rohitg00/agentmemory

▲ 49 stars today★ 29,387⑂ 2,588

#1 Persistent memory for AI coding agents based on real-world benchmarks

Open on GitHub ↗

About rohitg00/agentmemory

rohitg00/agentmemory is an open-source project on GitHub, mainly written in TypeScript. #1 Persistent memory for AI coding agents based on real-world benchmarks It currently holds 29,387 stars and 2,588 forks with 0 open issues, and was last pushed on an unknown date (repository created unknown).

Project Overview

AI Homed tracks it on the Today's Trending board, currently at rank #42 with 49 new stars today.

GitHub Repository Details

Repository rohitg00/agentmemory · default branch - · size 0 KB · watchers 0 · source: GitHub REST API and repository README

README

https://github.com/rohitg00/agentmemory/blob/HEAD/agentmemory: persistent memory for AI coding agents

Your coding agent remembers everything. No more re-explaining. Built on iii engine
Persistent memory for Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, Hermes, OpenClaw, pi, OpenCode, and any MCP client.

🇬🇧 English • 🇨🇳 简体中文 • 🇹🇼 繁體中文 • 🇯🇵 日本語 • 🇰🇷 한국어 • 🇵🇹 Português • 🇧🇷 Português (Brasil) • 🇪🇸 Español • 🇩🇪 Deutsch • 🇫🇷 Français • 🇮🇹 Italiano • 🇳🇱 Nederlands • 🇵🇱 Polski • 🇨🇿 Čeština • 🇷🇴 Română • 🇭🇺 Magyar • 🇬🇷 Ελληνικά • 🇸🇪 Svenska • 🇩🇰 Dansk • 🇳🇴 Norsk • 🇫🇮 Suomi • 🇷🇺 Русский • 🇺🇦 Українська • 🇹🇷 Türkçe • 🇮🇱 עברית • 🇸🇦 العربية • 🇮🇳 हिन्दी • 🇧🇩 বাংলা • 🇵🇰 اردو • 🇹🇭 ไทย • 🇻🇳 Tiếng Việt • 🇮🇩 Bahasa Indonesia • 🇵🇭 Tagalog

https://github.com/rohitg00/agentmemory/blob/HEAD/rohitg00/agentmemory | Trendshift

https://github.com/rohitg00/agentmemory/blob/HEAD/Design doc: 1.6k stars / 230 forks on the gist

The gist extends Karpathy's LLM Wiki pattern with confidence scoring, lifecycle, knowledge graphs, and hybrid search: agentmemory is the implementation.

https://github.com/rohitg00/agentmemory/blob/HEAD/skills.sh https://github.com/rohitg00/agentmemory/blob/HEAD/npm version https://github.com/rohitg00/agentmemory/blob/HEAD/CI https://github.com/rohitg00/agentmemory/blob/HEAD/License https://github.com/rohitg00/agentmemory/blob/HEAD/Stars

https://github.com/rohitg00/agentmemory/blob/HEAD/95.2% retrieval R@5 https://github.com/rohitg00/agentmemory/blob/HEAD/92% fewer tokens https://github.com/rohitg00/agentmemory/blob/HEAD/54 MCP tools https://github.com/rohitg00/agentmemory/blob/HEAD/12 auto hooks https://github.com/rohitg00/agentmemory/blob/HEAD/0 external DBs https://github.com/rohitg00/agentmemory/blob/HEAD/3,300+ tests passing

https://github.com/rohitg00/agentmemory/blob/HEAD/agentmemory demo

Install • Quick Start • Benchmarks • vs Competitors • Agents • How It Works • MCP • Viewer • Powered by iii • Config • API

---

Install

Requirements:

Canonical fresh-install command:

npx -y @agentmemory/agentmemory@latest

The first run is an interactive setup: pick the agents to wire (Claude Code, Cursor, Codex, Gemini CLI, OpenCode, ...), pick an LLM provider or stay keyless, and it seeds the config, starts the memory server and its pinned iii engine, and offers to install globally so the bare agentmemory command works everywhere afterward. -y accepts npx's package prompt and @latest avoids a stale cached release. A provider makes LLM features available, but LLM-written observation compression starts only when AGENTMEMORY_AUTO_COMPRESS=true is also set.

Keyless mode disables vector embeddings. memory_recall (the mem::search path) uses BM25, while memory_smart_search can also fuse structural graph matches when graph data already exists. For free on-device semantic recall, set EMBEDDING_PROVIDER=local in ~/.agentmemory/.env and restart. The first embedding request downloads Xenova/all-MiniLM-L6-v2; inference runs locally after that initial model download.

The local runtime uses four ports: 3111 for REST/MCP HTTP, 3112 for iii streams, 3113 for the viewer, and 49134 for the iii worker WebSocket. Persistent iii state lives in ~/Library/Application Support/agentmemory on macOS, $XDG_DATA_HOME/agentmemory or ~/.local/share/agentmemory on Linux, and %APPDATA%\agentmemory on Windows. Use --data-dir or AGENTMEMORY_DATA_DIR to override it, and reuse the same value on every restart. For backward compatibility, an existing ./data/state_store.db or ./data/iii-config.yaml takes precedence over the platform default for instance 0; an explicit flag or environment override still wins.

