MemPalace: Local-First Open-Source Memory System for AI Agents

RepositoryMemPalace/mempalaceTool

MemPalace is a local-first memory layer for AI agents that stores conversational history verbatim and retrieves it via semantic search without using external APIs.

Key points

  1. Verbatim storage of conversation history without summaries, extraction, or paraphrasing.
  2. Hierarchical index model organised into wings (people/projects), rooms (topics), and drawers (content) for scoped retrieval.
  3. Pluggable retrieval layer with ChromaDB as default backend via mempalace/backends/base.py.
  4. Local-first design ensuring zero data leaves the machine unless opted in.
  5. Integration via Model Context Protocol (MCP) and agent-guided skills, including retention hooks for Claude Code.
  6. Reported 96.6% R@5 raw performance on LongMemEval benchmark.

Why it matters

AI coding assistants frequently lose context between sessions or hit context window limits. MemPalace provides a privacy-preserving, local persistence layer that allows developers to maintain long-term context across workflows without relying on hosted external memory services.

Analysis

MemPalace targets developers and autonomous coding agents needing durable memory across sessions. By avoiding LLM-based summarisation in favour of exact verbatim storage and scoped vector retrieval, it prevents hallucinated summaries or lost details. Technologically built on Python and ChromaDB with MCP support, it integrates directly into modern agent setups. With nearly 59,000 GitHub stars and strong community activity, the project demonstrates high maturity and broad adoption, although official maintainers explicitly warn against malicious copycat domains.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:rohitg00/agentmemory

    agentmemory: Persistent Memory for AI Coding Agents

    agentmemory is an open-source TypeScript solution providing persistent memory for coding agents and MCP clients. Powered by the iii engine, it builds on Andrej Karpathy's LLM Wiki pattern by introducing confidence scoring, lifecycle management, knowledge graphs, and hybrid search.

    28kstarsTypeScript

    AI & LLMs· Tool

  • Repository:thedotmack/claude-mem

    claude-mem: Persistent Cross-Session Memory for AI Agents

    The open-source project claude-mem (now also branded as Grok Mem) captures agent activity during active sessions, compresses it with AI, and injects relevant context back into future runs.

    93.1kstarsJavaScript

    AI & LLMs· Tool

  • Repository:Gentleman-Programming/engram

    Engram: Persistent Memory System for AI Coding Agents

    Engram is an open-source, agent-agnostic memory engine written in Go that provides AI coding assistants with persistent memory across sessions.

    6.4kstarsGo

    AI & LLMs· Tool

  • Repository:vectorize-io/hindsight

    Hindsight: Agent Memory That Learns

    Hindsight is an MIT-licensed memory system designed to help AI agents learn over time. Rather than merely recalling conversation histories, it aims to overcome the limitations of conventional RAG and knowledge graphs on long-term memory tasks.

    41.3kstarsPython

    AI & LLMs· Tool

  • Repository:DeusData/codebase-memory-mcp

    codebase-memory-mcp: High-Performance Knowledge-Graph Code Intelligence via MCP

    codebase-memory-mcp is a pure C Model Context Protocol (MCP) server that indexes codebases into persistent knowledge graphs, providing AI coding agents with sub-millisecond structural search while dramatically reducing token consumption.

    42.3kstarsC

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.