Skip to content
Agents tracked: 442 Downloads (7d): 202M down 19.3% GitHub stars: 10.4M Releases (7d): 693 Agent status: 1 with issuesSince last limit reset: Claude 28d · Codex 1d Updated Oct 21, 2026

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.

Agent frameworks and SDKs New · Added to AgentGid on Oct 11, 2026Agent harness, desktop app and Rust libraryOpen source · GPL-3.0Free to start

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

Price
Free (OSS)
free and open source
Popularity
#35 in Frameworks
Gid Score 24 / 100 · #35 of 42 ranked frameworks and SDKs
Trend
Gaining stars
about +43 GitHub stars a day
Development
Actively updated
latest 0.64.15, 12d ago
Community
42.2K GitHub stars
public signals

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

MakerTiny Humans
TypeAgent harness, desktop app and Rust library
First releasedFebruary 2026
LicenseGPL-3.0
InterfacesDesktop app, SDK, CLI, Messaging apps, Self-hosted
Main languageRust
Open issues and PRs308

Pricing

Free and open source (GPL-3.0).

Source: official pricing page, checked Oct 11, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

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

All agent tooling

Listed because each tool documents support for Openhuman or for agent frameworks in general. Savings and results depend on your workload.

Compare Openhuman with another agent

vs
# 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 61 15.1M down 24.1% down 0.5% 8,315+7/day 0.2.170today Free (OSS)
6 58 4.4M down 17.4% down 10.0% 30.2K+26/day 0.24.06d ago Free (OSS)

Ratings from people who use Openhuman

No ratings yet. Used Openhuman? Rate it and say what it is good and bad at.

Openhuman news

All AI agent news

  1. New on AgentGid AgentGid

    10 agents added to AgentGid

    Paperclip, Graphify, Agent-Reach, ECC, OpenMontage, Ruflo, OmniRoute, Claude Mem, Ragflow, Openhuman

  2. Release GitHub Releases

    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!

  3. Release GitHub Releases

    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

0.64.15
  • 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!
0.64.14
  • 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
0.64.10
  • 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!
0.64.7
  • M3gA-Mind (#6672, #6693) — thank you!
  • senamakel (#6668, #6678, #6683, #6700, #6701, #6702, #6704, #6759, #6760) — thank you!
  • siddarthkay (#6699) — thank you!
0.64.4
  • This release is all about making the Windows desktop experience more reliable, more polished, and smoother to operate—especially when you’re offline. 🎉
0.64.3
  • 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.

GitHub starsrunning total 42.2K
Website rankTranco list; a lower rank means more traffic #1,128,678

Download the raw daily series: openhuman.csv

Gid Score breakdown

Adoption0
Community68
Attention—
Momentum53

Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.

How fresh these numbers are

NumberLatest readingLast checked
GitHub starsOct 21, 2026Oct 21, 06:32 UTC
Website rank (Tranco)Oct 20, 2026Oct 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:

AgentGid: #35 in Frameworks Gid Score: 24/100

[![AgentGid: #35 in Frameworks](https://agentgid.com/badges/openhuman-rank.svg)](https://agentgid.com/agents/openhuman/)
[![Gid Score: 24/100](https://agentgid.com/badges/openhuman-score.svg)](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.