Personal and general-purpose AI agents, ranked
OpenClaw-style personal agents: they run on your own machine or server, connect to chat channels like Telegram, WhatsApp or Slack, and carry out everyday tasks for you. They usually hold your accounts and files, so read the trust column closely.
| # | Agent | FARS | Trust | Stars | License | Language | Last commit |
|---|---|---|---|---|---|---|---|
| 1 | Hermes Agent | 67 | 19/29 | 255.2k | MIT | Python | 2026-10-19 |
| 2 | QwenPaw Personal Assistant | 64 | 17/29 | 35.9k | Apache-2.0 | TypeScript | 2026-10-19 |
| 3 | nanobot | 62 | 16/29 | 49.2k | MIT | Python | 2026-10-19 |
| 4 | ZeroClaw — Personal AI assistant runtime | 60 | 16/29 | 33.0k | Apache-2.0 | Rust | 2026-10-19 |
| 5 | NanoClaw | 58 | 16/29 | 31.0k | MIT | TypeScript | 2026-10-19 |
| 6 | Tiny Claw (Mandibles) | 58 | 13/29 | 297 | GPL-3.0 | TypeScript | 2026-02-25 |
| 7 | Moltis Personal Agent Server | 53 | 14/29 | 2.9k | MIT | Rust | 2026-10-19 |
| 8 | CowAgent | 52 | 10/29 | 47.5k | MIT | Python | 2026-10-19 |
| 9 | OpenHuman | 51 | 13/29 | 42.2k | GPL-3.0 | Rust | 2026-10-19 |
| 10 | OpenClaw Personal Assistant | 47 | 10/29 | 392.5k | MIT | TypeScript | 2026-10-19 |
| 11 | AgenticSeek | 40 | 7/29 | 27.5k | GPL-3.0 | Python | 2026-10-15 |
What qualifies: standalone, maintained tools of this kind that people search for by name. Plugins, skill packs and config layers built on top of them are left out and listed on the host tool's profile. The membership list is kept in our public repository, so every change is on record.
The order is the FARS total; stars only break ties, because popularity measures attention rather than whether something holds up. Two limits are worth knowing before you read the order. These are static reviews — source, documentation and repository metadata, with no runtime reproduction — which caps reliability, effectiveness and verifiability and puts the achievable maximum at 77 rather than 100. And a gap of a few points sits inside the noise of that method. Read the table as a shortlist worth investigating, not as a verdict; every score links to its full dimension breakdown and the evidence behind it. Review method →
1. Hermes Agent
A self-hosted, multi-channel agent that builds skills and retains context across sessions.
Where it differs
The repository names OpenClaw as a migration source. hermes claw migrate can import SOUL.md, memories, skills, command approval patterns, messaging settings, selected API keys, TTS assets, and workspace instructions; --dry-run previews the migration first.
2. QwenPaw Personal Assistant
A self-hosted personal assistant that combines chat, memory, automation, tools, and multi-channel access.
Where it differs
QwenPaw can use Ollama or LM Studio as local model backends. Compared with those model-serving backends, QwenPaw also documents a Console, TUI, channel connections, memory, scheduled tasks, Skills, plugins, and MCP management.
3. nanobot
A self-hosted Python runtime that brings personal AI assistants, tools, chat channels, and automation into one lightweight gateway.
Where it differs
The README presents nanobot gateway as a gateway-first entry point familiar to people coming from OpenClaw or already operating agents as long-lived services; it does not provide a feature-by-feature comparison.
4. ZeroClaw — Personal AI assistant runtime
A single Rust binary that runs your own AI assistant across 30+ channels, ~20 model providers, and every major OS, with your data, keys, and machine.
5. NanoClaw
A container-isolated, customizable assistant for your messaging channels.
Where it differs
NanoClaw presents itself as a lightweight alternative to OpenClaw. Its README contrasts OpenClaw's larger code and dependency footprint and shared-memory single-Node-process design with NanoClaw's smaller codebase and per-agent Linux-container filesystem isolation.
6. Tiny Claw (Mandibles)
A lightweight autonomous personal AI companion: tiny plugin-based core, self-improving memory, and smart cost-tiering routing that make AI simple, affordable, and truly personal.
Where it differs
The README contrasts Tiny Claw with other AI agent frameworks (frameworks built on Pi, Claude Code, or Codex, and OpenClaw): Tiny Claw is a native framework built from scratch with a tiny plugin-based core, self-improving memory, tiered routing, a bundled web UI, and SHIELD.md security, whereas OpenClaw is its inspiration (lobster vs ant) and competing frameworks typically wrap existing frameworks, grow into large monoliths, hit the most expensive model on every query, and require Claude Pro/Max subscriptions or multiple API keys.
7. Moltis Personal Agent Server
A self-hosted Rust server for persistent, multi-channel assistance with sandboxed tool execution on hardware you control.
Where it differs
The repository compares Moltis with OpenClaw and Hermes Agent. Moltis is positioned as a persistent personal-agent server with modular Rust crates and a single Rust-binary runtime, while OpenClaw is described as TypeScript with companion apps and Hermes Agent as Python with TypeScript TUI/web surfaces. The comparison also lists Moltis sandbox paths for Docker/Podman, Apple Container, and WASM, plus SQLite, FTS, and vector memory.
8. CowAgent
A self-hosted, multi-channel assistant that plans tasks and uses tools, skills, memory, and knowledge to carry them out.
9. OpenHuman
An open source, local-first personal AI for Mac, Windows and Linux — persistent memory, agent orchestration, and deep research in one desktop app.
10. OpenClaw Personal Assistant
A personal AI assistant that runs on your devices and meets you in the messaging channels you already use.
11. AgenticSeek
A local task assistant for web research, file work, and code execution.
Where it differs
The project positions itself as a local alternative to Manus AI, emphasizing local or self-hosted models, local workspace handling, and independence from cloud services. The repository does not provide evidence of feature parity or benchmark comparisons with Manus.