# VictorTaelin/OptMem

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Repository: https://github.com/VictorTaelin/OptMem
Canonical: https://ross.abutalabs.com/products/optmem
Language: Python
License Family: other
Last push: 2026-07-31T02:19:57+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 2
- inputs: {"age_days": 39, "days_push": 34, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1471, forks 96 (observed 2026-08-28T04:04:49.234464+00:00)

## What it is
OptMem is a dependency-free Python CLI that gives AI coding agents permanent, file-based memory via a small prompt block pasted into AGENTS.md/CLAUDE.md. It stores one-line memories in an append-only log with a rebuildable summary tree, exposed through commands like wake, note, recall, and nap.

## Use cases
- give my AI agent persistent memory across sessions
- remember decisions and facts between Claude Code sessions
- store what my coding agent learns so it survives compaction
- search all past agent memories with regex
- keep agent memory in a git-synced folder
- let an agent recall user preferences and past tasks

## When to choose
- you use an agent that reads AGENTS.md or CLAUDE.md and want zero-dependency persistent memory
- you want memory that survives model, vendor, or session changes
- you prefer simple file-based storage over a vector database
- you want full control and portability of the memory files

## When to avoid
- you need semantic similarity search rather than exact regex recall
- you need multi-user or server-side shared memory
- you want automatic background memory consolidation
- you require a maintained, licensed dependency for production use

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, cli, developer-tools, prompt-engineering
- domain: developer-tools
- platform: cli, python, cross-platform
- tags: ai-agent-memory, persistent-memory, llm-agents, memory-management, plug-and-play, no-dependencies, ai-agents, command-line, linux, macos

## Member repositories
- VictorTaelin/OptMem (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:49.234464+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:45.166787+00:00, confidence not recorded.
  - readme: https://github.com/VictorTaelin/OptMem (fetched 2026-08-28T04:04:49.234464+00:00, sha 79c455dc697e)
- Data as of 2026-08-30T08:39:29.467469+00:00.