OpenHands

AI Coding Assistants AI Productivity Tools AI Developer APIs & Platforms AI No-Code / Automation Tools

↳AI Pair Programming & Terminal Agents ↳AI Code Generation & Autocomplete ↳AI Agent Builders ↳AI App Builders for Developers

Freemium

The open platform for cloud coding agents — autonomous, transparent, and in your control

0(0 votes)

0 views

Released 2024

Visit Website

Gallery

6 items

1 of 6

VIDEO

VIDEO

About OpenHands

OpenHands (formerly OpenDevin) is the world's most-starred open-source platform for cloud coding agents, built by All Hands AI and founded in 2024 by Robert Brennan (CEO), Xingyao Wang (Chief AI Officer, UIUC CS PhD), and Graham Neubig (Chief Scientist, CMU professor). The project launched on GitHub in March 2024 as an open-source alternative to Devin, and within months accumulated 80,800+ stars, 9,700+ forks, and 4 million downloads — making it the fastest-growing open-source coding agent project. It was published as a conference paper at ICLR 2025 and has been adopted by engineers at Apple, Google, Amazon, Netflix, TikTok, NVIDIA, Mastercard, VMware, AMD, Red Hat, and MongoDB.

Unlike code suggestion tools like GitHub Copilot, OpenHands runs autonomous agents that complete entire engineering tasks end-to-end: given a bug ticket, a vulnerability report, or a migration request, an OpenHands agent will plan the approach, write code across multiple files, execute terminal commands, browse the web for documentation, run tests, and push a pull request — all without human intervention. The platform is model-agnostic (Claude, GPT, Gemini, DeepSeek, Llama, and more via BYOK or the OpenHands LLM provider at-cost), runs agents in sandboxed containerized environments, and scales from a single local developer to thousands of parallel enterprise agents. Automations trigger agent workflows from GitHub, Slack, Jira, Linear, and 70+ other integrations, keeping agents working even when the team is offline.

All Hands AI raised a $5M seed led by Menlo Ventures in September 2024 (with Pillar VC, Betaworks, and co-founders of Hugging Face and Cloudera) and an $18.8M Series A led by Madrona in November 2025 (with Obvious Ventures, Fujitsu Ventures, and Alumni Ventures), totaling $23.8M. Enterprise customers report resolving 87% of bug tickets same-day, reducing code-maintenance backlogs by up to 50%, and cutting vulnerability resolution from days to minutes.

Key Features

Autonomous cloud coding agents — agents plan, write code, execute terminal commands, browse the web, run tests, and push PRs end-to-end without human hand-holding
Agent Canvas — web-based GUI, Terminal UI, and Desktop app for managing multiple parallel agent conversations and automations from one interface
Automations — event-triggered agent workflows for GitHub PR review, Jira incident triage, Slack channel monitoring, CI failure fixing, and security vulnerability remediation
70+ integrations — native connections to GitHub, GitLab, Slack, Jira, Linear, Notion, Figma, Supabase, Stripe, Sentry, Datadog, Cloudflare, Vercel, and more via MCP
Model-agnostic architecture — works with any LLM: Claude, GPT, Gemini, DeepSeek, Llama, Mistral, and more via BYOK or the OpenHands LLM provider at-cost
Large Codebase SDK — maps dependencies across large systems and orchestrates multi-agent changes in the correct order without conflicts (Enterprise)
Open-source MIT license — 80,800+ GitHub stars, 9,700+ forks, 4M+ downloads, contributions from hundreds of developers worldwide
Sandboxed execution environments — agents run in isolated, containerized runtimes; Enterprise supports VPC/self-hosted deployment where code never leaves your environment

Pros

Most-starred open-source coding agent on GitHub with 80,800+ stars and MIT license — transparent, community-audited, and free forever to self-host
Fully autonomous end-to-end task completion — not autocomplete or suggestions; agents actually plan, code, test, and push PRs
Model-agnostic with BYOK — no vendor lock-in; use Claude, GPT, Gemini, DeepSeek, Llama, or any other LLM
70+ integrations and event-triggered automations run agents in the cloud even when your machine is off
Trusted by engineers at Apple, Google, Amazon, Netflix, TikTok, NVIDIA, Mastercard, VMware, AMD, and MongoDB
Enterprise adopters report 87% of bug tickets resolved same-day and code-maintenance backlogs reduced by up to 50%

