TrustClaw is a self-hostable personal AI agent that connects conversational access, persistent memory, and external tool use into one assistant workflow. It is built for users who want their own AI agent rather than a fully hosted platform, making it easier to run, inspect, and adapt the system for personal or technical needs. The project uses vector memory so the assistant can retain and retrieve useful context across interactions. It also integrates Composio tools, giving the agent access to third-party actions and services through a broader tool ecosystem. Telegram support makes the assistant reachable from a familiar messaging interface instead of only through a terminal or web app. Overall, it is aimed at developers and power users who want a customizable, always-available personal assistant with memory, tools, and self-hosted control.

Features

  • Self-hostable personal AI agent
  • Vector-based persistent memory
  • Composio tool integration
  • Telegram messaging interface
  • TypeScript-based implementation
  • MIT licensed open-source project

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow TrustClaw

TrustClaw Web Site

Other Useful Business Software
Gemini 3 and 200+ AI Models on One Platform Icon
Gemini 3 and 200+ AI Models on One Platform

Access Google's best plus Claude, Llama, and Gemma. Fine-tune and deploy from one console.

Build, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of TrustClaw!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

TypeScript

Related Categories

TypeScript AI Assistants, TypeScript AI Agents

Registered

3 days ago