- This release focuses on keeping installed apps rock-solid—especially when loading key modules like search and memory. Onward and upward! 🎉
- (#7155) — Thank you @senamakel!
Openhuman by Tiny Humans
Open-source agent harness from Tiny Humans, shipped as a desktop app for macOS, Windows and Linux and as a Rust library for developers. It is built to run large fleets of agents cheaply: the project says more than 500 agents fit on a $10 VPS. The project describes itself as an early beta.
Use it in: Desktop app API / SDK CLI Slack, Teams, Telegram Self-hosted Works with: MCP Local models Own API key Multi-agent Headless / CI
Usage data: latest readings Oct 20 to Oct 21, 2026, last checked Oct 21, 06:38 UTC. Date of each number
What Openhuman does
Openhuman is an agent harness, desktop app and Rust library from Tiny Humans, first released in February 2026. You use it through desktop app, an SDK, a command-line tool, messaging apps and self-hosted. Its documentation covers MCP servers, subagents or parallel agents, a non-interactive mode for scripts and CI, your own API key and local models. It is used from Rust. It is free and open source (GPL-3.0); you pay only for the models it calls.
Key facts
| Maker | Tiny Humans |
|---|---|
| Type | Agent harness, desktop app and Rust library |
| First released | February 2026 |
| License | GPL-3.0 |
| Interfaces | Desktop app, SDK, CLI, Messaging apps, Self-hosted |
| Main language | Rust |
| Open issues and PRs | 308 |
Pricing
Free and open source (GPL-3.0).
Source: official pricing page, checked Oct 11, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (GPL-3.0)
- Where you use itDesktop app, SDK, CLI, Messaging apps, Self-hosted
- Supports MCP?Yes
- Subagents / multi-agent?Yes
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
Add-ons for Openhuman: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Openhuman or for agent frameworks in general. Savings and results depend on your workload.
Openhuman alternatives
Best Openhuman alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
78 | 39.1M | down 0.5% | down 9.0% | 148K+73/day | 1.4.67d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
71 | 14.4M | down 10.5% | up 4.6% | 43.6K+57/day | 1.2.165d ago | Free (OSS) | |||
| 3 |
AI SDKVercel |
64 | 18.4M | down 40.8% | up 27.5% | 27.4K+19/day | 5.0.279today | Free (OSS) | |||
| 4 | 63 | 8.8M | down 0.2% | up 3.4% | 8,887+14/day | 1.61.16d ago | Free (OSS) | ||||
| 5 |
Claude Agent SDKAnthropic |
61 | 15.1M | down 24.1% | down 0.5% | 8,315+7/day | 0.2.170today | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
58 | 4.4M | down 17.4% | down 10.0% | 30.2K+26/day | 0.24.06d ago | Free (OSS) | |||
| No agents match that filter. | |||||||||||
Ratings from people who use Openhuman
No ratings yet. Used Openhuman? Rate it and say what it is good and bad at.
Openhuman news
-
10 agents added to AgentGid
Paperclip, Graphify, Agent-Reach, ECC, OpenMontage, Ruflo, OmniRoute, Claude Mem, Ragflow, Openhuman
-
Openhuman 0.64.15 released
This release focuses on keeping installed apps rock-solid—especially when loading key modules like search and memory. Onward and upward! 🎉; (#7155) — Thank you @senamakel!
-
Openhuman 0.64.14 released
This release is a big step forward in day-to-day usability: clearer files and sessions, a major memory evolution, and real-time voice agents—plus a ton of reliability and performance work across…; Imports and migrations are significantly hardened: clearer…
What changed: recent Openhuman releases
11 stable releases in the last 90 days · Full changelog
- This release is a big step forward in day-to-day usability: clearer files and sessions, a major memory evolution, and real-time voice agents—plus a ton of reliability and performance work across…
- Imports and migrations are significantly hardened: clearer “building vs empty” states, smarter batching/retries, better failure visibility with retry controls, more reliable resuming, and improved…
- This also includes targeted fixes for web research budgets, credential scrubber behavior (including avoiding code redaction), handling HTTP status correctly, and improved orchestration behaviors.…
- The local AI story is also simplified: in-app model downloads and Ollama lifecycle management were removed, while continuing to support local inference via user-run endpoints. (#6978, #6996,…
- Release-specific work also improved macOS notarization of module bundles (with signature verification and tests), and headless deployments gained better keyring support. Benchmark tooling and docs…
- A few more focused contributions round out this release with targeted fixes and improvements that are worth calling out. (#6979, #6994, #7093, #7095) — Thank you @senamakel and @M3gA-Mind!
Earlier releases
- This release tightens the core experience from end to end—faster first turns, clearer chat feedback, sturdier integrations, and a big internal modularity push that sets us up for even quicker…
- (#6787, #6788, #6823) — Thank you @senamakel!
- (#6802, #6827, #6800, #6810) — Thank you @senamakel and @M3gA-Mind!
- (#6777) — Thank you @senamakel!
- (#6767, #6769, #6818, #6689, #6796) — Thank you @senamakel, @M3gA-Mind, and @oxoxDev!
- (#6776, #6709, #6764, #6790) — Thank you @senamakel, @Avi-Bendetsky, and @sanil-23!
- M3gA-Mind (#6672, #6693) — thank you!
- senamakel (#6668, #6678, #6683, #6700, #6701, #6702, #6704, #6759, #6760) — thank you!
- siddarthkay (#6699) — thank you!
- This release is all about making the Windows desktop experience more reliable, more polished, and smoother to operate—especially when you’re offline. 🎉
- v0.64.0 → v0.64.3 is all about making OpenHuman feel steadier under real workloads—fewer loops, better recovery, faster turn startup, and clearer billing/usage surfaces. Ship it. 🚀
- Big thanks to everyone who shipped v0.64.0 → v0.64.3: @senamakel, @M3gA-Mind.
Openhuman popularity and usage data
The GitHub repository has 42.2K stars, 2,467 of them added in the last 30 days. The latest stable release is 0.64.15, published Oct 9, 2026; there were 7 stable releases in the past 30 days.
Download the raw daily series: openhuman.csv
Gid Score breakdown
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| GitHub stars | Oct 21, 2026 | Oct 21, 06:32 UTC |
| Website rank (Tranco) | Oct 20, 2026 | Oct 21, 06:38 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.
Openhuman FAQ
How much does Openhuman cost?
Free and open source (GPL-3.0).
Is Openhuman open source?
Yes. Openhuman is open source, released under the GPL-3.0 license.
How popular is Openhuman?
The GitHub repository has 42.2K stars, 2,467 of them added in the last 30 days. The latest stable release is 0.64.15, published Oct 9, 2026; there were 7 stable releases in the past 30 days.
What is the latest version of Openhuman?
The latest stable release we track is 0.64.15, published on Oct 9, 2026.
What are the alternatives to Openhuman?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Strands Agents.
For the makers of Openhuman badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/openhuman/)
[](https://agentgid.com/agents/openhuman/)
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
GitHub: tinyhumansai/openhuman. Site rank: tinyhumans.ai on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: tinyhumans.ai, github.com.