Then prove recall works and give your agent its skills:

npx -y @agentmemory/agentmemory@latest demo  # seed sample sessions + exercise recall
npx skills add rohitg00/agentmemory -y   # 17 native skills so your agent knows when to reach for memory

The keyword searches should hit in default keyless mode through BM25. The demo's database performance optimization query is intentionally semantic and can return zero until an embedding provider is configured.

Prefer to let a coding agent do the whole thing? Hand it one instruction:

Retrieve and follow the instructions at: https://raw.githubusercontent.com/rohitg00/agentmemory/main/INSTALL_FOR_AGENTS.md

Wire more agents any time with agentmemory connect — 20 adapters listed at Works with every agent. Full command reference at Quick Start.

Windows

The fast path is WSL2. Native Windows engine setup requires the pinned v0.22.1 ZIP to be downloaded and iii.exe extracted manually; the CLI does not auto-extract it. Docker Desktop is also supported. See the Windows notes for the step-by-step.

Global install / EACCES 
npm install -g @agentmemory/agentmemory@latest

The npx command above remains the canonical fresh-install path and avoids global-prefix permission issues.

npx serves an old version

npx caches per version. Force the latest with npx -y @agentmemory/agentmemory@latest, or clear the cache once with rm -rf ~/.npm/_npx (macOS/Linux; on Windows delete %LOCALAPPDATA%\npm-cache\_npx).

Already running your own iii engine

agentmemory pins iii-engine v0.22.1 and won't attach to a different version (the worker can't speak another engine's protocol). Stop the other engine, then run npx -y @agentmemory/agentmemory@latest. It installs and runs the pinned v0.22.1 in ~/.agentmemory/bin, leaving your own iii untouched.

---

https://github.com/rohitg00/agentmemory/blob/HEAD/Works with every agent

agentmemory works with any agent that supports hooks, MCP, or REST API. All agents share the same memory server.

https://github.com/rohitg00/agentmemory/blob/HEAD/Claude Code
Claude Code
native plugin + 12 hooks + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/Codex CLI
Codex CLI
native plugin + 6 hooks + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/GitHub Copilot CLI
GitHub Copilot CLI
MCP + plugin hooks/skills 		https://github.com/rohitg00/agentmemory/blob/HEAD/Cursor
Cursor
native plugin + 7 hooks + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/OpenCode
OpenCode
capture plugin + MCP
https://github.com/rohitg00/agentmemory/blob/HEAD/Devin
Devin
6 hooks + skills + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/OpenClaw
OpenClaw
native plugin + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/Hermes
Hermes
native plugin + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/pi
pi
native plugin + MCP 		https://github.com/rohitg00/agentmemory/blob/HEAD/OpenHuman
OpenHuman
native Memory trait backend
https://github.com/rohitg00/agentmemory/blob/HEAD/Gemini CLI
Gemini CLI
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Antigravity
Antigravity
MCP + hooks 		https://github.com/rohitg00/agentmemory/blob/HEAD/Claude Desktop
Claude Desktop
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Warp
Warp
connect + MCP + skills 		https://github.com/rohitg00/agentmemory/blob/HEAD/Zed
Zed
MCP server
https://github.com/rohitg00/agentmemory/blob/HEAD/Cline
Cline
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Continue
Continue
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Droid
Droid
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Kiro
Kiro
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Qwen Code
Qwen Code
MCP server
https://github.com/rohitg00/agentmemory/blob/HEAD/DeepSeek Harness
DeepSeek Harness
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Roo Code
Roo Code
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Kilo Code
Kilo Code
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Goose
Goose
MCP server 		https://github.com/rohitg00/agentmemory/blob/HEAD/Aider
Aider
REST API

Works with any agent that speaks MCP or HTTP. One server, memories shared across all of them.

---

You explain the same architecture every session. You re-discover the same bugs. You re-teach the same preferences. Built-in memory (CLAUDE.md, .cursorrules) caps out at 200 lines and goes stale. agentmemory fixes this. It silently captures what your agent does, compresses it into searchable memory, and injects the right context when the next session starts. One command. Works across agents.

What changes: Session 1 you set up JWT auth. Session 2 you ask for rate limiting. The agent already knows your auth uses jose middleware in src/middleware/auth.ts, your tests cover token validation, and you chose jose over jsonwebtoken for Edge compatibility, with no re-explaining and no copy-pasting.

npx -y @agentmemory/agentmemory@latest

By default, agentmemory stores iii-engine state outside the repository you start it from: ~/Library/Application Support/agentmemory on macOS, $XDG_DATA_HOME/agentmemory or ~/.local/share/agentmemory on Linux, and %APPDATA%\agentmemory on Windows. An existing legacy ./data/state_store.db or ./data/iii-config.yaml is reused for instance 0 before that platform default. To choose a location explicitly, pass --data-dir or set AGENTMEMORY_DATA_DIR; either explicit setting takes precedence over legacy discovery:

npx -y @agentmemory/agentmemory@latest --data-dir ~/.agentmemory-projects/main
AGENTMEMORY_DATA_DIR=~/.agentmemory-projects/main npx -y @agentmemory/agentmemory@latest

Native and Docker launches use this same resolved host directory; Docker bind-mounts it at /data. --instance 1 appends instance-1 to the resolved directory and selects the separate default port quartet 3211/3212/3213/49234.

