pocketpaw and pocket-agent
These are direct competitors: both are self-hosted personal AI desktop assistants using similar LLM backends (Anthropic/OpenAI/local models), with PocketPaw being the more mature and actively maintained option.
About pocketpaw
pocketpaw/pocketpaw
Your AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer, multi-agent Command Center(Deep Work), and 7-layer security. Anthropic, OpenAI, or Ollama.
Based on the README, here's a technical summary: Integrates natively with Discord, Slack, WhatsApp, and Telegram via the web dashboard, with a cross-platform desktop app (Electron-based) bundling the Python backend and providing system tray access, global shortcuts, and side panel UI. Built on Python 3.11+ with pip distribution and Docker Compose support, featuring configurable LLM providers (Anthropic, OpenAI, Ollama) and optional vector memory persistence via Qdrant. The architecture separates a native client frontend from a self-contained backend service running on localhost:8888, enabling multi-window browsing, browser automation, and shell execution while maintaining data isolation on the user's machine.
About pocket-agent
KenKaiii/pocket-agent
An AI personal assistant done the right way.
Builds persistent memory through semantic fact extraction and a "soul" system that learns your communication style, paired with browser automation (both hidden mode and authenticated Chrome sessions), scheduled agent routines, and multi-session isolation. Integrates with 40+ services including Notion, GitHub, Slack, and supports MCP servers, plus Telegram for mobile access with separate conversation threads per group.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work