Codeatrium — AI skill for Claude Code

English · 日本語

An AI coding agent recalls everything it has done through just two commands: `loci search` and `loci context`. That's the whole interface. The agent reaches for the right call without hesitation, and restores past decisions, conversations, and exact code locations in under 0.2 seconds.

The CLI command `loci` is designed to be **called by the agent itself** — running `loci search "..." --json` from within a prompt. *(The name comes from the [Method of Loci](https://en.wikipedia.org/wiki/Method_of_loci) — the memory-palace technique. Under the hood, conversations are distilled into "palace objects"; see [How It Works](#how-it-works). The architecture extends the conversational memory model from [arXiv:2603.13017](https://arxiv.org/abs/2603.13017) for coding agents.)*

**Harnesses:** Claude Code, Codex CLI, Oh My Pi, OpenCode, and Grok session logs are indexed into the same exchange, code-touch, symbol, search, context, and `show` contracts. Distillation is independent of the harness and can use `claude --print` or a local OpenAI-compatible LLM.

Minimal Interface

The whole recall interface is two commands:

• loci search "query" — semantic searc