agentic-box/memora

Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.

What it solves

Memora provides AI agents with a persistent, collective memory layer. It solves the problem of agents losing context between sessions or failing to organize complex information, allowing them to store facts, track TODOs, and maintain a structured knowledge graph that persists across different interactions.

How it works

Memora acts as a Model Context Protocol (MCP) server that manages a memory store. It uses a combination of SQLite (local) or cloud databases (Cloudflare D1, S3, R2) to store information. When agents "absorb" new information, an LLM classifies the data to determine if it is new, a duplicate, or an update to existing knowledge. It supports semantic search via vector embeddings and maintains a graph of relations between memories, allowing agents to retrieve a "digest" of a topic including related edges and source IDs.

Who it’s for

It is designed for developers building AI agents (such as those using Claude Code or Codex CLI) who need their agents to have long-term, structured memory and the ability to share context across multiple sessions or workspaces.

Highlights

  • Absorb & Lineage: Automatically classifies new facts and maintains a history of updates where new knowledge supersedes old versions without deleting them.
  • Semantic Search: Supports hybrid search using vector embeddings (OpenAI, sentence-transformers, or TF-IDF) and full-text queries.
  • Knowledge Graph: Includes an interactive visualization server to view memory clusters and relations via Mermaid rendering.
  • Flexible Storage: Supports local SQLite, Cloudflare D1, and S3/R2 sync modes for durable storage.
  • Document Storage: Stores markdown documents as searchable fragment trees, ensuring granular searchability while keeping the document intact.

Related

  • Project
    Lyellr88/marm-memory

    marm-memory is a local‑first memory server for AI agents that use the Model Context Protocol (MCP). It stores chats, notes, code‑graph data and extracted concepts in SQLite, exposing them via HTTP or STDIO so agents can retrieve relevant context instead of starting from scratch. The package includes a web console, Docker image, and CLI tools for starting, managing, and indexing repositories. Benchmarks show low‑latency retrieval (≈30 ms for 4 k memories) and hybrid FTS‑semantic recall that scales to 10 k entries. Ideal for developers building coding assistants or multi‑agent swarms who want a self‑hosted, searchable memory layer.

  • 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.

  • Project
    doobidoo/mcp-memory-service

    A self‑hosted memory backend for LLM agents that provides a REST API, CLI, OAuth, and a web dashboard. It stores facts, decisions, and causal knowledge graphs locally (SQLite + ONNX embeddings) or in hybrid/cloud mode, offering fast (≈5 ms) semantic search, tag‑scoped retrieval, and optional LLM‑generated summaries. Works with LangGraph, CrewAI, AutoGen, Claude Desktop, ChatGPT, and many other tools.

  • Project
    ScottRBK/forgetful

    Forgetful is an MCP server that provides a persistent, graph-based knowledge storage system for AI agents, allowing them to share and retrieve context across sessions using atomic, vector-embedded notes.

  • Project
    MemMachine/MemMachine

    An open-source long-term memory layer for AI agents that enables persistent storage and recall of user preferences and conversational context across sessions.