OpenHuman
Private. Simple. Extremely powerful. The first agent harness that truly knows you — with a Memory Tree, 118+ integrations, and a face that speaks.
curl -fsSL https://raw.githubusercontent.com/tinyhumansai/openhuman/main/scripts/install.sh | bash
irm https://raw.githubusercontent.com/tinyhumansai/openhuman/main/scripts/install.ps1 | iex
What is OpenHuman?
Context in minutes,
not weeks.
Most agents start cold. OpenHuman skips the wait. Connect your accounts, let auto-fetch pull data locally on a 20-minute loop, and Memory Trees compress everything into a Karpathy-style Obsidian wiki. One sync pass — full context of your inbox, calendar, repos, docs, and messages. No training period. It becomes you, controlled by you.
Features
Batteries Included.
Memory Tree + Obsidian Wiki
Local-first knowledge base built from your data. Everything canonicalized into Markdown chunks, scored, and folded into hierarchical summary trees stored in SQLite. Same chunks land as .md files in an Obsidian-compatible vault.
118+ Integrations with Auto-Fetch
One-click OAuth into Gmail, Notion, GitHub, Slack, Stripe, Calendar, Drive, Linear, Jira and more. Every 20 minutes the core walks each active connection and pulls fresh data into the memory tree.
Desktop Mascot with a Face
A living presence that speaks, reacts to its surroundings, joins your Google Meets as a real participant, remembers you across weeks, and keeps thinking in the background.
TokenJuice Compression
Every tool call, scrape result, email body, and search payload is run through a token compression layer before touching any LLM. Reducing cost & latency by up to 80%.
Smart Model Routing
Each task automatically sent to the right LLM — reasoning, fast, or vision — under one subscription. Optional local AI via Ollama for on-device workloads.
Native Voice + Code Tools
Web search, web-fetch scraper, full coder toolset (filesystem, git, lint, test, grep), and native voice with STT in, ElevenLabs TTS out, mascot lip-sync built in.
Why OpenHuman
OpenHuman vs the rest
| Claude Cowork | OpenClaw | Hermes Agent | OpenHuman | |
|---|---|---|---|---|
| Open-source | Proprietary | MIT | MIT | GNU GPL-3.0 |
| Simple to start | Desktop + CLI | Terminal-first | Terminal-first | Clean UI, minutes |
| Cost | Sub + add-ons | BYO models | BYO models | One sub + TokenJuice |
| Memory | Chat-scoped | Plugin-reliant | Self-learning | Memory Tree + Obsidian vault |
| Integrations | Few connectors | BYO | BYO | 118+ via OAuth |
| Auto-fetch | None | None | None | 20-min sync |
| API sprawl | Extra keys | BYOK | Multi-vendor | One account |
| Model routing | Single model | Manual | Manual | Built-in |
| Native tools | Code-only | Code-only | Code-only | Code + search + voice |
| OpenHuman is built to minimize vendor sprawl, keep workflow knowledge on-device, and give the agent a persistent memory of your data — not only chat. | ||||
Built With
Tech Stack
Join the Movement
Building toward AGI — together
OpenHuman is an open-source project by tinyhumansai, created by @senamakel. Star the repo, join the Discord, and help build the future of personal AI.