# tigerless-labs/agent-memory

> Local long-term memory runtime for AI agents: Markdown files as the source of truth, ranked retrieval over a SQLite index, and sleep-time consolidation. One shared store for Claude Code and Codex, no API keys.

- Magnitude: 1.2 out of 10 — Cooling
- Stars: 4,372 total · +1 star measured 2026-10-29, 00:11–03:01 UTC, ≈ 6 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-09-01 · Last push: 2026-10-27
- GitHub: https://github.com/tigerless-labs/agent-memory · Page: https://gitnova.dev/en/r/tigerless-labs/agent-memory

## Useful for

- Attach a shared memory store to Claude Code and Codex CLI
- Find past decisions via mem recall and open the right file at the needed depth
- Run sleep-time memory consolidation with deletion proposals to confirm

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:11–03:01: 4371 → 4372 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +6 stars, using observed gains and the previous day.
- The repository is 58 days old and already has 4,372 stars.
- Recent forks include notable developers: @strategist922 (911 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 199
- Issues and pull requests: 117
- Watchers: 96
- Average over the last week: 27 per day
- Usual pace: 110 per day
- Stars in the last hour (measured): 0

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 177, 229, 75, 35, 32, 6, 6, 5, 385, 280, 6, 4, 3, 53, 164, 107, 148, 123, 97, 123, 119, 155, 143, 153, 8, 10, 3, 7, 5, 1

## Magnitude by day, last 14 days

10-01 4.0, 10-02 3.8, 10-03 2.5, 10-04 2.0, 10-05 1.9, 10-06 1.3, 10-07 1.2, 10-08 3.2, 10-09 5.3, 10-10 4.1, 10-11 1.1, 10-27 1.0, 10-28 1.4, 10-29 1.3

## Similar by description

1. **TED-H-com/mcp-memory-server** — 0.0 · Quiet · AI agents · HTML · Not enough measurements today
   MCP server that gives AI agents typed long-term memory (decisions, resolved issues, open questions, knowledge) in one SQLite file per workspace, with salience ranking and optional Oracle-backed vector search.
   Full card: https://gitnova.dev/en/r/TED-H-com/mcp-memory-server.md
2. **gonzaroman/IHMT-MEMORY** — 0.0 · Quiet · AI agents · Python · +0 stars measured 2026-10-29, 00:12–03:03 UTC, ≈ 0 by evening
   IHMT is a local MCP server that gives AI coding agents long-term memory stored as a tree of plain text files, so decisions, preferences and corrections persist across sessions and across agents.
   Full card: https://gitnova.dev/en/r/gonzaroman/IHMT-MEMORY.md
3. **AlexGHerrera/agent-memory** — 0.0 · Quiet · Python · Not enough measurements today
   Long-term memory for AI agents: SQLite + FTS5 + vector search, MCP server, Claude Code hooks, nightly consolidation
   Full card: https://gitnova.dev/en/r/AlexGHerrera/agent-memory.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 03:04 UTC, updated every 30 minutes.