OpenHuman is an open-source agent harness whose core is compiled Rust in a single process. It ships as a desktop app, a terminal app or a headless server, and is licensed GPL-3.0. It is in early beta.
for Builders who already use Claude Code, Codex, OpenClaw or Hermes and want the same ideas (tools, MCP, skills, BYOK models, memory) with lower cost and resource use, including large agent fleets.
use this if you want a fast, lightweight open-source agent harness with built-in memory that can run many agents on a small server.
open tinyhumans.ai ↗Features
$ features --list
- ›Built-in memory over your files, repos, feeds and apps, recalled each turn with citations
- ›Live interruptible voice agent, dictation and spoken replies
- ›Drives a real Chrome browser and desktop apps, asking before irreversible actions
- ›119 OAuth apps through Composio, plus MCP servers and skills
- ›Desktop installers for macOS, Windows and Linux, plus an install script
Pricing
$ pricing --tiers
Open source
Free
GPL-3.0 source and desktop builds; you bring your own model keys.
Why this rank
$ diff --rank 6
Ranked #6 in agent ops, first below the editor-held DeepSeek Harness at #5 and the fixed top four, on adoption: 42,648 stars and 4,215 forks on 2026-11-11, the most of any agent-ops tool outside the top five, with public benchmarks. It is still early beta, and it has not tagged a release since v0.64.15 on 2026-10-09.
Score breakdown
$ scores --rubric
Measured so far · how we rank
Adoption
20% weight
How widely builders already use it for this kind of work. — 42,745 GitHub stars on 2026-11-18. Agent Ops adoption scale: 20 × log10(stars), rounded, capped at 100 (1k stars = 60, 10k = 80, 100k+ = 100); here 20 × log10(42,745) = 92.6. Stars are a proxy for builder adoption, not a usage count. · verified 2026-11-18
Strengths
$ strengths
- ›42,648 GitHub stars and 4,215 forks on 2026-11-11; the README says it was GitHub's #1 trending repo for nine days in a row.
- ›Published, rerunnable SWE-bench harness benchmarks claim 2.3x faster runs and 2.6x fewer tokens than the median of six other harnesses.
- ›Latest tagged release v0.64.15 on 2026-10-09; the default branch was still being pushed on 2026-11-11.
Limitations
$ limits
- ›Early beta by its own description.
- ›GPL-3.0 is copyleft, which matters if you embed it in a product.
- ›Benchmarks are run by the vendor itself.
Sources
$ sources --verified
- overview2026-10-18github.com/tinyhumansai/openhuman
- audience2026-10-18github.com/tinyhumansai/openhuman
- features2026-10-18github.com/tinyhumansai/openhuman
- pricing2026-11-18github.com/tinyhumansai/openhuman
- strengths2026-11-11github.com/tinyhumansai/openhuman
- limits2026-10-18github.com/tinyhumansai/openhuman
- why ranked2026-11-11github.com/tinyhumansai/openhuman
$ buildwith alternatives openhuman
- #1 Hermes AgentFree / OSS
use this if you want an always-on, model-agnostic agent that learns skills over time and lives in your terminal and chat apps.
- #2 HerdrFree / OSS
use this if you want your coding agents to keep running after you close the laptop and to reattach from any terminal.
- #3 OpenClawFree / OSS
use this if you want a hugely popular open-source personal agent that actually does things on any OS and platform.
- #4 PaperclipFree / OSS
use this if you want to run a team of agents (Claude, Codex, Cursor, Hermes and more) toward one goal, with roles, budgets and tickets.
- #5 DeepSeek HarnessFree / OSS
use this if you want an open-source, plugin-first agent harness you can run as a local web UI or desktop app and point at DeepSeek, Claude, OpenAI, Kimi or your own gateway.
- #7 BuzzFree / OSS
use this if your team wants humans and agents working in the same rooms with every message, workflow step and approval in one auditable log.
- #8 ComposioFreemium
use this if your agent needs authenticated access to real apps (Gmail, Slack, GitHub and many more) without you building OAuth and integrations yourself.
- #9 OpenMausBotFree / OSS
use this if you want a chat-app roster of bots running on the Claude, Codex or Grok CLIs and subscriptions you already have, each with its own computer.
- #10 RakazoFree / OSS
use this if you want persistent, self-hosted AI teammates with their own browser and shell, on your own model keys and machines.
- #11 OpenBotFreemium
use this if you want a self-hostable workspace where AI coworkers get their own computers, under company sign-in, tool permissions, approvals and audit.
- #12 HarnessFreemium
use this if you run Claude Code, Codex, Cursor and others across several machines and want one place to watch and steer them.