agi-memory
Active. Day-1 history import is built in:
agi-memory history-importreads the session transcripts Claude Code, Codex and OpenCode already wrote to disk into L1 observations, so recall works from moment zero instead of an empty vault. Zero dependencies, no LLM — just the history you already have.
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 your session history
New vault, years of sessions already on disk — start full, not empty:
agi-memory history-import --limit 20 # recent sessions -> L1 digests
agi-memory history-import --index # every session -> episodic history
agi-memory history-import --harness codex --dry-run
agi-bootstrap --repo . --with-history # README + git commits + history, one pass
Each session becomes one L1 observation (origin="history-import", title
[claude:1a2b3c4d] ..., project taken from the session's working directory).
Idempotent: re-runs skip sessions already imported. Filter with --project and
--harness (claude, codex, opencode, all).
A digest is the session's own words — goal, the prompts that drove it, files
touched — not a distillation, because nothing here calls an LLM. That is enough
for memory_recall to answer "have we been here before"; memory_timeline and
memory_wip read the same rows.
Other install options, including a one-line script and running from source, are in Installation.
Documentation
| Guide | What's in it |
|---|---|
| Installation | Install options, upgrading, lifecycle hooks |
| CLI Usage | Every agi-memory and agi-integrate command |
| Supported Assistants | Where each assistant's config lives, and the 18 MCP tools |
| How memory is organised | Notes, knowledge graph, session history, code index |
| Architecture | How the pieces fit together |
| Vault & Git Sync | The memory files, syncing between machines, compaction |
| Python API | Using it directly from Python |
| Testing & Evals | How it's tested, and where it falls short |
| Benchmarks | Speed and memory measurements |
| Integrations | Manual setup snippets for each assistant |
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for agi-memory 0.9.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| agi_memory-0.9.2.tar.gz | 178.9 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agi_memory-0.9.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 329.0 kB
Release files / agi_memory-0.9.2.tar.gz
| Download URL | agi_memory-0.9.2.tar.gz |
|---|---|
| Size | 178.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
28e782db189095da79d4017e2250b8c3f70384d69501892248610ed397dd9128
|
|
BLAKE2b-256 checksum How to use checksums |
e94aa4553c5a5e27f9196749393a11a69b763e27bf976de69612cf02ff73bf6c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 27, 2026.
Transparency logRelease files / agi_memory-0.9.2-py3-none-any.whl
| Download URL | agi_memory-0.9.2-py3-none-any.whl |
|---|---|
| Size | 150.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7f531823c4e8569ee6bd30ba1415a1233a3ee3fd4471f6b6ae6be79d019a68ff
|
|
BLAKE2b-256 checksum How to use checksums |
8d447ce375fbc2443069f567aaefa36c396360e046b59ff328800b2817ebb994
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 27, 2026.
Transparency logSecurity for agi-memory 0.9.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for agi_memory-0.9.2.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 27, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
