OpenHands

An open-source autonomous AI software engineer (formerly OpenDevin) that uses LLMs to write code, run tests, fix bugs, and interact with the web — fully containerized for safety.

OpenHands (formerly OpenDevin) is an open-source platform for AI software engineering agents. Unlike Cursor or Windsurf which are IDEs with AI assistance, OpenHands is a platform where AI agents operate autonomously — writing code, executing shell commands, browsing the web, and iterating until a task is complete.

How OpenHands Works

OpenHands runs agents inside isolated Docker containers. The agent has access to:

  • A full Linux shell (bash)
  • File system access (scoped to the project directory)
  • A browser (Playwright-controlled for web interaction)
  • Jupyter notebook execution for Python tasks

The isolation ensures the agent can't affect your host system — a key safety property when running autonomous code.

Agent Architecture

OpenHands uses a planner-executor loop:

  1. User provides a task (e.g., "implement OAuth login for this Express app")
  2. Agent plans steps using an LLM (configurable: Claude, GPT-4o, or a local model via Ollama)
  3. Agent executes each step: reads files, writes code, runs commands, observes output
  4. Agent corrects itself when execution fails
  5. When complete, agent presents the result

Resolver and SWE-bench

OpenHands includes a "Resolver" agent specialized for GitHub Issues — it clones a repo, reads the issue, implements a fix, and submits a PR. On the SWE-bench benchmark (real GitHub issues from popular repos), OpenHands achieves competitive scores against commercial tools.

MCP Support

OpenHands integrates with Mcp Model Context Protocol servers, allowing agents to use external tools (databases, APIs, internal services) through a standardized interface. This extends what the agent can do beyond the local filesystem.

Self-Hosting

OpenHands is MIT-licensed and runs locally or on a server. Teams use it for batch automation — running agents overnight on queues of tasks. Combine with Argocd for GitOps-triggered agent runs, or simply run it via Docker Compose.

  • Cursor — IDE-based alternative with tighter editor integration
  • Mcp Model Context Protocol — protocol OpenHands uses for external tool access
  • Langchain — agent orchestration framework; OpenHands is a complete platform rather than a framework
  • Ollama — run local models as the OpenHands backend
  • Docker — OpenHands runs every agent in a Docker container for isolation

Subscribe to Sahil's Playbook

Clear thinking on product, engineering, and building at scale. No noise. One email when there's something worth sharing.
[email protected]
Subscribe
Mastodon