agent-smriti

smriti

Plain-text memory for AI agents.
Markdown files — no database, no embeddings, no dependencies.

---

from smriti import Memory
mem = Memory("./memory")

mem.write("Use Postgres, not Mongo, for the ledger", type="decision")

mem.context()                  # the index — inject into your prompt every turn
mem.recall("postgres ledger")  # ranked matches, plus what they link to (one hop)
mem.get("use-postgres-for-the-ledger").body
mem.prune()                    # stale / duplicate / broken-link memories

Install  ·  pip install agent-smriti  ·  or copy smriti.py (stdlib, Python 3.10+)

The four rules  ·  write what's durable  ·  compress to a hook + seed  ·  recall by hook  ·  prune the rest

Limits  ·  recall is lexical (the model does the semantics over context())  ·  the filter checks shape, not worth  ·  built for agent scale

---

The format is the whole spec  ·  Benchmarks — local-model A/B: smriti 100% vs no-memory 25% at ~⅓ the context  ·  MIT