Skip to main content
AI Tool Radar
OSI-openAgent frameworks and runtimes

mercury-agent

cosmicstack-labs

Self-hosted personal agent with markdown-defined personality, permission-gated tools and persistent memory, run from CLI/web/Telegram.

2.7k stars(as of 2026-06-26)View on GitHubHomepage

What is mercury-agent?

A self-hosted personal AI agent that runs continuously and is controlled from a CLI, a localhost web dashboard and Telegram, with its personality defined by user-owned markdown files. It ships around 31 permission-gated tools (filesystem, sandboxed shell, git, web fetch, scheduler), a SQLite second-brain memory, Kanban task execution, daily token budgets and a community skills registry, with standalone binaries for macOS, Linux and Windows.

Pros & Cons

Pros

  • A strong permissions-first design (shell blocklist, folder scoping, ask-me/allow-all modes) plus token-budget enforcement
  • Persistent typed memory and multi-channel control (CLI, web, Telegram) out of the box
  • Permissive MIT, standalone binaries that need no Node, and frequent releases

Cons

  • Tool and skill counts differ between the homepage (40+) and the repo (31); the marketing overstates them
  • Self-described as breakable and 'use at your own risk'; a 24/7 shell-capable agent carries real security risk
  • A young project (v1.1.x) with a single-org maintainer and heavy reliance on external LLM providers

License

MIT (OSI-open)

When it is interesting

You want a self-hosted, permission-aware personal agent with persistent memory that you drive from CLI, web and Telegram and shape via your own markdown 'soul'.

When it is too early

If you need a hardened, audited autonomous agent for sensitive systems.

This repo featured in the 2026-07 edition of the Open-Source AI Radar.