Symbiotic AI
A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.
Install: git clone https://github.com/lout33/symbiotic-ai
Works with Claude Code · 737 GitHub stars
Install
git clone https://github.com/lout33/symbiotic-aiInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Symbiotic AI
Your AI's context should belong to you, not a platform. Symbiotic AI keeps it in plain files you own.
Your identity, commitments, and current direction live in a handful of Markdown files you can read, edit, version, and carry to any model. Native platform memory is opaque, automatic, and locked to one vendor. This is the opposite: you own it, and it moves with you.
Symbiotic AI is also a reference implementation of AI for better thinking loops, a category built around the claim that AI can help people think better in ways that survive commitment, action, and review. See proof, methods, and adjacent workflows at Thinking Loops.
Fastest start
Install the symbiotic-onboard skill and run it. A short interview, then you own your files.
gh skill install lout33/symbiotic-ai symbiotic-onboard
Then invoke symbiotic-onboard in your agent and answer the questions. Full walkthrough (plus the manual path): Get your agent to understand you in 10 minutes.
The System
The system is simple on purpose: a small set of files that turns one useful session into ongoing context.
| File | Purpose | Changes |
|---|---|---|
SOUL.md |
Agent personality, identity, values, how it thinks and talks | Monthly |
USER.md |
Your profile: identity, psychology, wiring, mission, energy patterns | Monthly |
AGENTS.md |
How the agent operates: protocols, tools, patterns, interventions | Weekly |
NOW.md |
Current state: tasks, queue, log, active projects, deadlines | Daily |
The agent reads all 4 at session start. Updates NOW.md as you work. The system gets smarter the longer you use it -- not because of AI improvements, but because the files accumulate real context about you.
Want to scale beyond one main agent? See the Multi-Agent Hierarchy Guide for a simple human -> orchestrator -> leads -> specialists pattern.
Guides
- Multi-Agent Hierarchy Guide -- run a human -> orchestrator -> leads -> specialists system without losing clarity
- HEARTBEAT Setup Guide -- add screen-aware accountability through OpenClaw, Telegram, and what-did-i-do
What Makes It Different
It challenges you. From a real conversation:
AI: "You find something valuable -> People want it -> You feel repulsed by the exchange -> You give it away for free -> You have no money -> Repeat. That's not idealism. That's self-punishment."
You own it. Your context lives in plain files you control, not a vendor's black box. Read it, edit it, version it in git, and carry it to any model. Unlike native platform memory, nothing is opaque, automatic, or locked to one tool.
It acts. Writes code, researches, creates files. Not just advice.
It evolves. After 100+ sessions, your files contain hard-won insights about what works for you specifically. No generic advice. Your patterns, your bugs, your wins.
Symbiotic AI vs native memory
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…