basicmachines-co/basic-memory

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

What it solves

Basic Memory provides a persistent, two-way memory system for AI assistants. It solves the problem of ephemeral LLM conversations where knowledge is lost between sessions. Unlike traditional RAG, which is read-only, Basic Memory allows both humans and AI agents to read and write to a shared knowledge base of Markdown files, creating a long-term memory that evolves over time.

How it works

The system uses plain Markdown files stored locally or in the cloud as the source of truth. It implements the the Model Context Protocol (MCP), allowing it to integrate with AI clients like Claude, Cursor, and VS Code.

Knowledge is structured as "Entities" with "Observations" (facts) and "Relations" (wiki-links) that form a traversable knowledge graph. To find information, it uses a combination of full-text and semantic vector search (via FastEmbed) with optional cross-encoder reranking for higher precision.

Who it’s for

Developers and AI power users who want their AI assistants to remember project architecture, personal learnings, and professional workflows across different sessions and tools (e.g., Obsidian, Claude Desktop, Cursor).

Highlights

  • Two-way synchronization: Humans and AI agents write to the same Markdown files.
  • MCP-native: Seamlessly works with any MCP-compatible AI client or IDE.
  • Local-first: Data is stored as plain text on the user's disk by default.
  • Semantic Search: Combines vector and hybrid search to find notes by meaning rather than just keywords.
  • Knowledge Graph: Uses wikilinks to allow AI agents to navigate connected concepts.
  • Progressive Tool Discovery: Tools are tagged with behavior hints (e.g., read-only, destructive) to help agents select the correct tool efficiently.

Related

  • Project
    MemTensor/MemOS

    MemOS 2.0 is a Memory Operating System for LLM‑based AI agents. It offers a unified API to store, retrieve, edit, and delete multi‑modal memories (text, images, tool traces) organized as a graph. The system can run as a hosted cloud service (API‑key access) or be self‑hosted via Docker (Neo4j + Qdrant) or a local SQLite plugin. Ready‑made plugins integrate MemOS with OpenClaw, Hermes, and DeepSeek Harness. Benchmarks show it outperforms existing commercial memory products. Licensed under Apache 2.0.

  • Project
    TencentCloud/TencentDB-Agent-Memory

    TencentDB Agent Memory is an open‑source memory hub for LLM agents. It captures conversations, extracts reusable skills, builds a Wiki from docs, and indexes code into a CodeGraph. A central UI (Memory Hub) lets teams manage assets, set fine‑grained ACLs, and bind specific memory pieces to individual agents. Agents talk to a uniform proxy, so any framework (Claude Code, DeepSeek Harness, OpenClaw, etc.) can use the same memory without code changes. Benchmarks show a 59 % boost in persona retention. The repo provides one‑click Docker deployment, migration tools, and a roadmap for zero‑config cold starts and more integrations.

  • Project
    EverMind-AI/EverOS

    EverOS is a Python library that provides local‑first, Markdown‑backed memory for AI agents. It syncs files to SQLite and LanceDB, offers a simple HTTP API for add/flush/search, and works with a single OpenRouter key for keyword search. Optional extras add embedding‑based hybrid search, reranking, and multimodal file ingestion.

  • Project
    rohitg00/agentmemory

    A persistent memory layer for AI coding agents that captures and compresses session data to eliminate the need for re-explaining project context across sessions and tools.

  • Project
    mnemon-dev/mnemon

    Mnemon is a cross‑platform CLI that adds persistent, graph‑based memory to LLM agents. The host LLM supervises what to remember, link, or forget, while Mnemon handles deterministic storage, decay, deduplication, and optional vector search. It integrates with many AI coding tools (Claude Code, Codex, Cursor, etc.) via one‑click setup, requiring only a single local binary and no extra API keys.