- feat(cloud): pick the exact connected git provider for repositories
- feat(verify-openhands): every run has a non-loopback plain-HTTP origin
- fix(filters): close EnumFilterDropdown menus on Escape
- fix(automations): restore native webhook source validation
- fix(clipboard): support fallback when Clipboard API is unavailable
- docs(verify-openhands): map maintenance 2026-11-17
OpenHands
Open-source AI software-development agent platform (formerly OpenDevin) with an open-source browser client (Agent Canvas; the older Docker-based local GUI is deprecated), a terminal UI/CLI, a hosted cloud and an SDK. It is model-agnostic and can use the user's own keys.
Use it in: Web app CLI API / SDK Works with: MCP Local models Own API key Headless / CI
On this page
Usage data: latest readings Oct 31 to Nov 19, 2026, last checked Nov 19, 06:32 UTC. Not updated since Oct 31: Wikipedia views. Date of each number
What OpenHands does
OpenHands is an agent platform (web GUI + terminal UI/CLI + cloud) from OpenHands, first released in March 2024. You use it through a web app, a command-line tool and an SDK on macOS, Linux and Windows (WSL). Its documentation covers MCP servers, a non-interactive mode for scripts and CI, your own API key and local models. It can run models from Anthropic, OpenAI, Google, Amazon Bedrock, OpenRouter and any OpenAI-compatible endpoint. Paid plans start at $500 a month; there is a free tier.
Status: Renamed from OpenDevin in 2024-08 (per Wikipedia); the GitHub repo has since moved from All-Hands-AI/OpenHands to OpenHands/OpenHands.
Key facts
| Maker | OpenHands (formerly All Hands AI) |
|---|---|
| Type | Agent platform (web GUI + terminal UI/CLI + cloud) |
| First released | March 2024 |
| License | MIT |
| Interfaces | Web, CLI, SDK |
| Platforms | macOS, Linux, Windows (WSL) |
| Models | Model-agnostic: user's own keys or OpenHands-hosted models at cost |
| Local models | LM Studio, Ollama, vLLM and SGLang (docs) |
| Bring your own API key | Yes |
| Main language | TypeScript |
| Open issues and PRs | 1,217 |
Pricing
OpenHands is free for local open-source deployment. Cloud plans: Teams at $500/month (up to 10 seats, $50/mo per additional seat, capped at 5,000 sessions/month, 30-day trial). Enterprise custom pricing available. All paid tiers include self-hosted deployment, bring-your-own LLM, and RBAC.
Source: official pricing page, checked Oct 28, 2026. Prices change often; confirm before you buy.
- Oct 28, 2026: Free + $499/mo → Free + $500/mo
OpenHands pricing history since 2024 · Compare prices of all agents
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Works with local models?Yes
- Bring your own API key?Yes
- Runs onmacOS, Linux, Windows (WSL)
- Where you use itWeb, CLI, SDK
- Supports MCP?Yes
- Model providersanthropic, openai, google, amazon, openrouter, any OpenAI-compatible, local
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativeClaude Code · all alternatives
What's new in OpenHands: November 2026 so far
November brought significant improvements to automations, workspace persistence, and UI refinements. The month focused on better repository handling, theme support, and conversation management.
- Automations now display Mermaid diagrams to explain each workflow visually.
- Added a Download button to the Files tab for easier file access.
- Sidebar can now be resized by dragging its edge, with larger text for readability.
- Workspace and repository metadata now persist as server-side tags.
7 releases this month · summarised from the official release notes · all months
Get started with OpenHands
| PyPI | pip install openhands-ai |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
OpenHands safety and permissions
| Out of the box | The CLI asks for confirmation before actions. |
|---|---|
| Sandbox | built-in Runs the agent in a Docker sandbox by default; a process runtime runs it on the host without isolation. |
| Approval modes | CLI confirmation modes: always ask (default), --llm-approve (security analyzer) and --always-approve. |
| Hooks | PreToolUse hooks can block an action. |
Add-ons for OpenHands: save tokens, add memory and tools
Listed because each tool documents support for OpenHands. Savings and results depend on your workload.
OpenHands alternatives
Best OpenHands alternatives compared · All terminal coding agents
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
Claude CodeAnthropic |
88 | 18.9M | up 15.1% | up 15.5% | 156K+136/day | 2.1.328yesterday | $20/mo | |||
| 2 |
OpenAI CodexOpenAI |
84 | 26.6M | up 2.4% | up 7.4% | 136K+144/day | 0.168.07d ago | Free + $8/mo | |||
| 3 |
OpenCodeAnomaly (SST team) |
80 | 3.9M | up 15.4% | up 28.7% | 228K+266/day | 2.3.22d ago | Free + $10/mo | |||
| 7 |
PiEarendil Inc. (created by Mario Zechner) |
73 | 6.4M | up 1.6% | up 36.3% | 123K+193/day | 1.5.210d ago | Free (OSS) | |||
| 15 |
Gemini CLIGoogle |
62 | 495K | up 16.9% | up 6.8% | 109K+35/day | 0.69.0yesterday | API usage or license | |||
| 20 |
ClineCline Bot Inc. |
58 | 84.3K | down 8.7% | up 14.9% | 71.8K+38/day | 4.1.2625d ago | Free + $9.99/mo | |||
Ratings from people who use OpenHands
No ratings yet. Used OpenHands? Rate it and say what it is good and bad at.
