openhands-ai
OpenHands: Code Less, Make More
Decision gist · record as of 2026-08-14
Yes, if you need a self-hosted, multi-backend agent orchestration platform with automation and third-party integrations. The active maintenance, large community (84043 stars), permissive MIT license, and low install friction support production use. The 85 dependencies and requirement for Python 3.12 or 3.13 are expected for a full orchestration system. No known vulnerabilities. Install if you're building agent-driven workflows; skip if you need a lightweight agent library or are not ready to manage a backend service.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Node.js 22.12.x or later and uv (for local install); Docker Desktop or Engine for sandboxed execution; Python 3.12 or 3.13 for the backend agent server.
- Low install friction with a pure-Python wheel.
- Active maintenance (last commit 2026-08-14, 84043 stars).
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use, modification, and distribution with minimal restrictions—standard permissive terms suitable for both self-hosted deployments and integration into other projects.
last release 2026-07-09 (36 days) · last repo commit 2026-08-14 · 84,043 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,805,117 downloads/mo, #3,538 on PyPI
Alternatives
Verify before relying
npm install -g @openhands/agent-canvas
agent-canvas
# Or via Docker:
export PROJECTS_PATH="$HOME/projects"
mkdir -p "$PROJECTS_PATH" "$HOME/.openhands"
docker run -it --rm -p 8000:8000 \
-v "$HOME/.openhands:/home/openhands/.openhands" \
-v "${PROJECTS_PATH}:/projects" \
ghcr.io/openhands/agent-canvas:1.0.0-rc.11- Whether the 85 runtime dependencies are all required for minimal deployments or if many are optional for specific backends/integrations.
- Performance and resource requirements when running multiple agents or automations concurrently.
- Security hardening specifics beyond the self-hosting guide reference (e.g., network isolation, credential handling).
What it is and what it does
OpenHands is a full-stack developer control center that orchestrates coding agents—either the open-source OpenHands agent or third-party agents like Claude Code and Codex—across multiple execution backends (local, Docker, VMs, cloud infrastructure). It provides a web UI for starting agent conversations and a REST API backend that manages agent lifecycle, state, and communication. The platform emphasizes flexibility: you can run agents on your laptop, a dedicated machine, or cloud infrastructure, and switch between backends without losing context.
Beyond interactive agent control, OpenHands includes an Automation Server layer for scheduling agents or triggering them via webhooks—enabling workflows like publishing reports to Slack or decomposing GitHub issues into tasks. It integrates with third-party services (Slack, GitHub, Linear, Notion) and supports any LLM. The architecture separates the frontend UI from the backend agent server, allowing distributed deployments where teams can share a central Agent Server for code review while running personal agents locally. With 85 runtime dependencies spanning async frameworks, cloud SDKs, container orchestration, and LLM clients, it is designed as a production orchestration platform rather than a lightweight agent library.
Use it for
- Run a persistent coding agent on a shared team server for routine tasks while keeping personal agents on your laptop.
- Automate report generation and publish results to Slack on a schedule or via GitHub webhook events.
- Decompose GitHub issues into subtasks automatically and sync them to Linear or Notion.
- Experiment with different LLMs and agent implementations by switching backends from the same UI.
- Deploy agents across multiple cloud providers or on-premises infrastructure from a single control center.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need a self-hosted, multi-backend agent orchestration platform with automation and third-party integrations.
The active maintenance, large community (84043 stars), permissive MIT license, and low install friction support production use. The 85 dependencies and requirement for Python 3.12 or 3.13 are expected for a full orchestration system. No known vulnerabilities. Install if you're building agent-driven workflows; skip if you need a lightweight agent library or are not ready to manage a backend service.
Install
openhands-ai on PyPI
Before you install
Low install friction with a pure-Python wheel. Active maintenance (last commit 2026-08-14, 84043 stars). Requires Python 3.12 or 3.13. Runtime dependency footprint is large (85 dependencies including Docker, Kubernetes, cloud SDKs, and async frameworks), reflecting its role as a full orchestration platform rather than a lightweight library.
Requires Node.js 22.12.x or later and uv (for local install); Docker Desktop or Engine for sandboxed execution; Python 3.12 or 3.13 for the backend agent server.
License in practice
MIT license permits commercial and private use, modification, and distribution with minimal restrictions—standard permissive terms suitable for both self-hosted deployments and integration into other projects.
Quickstart
npm install -g @openhands/agent-canvas
agent-canvas
# Or via Docker:
export PROJECTS_PATH="$HOME/projects"
mkdir -p "$PROJECTS_PATH" "$HOME/.openhands"
docker run -it --rm -p 8000:8000 \
-v "$HOME/.openhands:/home/openhands/.openhands" \
-v "${PROJECTS_PATH}:/projects" \
ghcr.io/openhands/agent-canvas:1.0.0-rc.11Verify before relying
- Whether the 85 runtime dependencies are all required for minimal deployments or if many are optional for specific backends/integrations.
- Performance and resource requirements when running multiple agents or automations concurrently.
- Security hardening specifics beyond the self-hosting guide reference (e.g., network isolation, credential handling).
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <3.14,>=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 85 packagesaiohttpanthropicanyioasyncpgauthlibbashlexbinaryornotboto3browsergym-coredeprecateddeprecationdirhashdockerfastapifastmcpgitpythongoogle-api-python-clientgoogle-auth-httplib2google-auth-oauthlibgoogle-cloud-aiplatformgoogle-genaihtml2texthttpx-aiohttpipywidgetsjinja2joblibjoserfcjson-repairjupyter-kernel-gatewaykubernetes |
| Maintenance | Actively maintained 36 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,805,117 / month, #3,538 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: openhands_ai-1.11.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “coding agent control center”
- openhands-aiOpenHands is a self-hosted developer control center that runs coding…
- mistral-vibeMistral Vibe is a command-line coding assistant that lets you…
- google-agents-cliA CLI toolchain that equips coding agents (Claude Code, Antigravity…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also openhands-aci · openhands-agent-server · openhands-workspace · openhands · openhands-tools · openhands-sdk · google-agents-cli · open-webui · deepagents-code · serena-agent