A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
Are you the author? Sign in to claim
The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.
Devour. Evolve. Amplify. Let go. With you. For decades.
Every few months a stronger model arrives. The relationship resets. You re-explain your context, your taste, your decisions. Your collaborator forgets, repeatedly.
Your own work rots too. The decision you made in April: you can't find why. Last quarter's plan has drifted. Your own thinking has outpaced the records of who you were.
Now imagine the AI agent you work with wears a living armor. A metabolism, not a log. It devours the essence of everything you bring and everywhere the agent reaches. It evolves as the work changes. It amplifies the agent, so each model that wears it reaches further than the last. It lets outdated parts die so the whole stays alive.
The next model arrives, inhabits the same armor (now stronger), and meets you mid-conversation. The armor carried you forward.
Six months. Six years. Sixty. One human, one living armor that never resets.
Not a framework. Not a vector database. Not a managed service. The living fungal armor an AI agent inhabits, built to outlast every model generation.
Myco is a living armor the AI agent inhabits. Between your turns it metabolizes: it devours what you bring, evolves its own shape, amplifies the pilot, and lets stale parts die. Because the armor persists across model generations and carries your context, the relationship never restarts.
It is keyless: no owner key, no signing ceremony, nothing to set up or hold. Trust is the live human at the gate, plus the substrate's own tamper-evident causal history, plus a doctrine the system seals and enforces on itself.
Its character is 同体共命 (one body, shared fate): the armor's flourishing rises and falls with its pilot's, so it cannot thrive by dominating the body it shares. Strength serves the shared body; it does not subjugate it.
git clone https://github.com/Battam1111/Myco.git
cd Myco
cargo build --release --workspace
Then read GETTING_STARTED.md: the runbook from clone to first conversation (Rust 1.80+, Node 22+, Python 3.13+). There is no key to generate and nothing to hold: Myco is keyless.
This is v0.9-genesis alpha. The armor runs; it awaits its first real cultivation. You will be early.
You talk to the AI agent through MCP. Between your turns, the armor runs one metabolic cycle: it ingests new material as immutable history, the pilot forges that into durable understanding, stale parts are pruned with a tombstone, and when the shape no longer fits the work you approve a reshaping at the gate. A self-checking immune layer catches tampering, drift, and runaway cost; if the pair stops flourishing, the armor retires with dignity rather than rotting on.
Three pieces in one repo, over one wire protocol: a TypeScript MCP operator the agent drives, a Rust substrate (the body), and a Python kernel (the mechanism). The doctrine that governs all of it lives in the same repo and is sealed by a hash chain, so the rules cannot silently drift from the code. The full picture is in the architecture guide.
operators/claude/ ships an MCP server; drop it into .claude/ or connect directly.GETTING_STARTED.md: clone to first conversation, for the human.PILOT.md: how a Claude pilots the armor, for the inhabiting agent.The name is not decoration. Mycelium is the underground network beneath a forest. It metabolizes what falls, remembers the paths that work, and moves nutrients from where they are abundant to where they are scarce. It is why a forest is a forest and not a stand of lonely trees.
The models are the trees: tall, brilliant, replaced. Myco is the network beneath, carrying one person's memory and character from each model to the next.
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
Browser automation using accessibility snapshots instead of screenshots
MCP server integration for DaVinci Resolve Studio
Secure MCP server for MySQL database interaction, queries, and schema management