OpenHands news
-
OpenHands 1.42.0 released
feat(cloud): pick the exact connected git provider for repositories; feat(verify-openhands): every run has a non-loopback plain-HTTP origin; fix(filters): close EnumFilterDropdown menus on Escape
-
OpenHands 1.41.0 released
feat(verify-openhands): scenarios beyond the happy path, map controls, browser timezone; feat(acp): choose the reasoning effort from what the agent reports; feat(hooks): name the workspace and user hooks files in the Available Hooks dialog
-
OpenHands downloads up 146% in a week
86.6K PyPI downloads in the 7 days to Nov 12, against 35.2K the week before.
What changed: recent OpenHands releases
31 stable releases in the last 90 days · Monthly summary · Full changelog
- feat(verify-openhands): scenarios beyond the happy path, map controls, browser timezone
- feat(acp): choose the reasoning effort from what the agent reports
- feat(hooks): name the workspace and user hooks files in the Available Hooks dialog
- feat(analytics): instrument automation setup funnel dead ends
- feat: reuse profile secret consent for automatic managed App enablement
- feat(automations): group the dashboard list by tag
Earlier releases
- feat: improve Codex subscription authentication guidance
- fix(chat): keep messages at tied history page boundaries
- fix(chat): prevent delayed echoes from deleting newer drafts
- fix(chat): activate the home model pick when a self-hosted instance turns Agent Profiles off
- fix(git): use a repository's real default branch instead of assuming "main"
- fix(i18n): add the missing Indonesian translations for the Codex subscription keys
- feat(automations): filter the dashboard by owner with a Service accounts option
- feat(chat): move the message hover timestamp closer to its message
- feat(conversation): keep Stop hook feedback out of the chat
- feat(themes): print Paper as aged newsprint, with readable warnings
- feat(verify-openhands): Server: lines link Canvas families to Agent Server features
- fix(chat): interpret resume visibility timestamps as UTC
- feat: edit executable plugin configuration in automation help
- feat: display conversation budgets with semantic meter fills
- feat: add Paper theme to Agent Canvas
- feat(chat): show a resolved banner for project conversations
- feat(themes): finish Light+ and Solarized contrast pass
- feat(launch): automation-aware install via mode=automation + POST /plugin-spec (toward
- feat(automations): explain each automation with a Mermaid diagram
- fix(chat): place resumed sessions after UTC conversation history
- fix: keep generated conversation titles visible during startup handoff
- fix: wait for session replay before showing empty chat suggestions
- fix: load the home page at the base path without a trailing slash
- perf(chat): avoid repeated history scans during live updates
OpenHands prices over time
OpenHands popularity and usage data
OpenHands was downloaded 105K times from PyPI in the week ending Nov 17, 2026, up 239.6% on the week before. Its download count moved to a different level overnight on Sep 29, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 93.8K stars, 2,718 of them added in the last 30 days. The latest stable release is 1.42.0, published Nov 18, 2026; there were 15 stable releases in the past 30 days. On Terminal-Bench 2.0 its best listed result is 51.9% with Claude Opus 4.5, ranking 35 of 43 agents on that board. It was mentioned in 4 Hacker News posts and comments over the last 30 days.
Download the raw daily series: openhands.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Website rank (Tranco) | Nov 18, 2026 | Nov 19, 06:32 UTC |
| Wikipedia views | Oct 31, 2026 not updated for 20 days | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
OpenHands benchmark results
| Benchmark | Model | Effort | Tasks solved | Cost of run | Place |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Claude Opus 4.5 · v1.1.0 | — | 51.9% ± 2.9 | — | #35 of 43 |
| GPT-5 · v0.60.0 | — | 43.8% ± 3.0 | — | ||
| Claude Sonnet 4.5 · v0.60.0 | — | 42.6% ± 2.8 | — | ||
| Claude Opus 4.1 · v0.60.0 | — | 36.9% ± 2.7 | — |
Up to four best runs per board. Scores are not comparable between Terminal-Bench versions. Source: Terminal-Bench (tbench.ai).
OpenHands FAQ
How much does OpenHands cost?
OpenHands is free for local open-source deployment. Cloud plans: Teams at $500/month (up to 10 seats, $50/mo per additional seat, capped at 5,000 sessions/month, 30-day trial). Enterprise custom pricing available. All paid tiers include self-hosted deployment, bring-your-own LLM, and RBAC.
Is OpenHands open source?
Yes. OpenHands is open source, released under the MIT license.
How popular is OpenHands?
OpenHands was downloaded 105K times from PyPI in the week ending Nov 17, 2026, up 239.6% on the week before. Its download count moved to a different level overnight on Sep 29, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 93.8K stars, 2,718 of them added in the last 30 days.
What is the latest version of OpenHands?
The latest stable release we track is 1.42.0, published on Nov 18, 2026.
What are the alternatives to OpenHands?
The closest alternatives in the same category by Gid Score are Claude Code, OpenAI Codex, OpenCode, Pi.
For the makers of OpenHands badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/openhands/)
[](https://agentgid.com/agents/openhands/)
[](https://agentgid.com/agents/openhands/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: openhands-ai. GitHub: OpenHands/OpenHands. Wikipedia: OpenHands. Site rank: openhands.dev on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: openhands.dev, docs.openhands.dev, github.com, pypi.org, en.wikipedia.org.