OpenHands: AI-powered software development agent platform
LLM agent framework automating development in sandboxed containers.
Learn more about OpenHands
OpenHands is an AI-powered agent framework that automates software development tasks by leveraging large language models within isolated sandbox environments. The platform instantiates autonomous agents that interpret natural language instructions, generate code, execute commands, and iterate on solutions while operating in containerized workspaces to ensure system safety. These agents employ a reasoning loop that combines LLM-based decision making with direct interaction capabilities including file system manipulation, shell command execution, and web browsing. The framework provides programmatic interfaces for initializing agents with specific objectives, allowing developers to delegate complex development workflows to the AI system. By running all agent operations in sandboxed containers, the architecture maintains security boundaries while enabling the agent to perform real development actions without compromising the host environment.
Sandboxed execution environment
Agents operate within isolated Docker containers that can execute arbitrary commands and file operations. This isolation allows agents to perform development tasks without affecting the host system.
Multi-LLM backend support
The platform supports various language models including OpenAI GPT, Claude, and other LLM providers. Users can select different models based on their requirements and API access.
Dual interface options
OpenHands provides both a web GUI accessible at localhost:3000 and a command-line interface. The CLI launcher uses uv for environment isolation, separating the agent runtime from the user's project dependencies.
from openhands.controller import AgentController
from openhands.core.config import LLMConfig
llm_config = LLMConfig(model="gpt-4o", api_key="your-api-key")
controller = AgentController(llm_config=llm_config)
result = controller.run("Create a Python script that calculates fibonacci numbers")
print(result.output)1.2.1 - 2026-01-16
- –Error messages in the chat interface now include a dismiss button and automatically truncate long messages with a "View More" toggle by @VedantMadane in
- –@MkDev11 made their first contribution in
- –@VedantMadane made their first contribution in
1.2.0 - 2026-01-15
- –Adding a status indicator above the chat until the conversation is ready by @HeyItsChloe in
- –Conversation title is now displayed in delete confirmation modal by @naaa760 in
- –Bumped condenser defaults max_size from 120 to 240 by @xingyaoww in
- –Fixed a bug where the Search API Key was getting reset when saving other settings by @sarva-20 in
- –Many bug fixes and improvements
1.1.0 - 2025-12-30
- –Added OAuth 2.0 Device Flow for CLI authentication by @malhotra5 in
- –Added refresh button to the Changes tab by @hieptl in
- –Added `Export Conversation` button for conversations in the conversation panel by @tofarr in
- –Added Forgejo integration by @johba37 in
- –Changed the init process for each runtime container from micromamba to tini so that child processes of tmux get reaped properly by @GuyPaddock in
See how people are using OpenHands
Top in AI & ML
Related Repositories
Discover similar tools and frameworks used by developers
llama.cpp
Quantized LLM inference with hardware-accelerated CPU/GPU backends.
OpenAI.fm
Web demo showcasing OpenAI's Speech API text-to-speech capabilities with an interactive Next.js interface.
stablediffusion
Text-to-image diffusion in compressed latent space.
pix2pix
Torch implementation for paired image-to-image translation using cGANs.
AI-Trader
LLM agent benchmarking framework for autonomous market trading.