Gentleman-Programming/engram

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.

What it solves

AI coding agents typically lose all context and knowledge when a session ends. Engram provides a persistent, project-aware memory layer that allows agents to remember decisions, bug fixes, patterns, and user constraints across different sessions and projects.

How it works

Engram is delivered as a single Go binary that uses a local SQLite database with FTS5 full-text search for storage. It integrates with AI agents via the Model Context Protocol (MCP), an HTTP API, or a CLI. It can bet be configured to be project-aware, automatically detecting the current repository to load the correct memory scope. For portability and collaboration, it supports Git Sync for sharing compressed memory chunks and an optional Cloud replication service for shared access.

Who it’s for

Developers using AI coding agents (such as Claude Code, Cursor, Windsurf, or Gemini CLI) who want their agents to maintain a long-term memory of their codebase and project-specific knowledge.

Highlights

  • Agent-Agnostic: Works with any MCP-compatible agent, including 14 pre-configured setup targets.
  • Zero Dependencies: A single binary with no requirement for Node.js, Python, or Docker.
  • Project-Aware: Automatically manages separate memory stores for different repositories.
  • TUI Dashboard: Includes a terminal user interface to browse, search, and manage what the agent remembers.
  • Local-First: Keeps data in a local SQLite file by default, with optional cloud or Git-based synchronization.
  • Extensible: Provides a suite of MCP tools for agents to save, search, and review memories.

Related

  • Dispatch
    Engrim 1.3.0: Local‑First SQLite Memory Engine for Multi‑Model AI CLIs

    Engrim 1.3.0 introduces a universal, project‑scoped SQLite memory store that lets developers switch between AI coding assistants without losing context, cutting reload costs by over 99%.

  • Project
    Lyellr88/marm-memory

    A persistent local memory server for AI agents using the Model Context Protocol (MCP), providing shared long-term memory and code-graph awareness across different AI clients.

  • Project
    doobidoo/mcp-memory-service

    A persistent, shared memory backend for AI agents that uses a knowledge graph and semantic search to maintain context across sessions.

  • