RCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).
Latest release rcll-v0.1.0 — RCLL 0.1.0 · 28 Aug 2026
3 files for Claude Code, Codex and OpenCode: code-review, fleet-memory AGENTS.md, fleet-memory CLAUDE.md — 3,016 tokens loaded in every session.
AGENTS.md A 25 tok CLAUDE.md A 2,991 tok .claude/skills/code-review/SKILL.md A 35 tok These files are Holetron-lab/fleet-memory's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.