🧠agentmemory
rohitg00/agentmemory · homepage ↗
#1 Persistent memory for AI coding agents based on real-world benchmarks
⭐ Very popular: 27k stars, gaining about 351 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Gives AI coding agents persistent memory across sessions, so developers stop re-explaining project architecture and preferences on every new conversation.
- One memory server is shared across agents including Claude Code, Cursor, Cline, Copilot CLI, and Aider, so context follows the developer rather than being locked to a single tool.
- Runs locally with SQLite and an in-memory vector index by default, so there is no external database to provision and secrets are stripped before storage.
under the hood
- Written in TypeScript on the iii-engine worker, function, and trigger primitives, replacing a stack that would otherwise use Express, PostgreSQL, Redis, pm2, and Prometheus.
- Retrieval fuses BM25 keyword matching, vector similarity, and knowledge graph traversal via Reciprocal Rank Fusion, with embeddings from a local all-MiniLM-L6-v2 model or hosted providers.
- Lifecycle hooks auto-capture tool use with SHA-256 deduplication, then consolidate memories across four tiers of working, episodic, semantic, and procedural, exposed through 53 MCP tools and a REST API.
Radar summary, generated from the project's public sources
star history
- PR#34 9k 2026-05-20
- now 27k + 18k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Output and attention are roughly in balance.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Local-first persistent memory for coding agents
similar projects
compare these →- 🧠 oh-my-opencode
2.5× the stars
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
68k ACTIVE - 🧠 Context Mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
20k ACTIVE - ☤ hermes-agent
Python · 8.5× the stars
The agent that grows with you
231k ACTIVE
comments
Sign in with GitHub to add your blip on agentmemory.