack applications directly in the browser using simple text prompts and StackBlitz's WebContainer technology.
No reviews yet. Be the first to share your experience!
Get started with OpenHands and see if it's the right fit for your needs.
Get Started âTake our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack âExplore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates âTwo years ago, picking an AI coding assistant meant choosing between a handful of autocomplete plugins. In 2026, the **cursor vs github copilot** decision affects how your entire team writes, reviews, and ships code. Both tools have added agentic capabilities, background task run
The average developer now spends between 30% and 55% of their working hours on tasks that AI can accelerate â code completion, test generation, debugging, and documentation. A [2025 GitHub survey](https://github.blog/news-insights/research/survey-ai-wave-grows/) found that 97%
Compare the top AI coding agents in 2026 â Claude Code, Cursor, Copilot, Codex, Windsurf, Aider, and more. Real pricing, honest strengths, and a decision framework for every skill level.