Cons

Fully autonomous agents can make unintended changes — production use requires careful scope control and human review of diffs before merging
Cloud Individual plan limits daily conversations to 10 — heavy users need Enterprise for unlimited runs
Self-hosted deployment requires Docker and local setup; not a zero-config experience for non-technical teams
Enterprise pricing is custom and sales-gated — no transparent list price for team deployments
Open-source core means community support on the free tier; production SLAs and priority support require Enterprise

Pricing

OpenHands has three tiers. The Open Source plan is free forever (MIT license) — self-host locally with your own LLM keys, with a web-based GUI, terminal UI, CLI, Git integrations, and community support. No infra cost.

The Cloud Individual plan is also free, adding hosted cloud access from desktop and mobile, API support for automation and scripting, Jira and Slack integrations, and BYOK or access to the OpenHands LLM provider at-cost with no markup. The Individual plan supports 1 user with up to 10 conversations per day.

Enterprise has custom pricing and adds VPC or self-hosted deployment (code never leaves your environment), Enterprise SAML/SSO, RBAC, unlimited concurrent conversations per user, the Large Codebase SDK for large/legacy codebases, centralized team billing, Agent Control Plane, audit logs, budget controls, priority support, a named Customer Engineer, and a shared Slack channel. Contact sales at openhands.dev/contact.

Claim Verified Creator Badge

Are you the founder of OpenHands? Display this listing's verified badge on your website to show your customers that your product has been vetted and listed on AI Central Resources.

HTML Embed Code

<a href="https://www.aicentralresources.com/tool/openhands" target="_blank" rel="noopener">
  <img src="https://www.aicentralresources.com/badges/featured-badge-dark.svg" alt="Featured on AICentralResources" width="200" height="54" style="border: none;" />
</a>

* Place this HTML snippet in your website's footer, landing page, or press section. This creates a search-friendly backlink directly to your verification page.

Connect with OpenHands

X (Twitter)LinkedIn Discord GitHub YouTube

Frequently Asked Questions

OpenHands is an open-source, model-agnostic platform for cloud coding agents. Unlike GitHub Copilot or ChatGPT, which suggest code, OpenHands runs autonomous agents that complete entire engineering tasks end-to-end: they plan, write code across files, execute terminal commands, browse the web, run tests, and push pull requests. You hand it a task — a bug ticket, a vulnerability, a migration — and it ships the change. It is the most-starred open-source coding agent on GitHub with 80,800+ stars.

OpenHands was built by All Hands AI, founded in 2024 by Robert Brennan (CEO), Xingyao Wang (Chief AI Officer, CS PhD candidate at UIUC), and Graham Neubig (Chief Scientist, CMU professor). The project began in March 2024 as OpenDevin — an open-source alternative to Devin — and grew into a company. The $5M seed was led by Menlo Ventures (Sep 2024); the $18.8M Series A was led by Madrona with Obvious Ventures, Fujitsu Ventures, and Alumni Ventures (Nov 2025). Total funding: $23.8M.

The open-source version is fully free and MIT licensed — self-host it locally or on your cloud with your own LLM keys at zero cost. The hosted Individual plan is also free with BYOK or pay-as-you-go model access at cost (no markup). Enterprise has custom pricing and adds VPC deployment, SSO, RBAC, audit logs, and dedicated support.

OpenHands is model-agnostic and supports all major LLMs: Claude (Anthropic), GPT and o-series (OpenAI), Gemini (Google), DeepSeek, Llama, Mistral, and others via API. You can bring your own API keys or use the OpenHands LLM provider at cost with no markup. The platform is designed so you are never locked to a single model provider.

At the enterprise level, OpenHands runs inside your VPC or on-premises so your code never leaves your environment. Agents run in sandboxed, containerized execution environments. The platform provides full audit logs and the Agent Control Plane gives engineers complete visibility and governance over every agent run. OpenHands maintains a public Trust Center at Vanta.