Our take
Activeregular commits and releases- Activity
- 87
- Community
- 63
- Issues
- 94
- Pull requests
- 82
+769 stars in the last 16 days
- Merges more pull requests than 92% of the projects we track
- Releases more often than 89% of the projects we track
- Closes issues faster than 82% of the projects we track
OpenHuman is a feature-rich Rust harness with active development and releases, but its early-beta status and heavy contributor concentration call for careful evaluation before relying on it in production.
Good fit if
- You want a Rust library as well as a desktop agent, and can work within its Rust-based development stack.
- Your use case benefits from built-in memory, integrations, and agent tools across desktop or server environments.
- You can evaluate the GPL-3.0 license and its implications for your application.
Look elsewhere if
- You need a mature product with less beta-stage uncertainty.
- Your project cannot accept GPL-3.0 obligations.
- You need an agent harness that does not require Rust and Node.js in its development setup.
All health signals
| Last commit | 2026-10-21 (today) |
|---|---|
| Commits, last 90 days | 100+ |
| Releases, last 12 months | 63 (latest v0.64.15, 2026-10-09) |
| Contributors | 100+ (top contributor: 81% of commits) |
| Issues closed, last 90 days | 59+ (typically closed in 0 days) |
| Pull requests merged, last 90 days | 87 (typically merged in 0 days) |
| Project age | 8 months |
Checked on 2026-10-21 with the GitHub API.
Overview
OpenHuman is a Rust-based AI agent harness, delivered as a Tauri desktop app for people and a Rust library for developers. It aims to make agent runs lighter on time, tokens, memory, and CPU, so users can work with agents on desktop while developers can embed agents or run fleets on a server.
The project includes an early-beta desktop experience and a programmable core. Its README describes support for macOS, Windows, and Linux, as well as terminal and headless server use. The repository publishes benchmark results and documentation for its design and integrations.
Key Features
- Rust library API for embedding agents directly in Rust applications, without a separate daemon.
- Desktop, terminal, and headless-server use, with packages for macOS, Windows, and Linux.
- Agent tools for shell and coding tasks, browser and desktop control, web search, documents, and voice.
- Built-in memory that recalls relevant information with citations, with configurable memory engines.
- MCP servers, skill bundles, model routing, and integrations with external apps and messaging channels.
- Approval gates, sandboxed execution, local-only Privacy Mode, and secrets stored in the OS keyring.
- Token compression and Jev tool search, which the project says reduce prompt size and help select tools.
- Workflow graphs with scheduled, event-based, or manual triggers and approval steps.
Use Cases
- Desktop users who want one assistant for browser, computer, search, and document tasks, with approval controls for actions.
- Rust developers embedding an agent in an application or service without running a separate agent process.
- Teams building agent-per-customer products that want to test a single Rust runtime hosting multiple agents.
- Developers comparing agent-harness resource use and task performance using the project's public benchmark setup.
What you need
Detected in the repository
- Node.js (from package.json)
- Rust (from Cargo.toml)
- A Dockerfile, so it can run in a container; a Compose file sets up the related services
- A test suite and automated checks on GitHub Actions
License in plain words
GPL-3.0strong copyleft
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the license notice
- Share your changes: yes, the full source of anything you distribute that includes it, under the GPL
- Includes an explicit patent grant from the contributors:
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Download the desktop app from tinyhumans.ai/openhuman or the latest GitHub release. On macOS or Linux, the installer can also be run with:
curl -fsSL https://raw.githubusercontent.com/tinyhumansai/openhuman/main/scripts/install.sh | bash
See the README for Windows installation, Rust library setup, and development instructions.
Alternatives
- coven: Coven focuses on coding-agent tools within project boundaries, while OpenHuman is a general-purpose Rust harness for agents and fleets.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| OpenHuman | Rust | GPL-3.0 | 42.2k | Active |
| coven | Rust | MIT | 66 | New |
Considerations
- The README labels the application early beta and warns that rough edges are expected.
- Development requires both Node.js and Rust; Docker and Docker Compose are also listed in the project requirements.
- Contributor activity is concentrated: most contributions come from one person, even though the project has a broader contributor base. Review the project's bus factor and maintenance plans before making it a critical dependency.
- The repository is actively maintained, with regular commits and releases, and reports prompt issue and pull-request handling. This is a positive maintenance signal, but does not remove the early-beta caveat.
- The benchmark results and performance claims are published by the project itself. Consult the benchmark repository and assess whether its tasks and setup match your workload.
- GPL-3.0 licensing may affect how you distribute software that incorporates the library; review the license terms for your intended use.
Found this useful?
Share it with someone who would like OpenHuman.