rohitg00/agentmemory

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

What it solves

Coding agents often suffer from "forgetfulness," requiring users to re-explain project architectures, preferences, and previous bugs across different sessions. While static files like .cursorrules exist, they are limited in size and quickly become outdated. agentmemory provides a persistent, shared memory layer that automatically captures agent activities and injects relevant context into new sessions without manual updating.

How it works

Built on the iii engine, agentmemory acts as a memory server that integrates with AI agents via hooks, the Model Context Protocol (MCP), or REST APIs. It silently captures agent actions, compresses them into searchable memory, and uses a hybrid search approach—combining BM25 (keyword), vector embeddings (semantic), and structural graph matches—to retrieve the most relevant information. It can run in a keyless mode using BM25 or with local embeddings (via all-MiniLM-L6-v2) for free on-device semantic recall.

Who it’s for

Developers using AI coding agents such as Claude Code, Cursor, GitHub Copilot CLI, Gemini CLI, and other MCP-compatible clients who want their agents to maintain long-term project knowledge across sessions and different tools.

Highlights

  • Broad Compatibility: Works with a wide array of agents including Claude Code, Cursor, Codex CLI, and OpenCode via native plugins, hooks, or MCP.
  • Automatic Capture: Features 12 auto-hooks to capture information with zero manual effort.
  • Hybrid Retrieval: Combines keyword, vector, and graph search to achieve high retrieval accuracy (95.2% R@5 on LongMemEval-S).
  • Zero External DBs: Operates without requiring external database installations.
  • Token Efficiency: Significantly reduces token usage compared to pasting full context or using LLM-summarized approaches.

Related

  • Project
    Lyellr88/marm-memory

    A persistent local memory server for AI agents using the Model Context Protocol (MCP), providing shared context, code graphs, and concept graphs across sessions.

  • Project
    doobidoo/mcp-memory-service

    A persistent, shared memory backend for AI agents that provides a knowledge graph and semantic search across sessions and tools via REST API and MCP.

  • Project
    mem9-ai/mem9

    A persistent memory layer for AI agents that enables shared context and recall across sessions, machines, and different agent runtimes.

  • Project
    JuliusBrussee/cavemem

    A cross-agent persistent memory system for coding assistants that uses compressed local storage and MCP to allow AI agents to remember information across sessions.

  • Project
    akitaonrails/ai-memory

    ai‑memory is a Rust‑based server that records every observation a coding‑assistant makes (prompts, tool calls, session boundaries) as plain markdown files in a git‑backed wiki. The server can be run locally, in Docker/Podman, or on a homelab box and is designed to be shared across many agents (Claude Code, Codex, Cursor, Gemini CLI, etc.), machines and team members. Hooks posted by agents are consolidated into readable wiki pages at session end; the next session receives a concise handoff so it can continue exactly where the previous one stopped. Storage is human‑readable markdown plus a SQLite index (FTS5, entity and optional vector search). By default it needs no LLM or embedding keys; optional Anthropic/OpenAI integrations add LLM‑generated summaries and semantic search. Multi‑user authentication, audit logs and per‑person attribution are built in. Install via Arch AUR, Docker wrapper, or native binary, start the server, register a client and its hooks, and the system works transparently.