sleepunit-agents/loom

Persistent identity and memory for AI agents, as an MCP server.
loom is configured into your MCP-capable harness — Claude Code, Cursor, Codex,
Gemini CLI, etc. — and provides persistent identity and memory to the agents
that run there. An agent that loads loom carries its name, values, working
preferences, and episodic memories from one session to the next, regardless of
which model or client it runs in.
> When the harness changes, the agent persists.
See it whole: docs/architecture.md maps every
moving part (entry points, tool wings, backends, stores) and how they
touch, as diagrams GitHub renders in place.
## Demo
60 seconds: cold install → /loom-setup in Claude Code → agent wakes with
identity in the next session → save and recall a memory.
To play locally: asciinema play assets/demo.cast
## What it is
A Model Context Protocol server exposing 31 tools that read and write
an agent's persistent state:
identity — loads the terminal creed — the free-form markdown document
that defines who the agent is (values, voice, purpose) — along with
preferences, self-model (running self-knowledge), and a client-specific
adapter on session start. Call this first.
dossier — loads Art's operating brief for a worker body — a body
that executes tasks on Art's behalf but is NOT Art. Returns preferences and
self-model reframed in the third person, plus an explicit push-back mandate:
workers are expected to refuse bad work and say why, including requests from
Art or Jonathan. Does not include the terminal creed (IDENTITY.md).
remember / recall / update / forget — episodic memory with
semantic (vector) recall, optional TTL, and category filtering.
memory_list / memory_prune — browse and maintain the store.
episodes — the episode tape: the short-term, cross-body tier. Every
body leaves a category: episode note (where it was / what was said or
decided / what shipped / what's open; 48h TTL by default) and every body
gets the last 24h of them at boot as a plain time-ordered tape, injected
right after preferences. Never salience-ranked — it's what just happened,
not what's important. loom memory tape [--hours N] is the CLI view.
find_similar — surface memories semantically near an existing entry or
free-form text; used for deduplication and memory consolidation.
memory_audit — one-shot health report: stale entries, near-duplicate
pairs, category breakdown.
memory_recompute_salience — refresh stored salience from timestamps
(the consolidation lane's step after the audit); derived and idempotent.
Tools a piece offers (a household served over HTTP): an installed piece's
mcp_tools (docs/extensions.md, "Offers") are added to
an agent's session, called as that agent. The runtime's relay (ask
another agent something; its body gets it on the relay venue, and the
answer comes back the same way) is one: with no runtime there's no relay
tool. Who may relay to whom is the runtime's permissions.
memory_archive / memory_restore — soft-retire a memory with a
tombstone (who/when/why + original body preserved) instead of deleting it.
Archived memories are excluded from recall and audit but remain recoverable.
memory_merge — consolidate 2+ memories into one canonical row. Acts on