nanobot vs openhuman
Two of the top projects in Assistants, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
nanobot
Self-hosted Python personal agent with WebUI, TUI and chat-app channels
openhuman
Rust agent harness with desktop app, built-in memory and embeddable library
Verdict
nanobot ranks higher, 82 to 81. Of the 5 score parts we measure for both, nanobot leads on 2, openhuman on 2 and 1 is even.
- Adoptionnanobot leads by 9 points, 72 to 63.
- FreshnessEven at 100.
- Maintenanceopenhuman leads by 3 points, 94 to 91: close to even.
- Easy to runnanobot leads by 16 points, 83 to 67: a wide gap.
- Agent-readyopenhuman leads by 70 points, 100 to 30: a wide gap.
Pick nanobot if you are
Self-hosters wanting a personal agent in browser, terminal and chat apps
- Many channels: Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, Teams, Feishu
- Built-in long-term memory, cron automations and /goal long-running tasks
Pick openhuman if you are
Users wanting a self-run agent app, and Rust developers embedding agents
- 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
| What we compare | nanobot | openhuman |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 72, popular | 63, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 91, healthy | 94, healthy |
| Easy to run | 83, very easy | 67, easy |
| Agent-ready | 30, minimal | 100, ready |
| Facts from GitHub and the README | ||
| Stars | 49k | 42k |
| License | MIT (permissive) | GPL-3.0 (copyleft) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Oct 2026 |
| Language | Python | Rust |
| Docker | Yes | Yes |
| GPU | Not needed | Optional |
| arm64 or Apple Silicon | Mentioned | Mentioned |
nanobot
nanobot is a Python agent framework you run yourself and use from a browser WebUI, a terminal TUI, or chat apps such as Telegram, Discord, Slack and Email. It keeps session history and long-term memory (Dream), runs shell, web, MCP and cron tools, and supports long-running goals. It also exposes a Python SDK and an OpenAI-compatible API, and needs an external model provider or local server.
Who it is for: Self-hosters wanting a personal agent in browser, terminal and chat apps
Strengths
- Many channels: Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, Teams, Feishu
- Built-in long-term memory, cron automations and /goal long-running tasks
- Works with OpenAI-compatible APIs, Ollama and vLLM, with fallback models
- Installs via script, uv or pip; Python SDK and OpenAI-compatible API included
Weaknesses
- Supplies no model; needs a provider account or local model server
- Background gateway does not restart after reboot or crash without an OS service
- Interrupted subagent tasks and missed scheduled runs are not replayed after restart
- Source install needs Git and Bun; native TUI wheels cover limited platforms
- no GPU
- Docker + Compose
- Needs Python 3.11+, model provider or local model server
- Models: OpenAI-compatible APIs, Ollama, vLLM
- port 8765
openhuman
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
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
- 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
More in Assistants
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.