Soul-driven. Token-efficient. Always on.
Your personal AI agent with 31 built-in tools, skill system, multi-agent orchestration, Spotify integration, GitHub companion, and hardened permissions. Runs 24/7 from your terminal or Telegram.
npm i -g @cosmicstack/mercury-agent && mercuryNot another chatbot. An orchestrator that works for you.
Mercury isn't a blank slate. Its personality is defined by markdown soul files — soul.md, persona.md, taste.md, heartbeat.md — that you control.
Daily token budgets with enforcement. Only soul + persona injected per request (~400 tokens). Progressive skill loading. Auto-concise when budget exceeds 70%.
Background daemon by default. Cron scheduling, delayed tasks, and a heartbeat system. Auto-starts on boot, auto-restarts on crash.
CLI with readline and arrow-key menus. Telegram with typing indicators, HTML formatting, file uploads, and private 1:1 access.
Spawn parallel AI agents for concurrent tasks. Mercury orchestrates — research, code, and review run simultaneously. Non-blocking: keep chatting while agents work.
Native Spotify control through conversation. Play music, manage playlists, DJ on your devices. Search, like, queue — all through natural language.
Install community skills with a single command. Skills auto-load into context, get elevated permissions, and can be scheduled as recurring tasks.
Folder-level read/write scoping. Command blocklist. Pending approval flow. Ask Me or Allow All mode per session.
Most AI agents forget everything when you close the chat. Mercury remembers — automatically, privately, and with surgical precision.
After each conversation, Mercury extracts facts about you — your preferences, goals, projects, habits, relationships, and decisions.
Only memories relevant to the current conversation are injected — up to 5 facts within a 900-character budget.
When Mercury detects a contradiction, the higher-confidence memory wins. No stale data.
Identity, preference, goal, project, habit, decision, constraint, relationship, episode, and reflection — each scored by confidence, importance, and durability.
Every hour Mercury synthesizes a profile summary and generates reflections from patterns it detects.
/memory gives you overview, search, pause, and clear. All data stays on your machine in SQLite — nothing leaves.
npm i -g @cosmicstack/mercury-agentOr use npx @cosmicstack/mercury-agent — no install needed.
mercuryFirst run triggers the onboarding wizard. Choose providers, validate keys, pick your default model, optionally pair Telegram.
mercury startMercury wakes up, loads your soul files, restores scheduled tasks, and runs as a background daemon.
A real Mercury session — tool calls, streaming, files, and scheduling.
Plus extensible skills, scheduling, and memory.
We built Mercury because nothing else did all of this.
| Feature | Mercury | Open Interpreter | Claude Code |
|---|---|---|---|
| Soul / Persona System | 4 markdown files | Custom instructions | CLAUDE.md |
| Token Budget | Daily budget + override | — | — |
| Multi-Channel | CLI + Telegram + more | All | All |
| Sub-Agents | Parallel AI workers, non-blocking | — | — |
| Spotify Integration | Native playback + DJ mode | — | — |
| Skill System | Install, invoke, schedule | — | — |
| Cron + Delayed Scheduling | Persisted, auto-restore | — | — |
| Permission Hardening | Blocklist + scope + approval | Confirmation prompts | Permission prompts |
| GitHub Companion | PRs, issues, co-authored commits | — | — |
| Proactive Notifications | Heartbeat + task alerts | — | — |
| Auto Fact Extraction | With dedup | — | — |
| Provider Fallback | Auto with last-successful | Manual config | Anthropic only |
| File Upload (Telegram) | Auto type detection | — | — |
| Streaming Output | Real-time text stream | Real-time text stream | Real-time text stream |
| Headless / 24-7 | Built-in | — | — |
| Language | TypeScript / Node.js | Python | TypeScript / Node.js |
| Open Source | MIT | LGPL-2.1 | Source-available |
Minimal runtime, maximum capability.
Pick one or stack them all. Mercury falls back automatically.
Default provider. Cost-effective with strong reasoning.
GPT-4o-mini, GPT-4o, o3. Industry standard.
Claude Sonnet, Haiku, Opus. Nuanced reasoning.
xAI's models. OpenAI-compatible endpoint.
Remote Ollama models via API. No local setup.
On your machine. Zero API cost, fully private.
More providers on the way — Google Gemini, Mistral, and others. Mercury's OpenAI-compatible architecture also supports custom endpoints.
npm i -g @cosmicstack/mercury-agent && mercuryThat's it. 60 seconds to your own AI agent with GitHub companion.