Colonies, not committees.
Today's agent "swarms" are a manager with assistants. A bee swarm has no manager.
Open: can agents following only local rules solve what one agent, or the best of many, cannot?
An open-source coding agent from INIT Labs
The harness is everything around the model: its prompts, tools and loop. INIT rewrites its own, tests each change and swaps it in, mid-conversation. A Root it can never touch can undo any change.
An AI agent is a model plus a harness.
INIT may rewrite every layer. Except one.
A new core, through four gates. Same conversation.
If a change does harm, the Root rolls it back. A fixed harness becomes a ceiling. INIT grows.
one cell = one real file · INIT v0.3.3
Diagram. One cell is one real file of INIT v0.3.3: 7 prompt and skill files, 5 tool files and 124 compiled-core files. The kernel is drawn as a texture, not counted. Gate and swap times are measured, and the rollback is a real signed record (2026-10-21, seq 88 to 90). Motion, and all of step 5, are illustrative.
One cell per real file at v0.3.3, the last measured release. Coloured: files INIT changed itself.
The model may rewrite almost all of itself. One thing it can never touch: the Root, which holds the keys, the record and the undo.
sandboxed · no API key · one socket to the Root
separate service · outside the sandbox · holds the signing key
The change scored lower.
The gate refused it.
It was rolled back, and signed.
INIT Labs builds the agent and studies what it does to itself. Every change it makes is signed, tested and undoable: a dataset for the questions below.
From agents that edit their own code to agents that inherit, recombine and evolve, with no human-written score. Open: is there a genome for agents, where mutation makes variation instead of collapse?
Today's agents notice an error after they make it. Minds forecast their own failures, and change course first.
Open: can an agent model itself well enough to foresee its own failures, and act on that in time?
An agent that upgrades itself can be infected by its own upgrades. Nothing guards against that yet.
Open: can it tell self from non-self in its own changes, without attacking the healthy ones?
Every change INIT makes to itself is signed, tested and undoable. Each one is a data point for all four questions.
signed · gated · reversible
Open problems, not results. We will publish what fails, too.
curl -fsSL https://github.com/ nagisanzenin/INIT-Agent/releases/latest/download/get.sh | sh