33rd of 37 in Assistants

openhuman

Rust agent harness with desktop app, built-in memory and embeddable library

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 42.3k
License: GPL-3.0
Last commit: Oct 2026
Last release: Oct 2026
Language: Rust

Stars, last 30 weeks+42,274

9 on 27 Mar 202642,283 on 23 Oct 2026

From GitHub's daily star counts.

Checked 24 Oct 2026 on GitHub.

Overview

OpenHuman is a single-process Rust agent harness shipped as a desktop app (macOS, Windows, Linux), a terminal app, a headless server and an embeddable Rust crate. It bundles memory recalled with citations, browser and desktop control, MCP and skills, 14 messaging channels, durable workflows, and local or BYOK models. The README reports its own benchmark on ten SWE-bench tasks and claims 500 agents fit on a $10 VPS; it is labelled early beta.

Who it is for: Users wanting a self-run agent app, and Rust developers embedding agents

Ranked among open-source alternatives to Manus (#3 of 10).

Strengths

Embeds as a typed Rust library, no sidecar or daemon needed
Public benchmark repo; reports 68 MB peak memory and 19.8 s median task time
Local models (Ollama, LM Studio, MLX) or BYOK across 26 providers
Approval gate, OS-jail or Docker sandboxing, secrets stored in OS keyring

Weaknesses

Labelled early beta; README warns of rough edges
Benchmark is self-run on only ten tasks
GPL-3.0 license constrains embedding in proprietary products
119 OAuth app integrations go through Composio, an external service

What it needs

GPU optional
Docker + Compose
Needs Composio (OAuth integrations), Ollama / LM Studio / MLX (optional local models), Docker (optional sandbox)
Models: Ollama, LM Studio, MLX, OpenAI-compatible APIs, 26 BYOK providers

Quick answers

Is openhuman open source?

Yes. Its code is on GitHub under the GPL-3.0 license.

Can you run openhuman with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does openhuman need a GPU?

No. It runs on a CPU and can use a GPU when you have one.

Head to head

Also in Assistants

See all 37

Also in Assistants
Rank	Project	Score
1	career-opsJob-search agent that scores listings, tailors CVs and drafts applications76.9k starsMIT	95 out of 100
2	ai-job-searchClaude Code workflow that searches job boards and drafts tailored CVs and cover letters64.2k starsMIT	95 out of 100
#4	OpenClawPersonal AI assistant reachable through Discord, Slack, Telegram, WhatsApp and more392.9k starsMIT	92 out of 100
#5	airiAI VTuber companion with VRM and Live2D avatars, voice, and game-playing Live demo ↗ (opens in a new tab)50.6k starsMIT	91 out of 100
#6	Hermes AgentSelf-hosted agent with skill learning, memory and Telegram/Discord/Slack gateway256.6k starsMIT	87 out of 100

How to choose

Check which channels it supports today (WhatsApp, Telegram, Slack, Discord, email) and whether each needs a paid API.
Look at how memory is stored and whether you can inspect or wipe it.
Actions need credentials; prefer assistants that scope them per tool.

Health

Releases: 63 in the last 12 monthsLast one 15 days ago
Top contributor: 57% of commits35,590 of 62,317 in the last 12 months
Security advisories: 12 published ↗ (opens in a new tab)On GitHub, in the last 12 months; 10 critical or high
OpenSSF Scorecard: Not checked

Read from GitHub, deps.dev and OpenSSF on 23 Oct 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

GPL-3.0 Copyleft

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: If you distribute it, or software built on it, share the full source under GPL-3.0. Running it on your own servers is not distributing.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

Set it up

Needs before it works: Composio (OAuth integrations), Ollama / LM Studio / MLX (optional local models), Docker (optional sandbox).

Bring in an engineer who knows openhuman. By the hour for upkeep and fixes, or a fixed price for a build. Our own engineering service; it never changes a rank.

Where to run it

Vast.ai ↗ (opens in a new tab)Rent a GPU by the hour from a marketplace of hosts.
RackNerd ↗ (opens in a new tab)Budget KVM VPS from $26.99 a year to run Docker apps yourself.
RepoCloud ↗ (opens in a new tab)One-click hosting for about 890 open-source apps, each on its own VPS.
Clore.ai ↗ (opens in a new tab)A GPU marketplace; its August 2026 price guide puts an RTX 3090 near $0.09 an hour.

Referral links: if you sign up through one, we get a commission. They never change a rank.

Ask your AI assistant

The rankings as an MCP server for Claude, Cursor, ChatGPT and any MCP client. Free, no key, read-only.

Claude Codeclaude mcp add archestack -- npx -y @archestack/mcp

Connector URLhttps://mcp.archestack.com/mcp

Then ask: Compare openhuman with its top alternatives on Archestack

Setup for other apps

#3 of 37 in Assistants on Archestack, as of 24 Oct 2026.

Show it in your README or on your site

The badge below goes in a README; a card with the rank, score and signals goes on a site or blog. Both update twice a day.

Show code

README (Markdown)

[![Archestack](https://archestack.com/badge/tinyhumansai/openhuman.svg)](https://archestack.com/best-of-ai/projects/openhuman/)

Site or blog (HTML)

<iframe src="https://archestack.com/embed/best-of-ai/openhuman/" title="openhuman on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

How badges work Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with openhuman filled in.

Chat and assistants

Agents and MCP

RAG, search and memory

Voice

Image and video

Workflows

Coding with AI

Apps and SaaS

Models and ML

Security

Learning

By field