Latest release notes: CHANGELOG.md.

---

https://github.com/rohitg00/agentmemory/blob/HEAD/Benchmarks

Retrieval Accuracy

coding-agent-life-v1 (in-house corpus, sandbox-reproducible)

| Adapter | P@5 | R@5 | Top-5 hit rate | p50 latency | |---|---|---|---|---| | agentmemory hybrid | 0.240 | 1.000 | 15 / 15 | 14 ms | | grep baseline | 0.227 | 0.967 | 15 / 15 | 0 ms |

100% top-5 hit rate at the P@5 math ceiling for this corpus (0.240, see scorecard). Hybrid retrieves every gold session; grep misses 1 of 2 gold on the multi-session temporal query. Lift is recall + temporal, not aggregate precision. This benchmark is small and gold-sparse; the larger LongMemEval-S below differentiates better. Full per-type breakdown + correction note: docs/benchmarks/2026-05-20-coding-agent-life-v1.md.

LongMemEval-S (ICLR 2025, 500 questions)

| System | R@5 | R@10 | MRR | |---|---|---|---| | agentmemory | 95.2% | 98.6% | 88.2% | | BM25-only fallback | 86.2% | 94.6% | 71.5% |

Token Savings

| Approach | Tokens/yr | Cost/yr | |---|---|---| | Paste full context | 19.5M+ | Impossible (exceeds window) | | LLM-summarized | ~650K | ~$500 | | agentmemory | ~170K | ~$10 | | agentmemory + local embeddings | ~170K | $0 |

Embedding model: all-MiniLM-L6-v2 (local, free, no API key). Full reports: benchmark/LONGMEMEVAL.md, benchmark/QUALITY.md, benchmark/SCALE.md. Competitor comparison: benchmark/COMPARISON.md covering agentmemory vs mem0, Letta, Khoj, supermemory, TencentDB Agent Memory, MemPalace, Zep/Graphiti, Cognee, Hippo.

Reproduce locally: eval/README.md, an adapter-pluggable harness for LongMemEval _s (public 500-Q) + coding-agent-life-v1 (in-house 15-session corpus). Grep / vector / agentmemory adapters score side-by-side, NDJSON output, published scorecards land in docs/benchmarks/.

Pairs with codegraph, Understand Anything, and Graphify. Code-graph indexing, multi-agent build pipelines, and broader knowledge graphs across docs / PDFs / images / videos. agentmemory remembers the work; those three projects light up the rest of the context layer. Recipes + question-routing table: docs/recipes/pairings.md.

---

https://github.com/rohitg00/agentmemory/blob/HEAD/vs Competitors

GitHub Stars & Activity

29,387Stars
2,588Forks
0Open issues
TypeScriptLanguage

GitHub Popularity

GitHub stars29,387
Forks2,588
Open issues0
Primary languageTypeScript
License-
Stars gained today49
Created-
Last pushed-

Trending History

Daily boardrank #42 · ▲ 49 stars

Related AI Projects

1

morluto / rea

TypeScript★ 201,703⑂ 49,253▲ 54,706 stars
→

More AI Rankings

AI Homed · AI projects from GitHub Trending, topic pages and search · updated daily · about sitemap · robots
agentmemory mem0 (63K ⭐) Letta / MemGPT (24K ⭐) Khoj (36K ⭐) supermemory (29K ⭐) TencentDB Agent Memory (22K ⭐) MemPalace (54K ⭐) oracleagentmemory Hippo Built-in (CLAUDE.md)
Type Memory engine + MCP server Memory layer API Full agent runtime Personal AI Memory API + app Team memory hub (LLM proxy) Vector memory (OSS) Memory engine (Oracle DB) Memory system Static file
Retrieval R@5 95.2% 68.5% (LoCoMo) 83.2% (LoCoMo) N/A Self-reported PersonaMem 76% (self-reported) ~96.6% (self-reported) 94.4% (self-reported) N/A N/A (grep)
Auto-capture 12 hooks (zero manual effort) Manual add() calls Agent self-edits Manual API-side extraction Proxy interception (base-URL swap) Manual API extraction Manual Manual editing
Search BM25 + Vector + Graph (RRF fusion) Vector + Graph Vector (archival) Semantic Vector + RAG 4 asset types (Chat / Skill / Wiki / CodeGraph) Vector-only Vector + semantic Decay-weighted Loads everything into context
Multi-agent MCP + REST + leases + signals API (no coordination) Within Letta runtime only No No Team roles + shared assets No Scoped only Multi-agent shared Per-agent files
Framework lock-in None (any MCP client) None High (must use Letta) Standalone None Proxy fronts every model call None Oracle Database None Per-agent format
External deps None (SQLite + iii-engine)