agi-memory

Active. Day-1 history import from deja-vu is built in: agi-memory deja-import distills your existing session transcripts into curated L1 observations, so recall works from moment zero instead of an empty vault. Record-forward curation (rationale, supersession, pins) stays here; raw transcript search stays in deja.

Coding assistants forget everything when a session ends. agi-memory is a small local memory they can all read and write, so you don't have to re-explain your project every time you open a new session or switch tools.

A basic example

On Monday you tell Claude Code why webhook retries are capped, and it saves that:

memory_record(
  title="Webhook retry limit",
  text="Payment webhooks retry at most 5 times with exponential backoff. "
       "Do not raise the limit: the provider bans endpoints that retry more.",
  rationale="Stripe disables endpoints after repeated failed retries",
)

On Thursday you're in Cursor, in a fresh session, and ask it to make webhooks more reliable. Before touching the code it checks memory:

$ agi-memory recall "webhook retries" --project shop
#1 [shop] Webhook retry limit: Payment webhooks retry at most 5 times with
exponential backoff. Do not raise the limit: the provider bans endpoints that
retry more. | Why: Stripe disables endpoints after repeated failed retries

So it doesn't "fix" reliability by raising the retry count. That's the whole idea: decisions, bugs you already fixed, and what you tried last time stay available across sessions and across tools.

How it works

• Memories are stored in SQLite on your machine, and also written to plain append-only text files you can read, diff, and keep in git.
• Each assistant talks to it through a local MCP server. It works in Claude Code, Cursor, Windsurf, Codex, OpenCode, Antigravity, Aider, Goose, Cline, Roo Code, Crush, Pi, and Hermes Agent.
• Nothing leaves your machine unless you point the memory files at a git remote to sync them between computers.
• It's pure Python with no dependencies: no vector database, no model download, no background service.

Besides notes and decisions, it also keeps a short history of past sessions and an index of your code (functions and who calls them), so an assistant can ask "what calls this?" before changing it.

What it won't do

Search is by keyword, not meaning. If you saved "authentication" and later ask about "login", it can miss. It helps to use the words you'd search for when saving something. The measured hit rates, including the misses, are in Testing & Evals.

Install

pipx install agi-memory            # or: brew tap kdbhalala/agi-memory https://github.com/kdbhalala/agi-memory && brew install agi-memory
agi-integrate install all          # connect every assistant it finds on your machine
agi-integrate status               # see what got connected

Day-1: import deja history

New vault, years of sessions already on disk — start full, not empty:

agi-memory deja-import --limit 50 --dry-run   # preview what would import
agi-memory deja-import --limit 200 --since 90d
agi-bootstrap --repo . --with-deja             # README + git commits + deja in one pass

Each deja session becomes one L1 observation (origin="deja-import", title [deja:<short-id>] ..., project mapped from deja). Idempotent: re-runs skip imported sessions and tiny transcripts (--min-words 800). Filter with --project, --harness, --since.

Other install options, including a one-line script and running from source, are in Installation.

Documentation

License

MIT