Open sourceRust · ≈43k stars · GPL-3.0
OpenHuman
Your personal AI, on your own machine — local-first harness.
OpenHuman is TinyHumans' local-first, Rust-written agent harness: it builds a private memory of your life, runs agents and workflows for you, and does the deep research you'd never get to — online or offline, on hardware you own.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsClaims coding tasks finish in about 20s with 2.6x fewer tokens and the lowest bill of seven agents tested (vendor benchmark).[1][2]
- DocsBuilt for fleets: the README claims about 8x less memory and CPU than typical harnesses and 500+ agents on a $10 VPS.[1]
- MetadataFast-moving Rust codebase with frequent releases (v0.64.15) and about 42k stars in eight months.[1]
Cons
- MetadataIts headline performance numbers are self-published; independent discussion on HN is close to nonexistent.[1][2]
- MetadataGPL-3.0 licensed, which limits proprietary embedding.[1]
- User reportsOpen issues show runtime rough edges: TinyJuice summaries block agent turns for 15-30s, and the renderer gets stuck in an update loop while tool calls stream.[1][2]
- DocsThe maintainers' own tracker plans Terminal-Bench runs to separate harness failures from model failures, so independent benchmark coverage is still pending.[1]
- Best for
- Running many lightweight agents cheaply on small servers, if you can validate the efficiency claims yourself.
- Watch out for
- Treat the benchmark claims as vendor marketing until you've reproduced them, and check GPL-3.0 compatibility.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
TinyHumans
Founder
OpenClaw, Hermes & personal agents · Context engineering & memory
Activity
- Last push
- · yesterday
- Latest release
- v0.64.15
· 6w ago - Last 90 days
- 7 releases
v0.64.15OpenHuman v0.64.15
· 6w agoThe Installed-Build Reliability Upgrade This release focuses on keeping installed apps rock-solid—especially when loading key modules like search and memory. Onward and upward! 🎉 Highlights Modules & installed builds 🧩 A targeted hotfix improves module admission in installed…
v0.64.14OpenHuman v0.64.14
· 6w agoThe Files, Memory & Voice Power-Up 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 the stack. 🎉 Highlights Files & project…
v0.64.10OpenHuman v0.64.10
· 7w agoThe Speed, Structure & Reliability Upgrade 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 iteration. 🎉 Highlights Performance &…
v0.64.7OpenHuman v0.64.7
· 7w agoThe Intelligence Upgrade 🎉 v0.64.4 to v0.64.7 brings 12 PRs across 12 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨ Highlights 🚀 ✅ Tasks, chat & agent workflows Task, chat,…
v0.64.4OpenHuman v0.64.4
· 8w agoThe Better Windows Desktop Upgrade This release is all about making the Windows desktop experience more reliable, more polished, and smoother to operate—especially when you’re offline. 🎉 Highlights Offline-ready Windows installers 📦 Windows desktop installers now bundle all…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
The team behind it
Est. 2026
Open-source AI agents that work for you.
TinyHumans builds a family of open-source agents: OpenHuman, a local-first Rust harness with private lifelong memory; OpenCompany, an agent 'hive mind' that thinks as one team; and Medulla, a terminal that runs Claude Code, Codex and OpenCode side by side.
Neighbours on the workbench
JavaScript · ≈308k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
TypeScript · ≈265k stars · MIT
NousResearch/hermes-agent
The agent that grows with you.
Maintained by Nous Research
v0.23.3releasedPython · ≈151k stars · Apache-2.0
Graphify-Labs/graphify
A /graphify skill that turns a codebase, docs and schemas into a queryable knowledge graph.
Maintained by Graphify-Labs
v0.9.114releasedConnections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- TinyHumansStartup
Similar entries · 2
- Hermes AgentProject
- TinyHumansStartup
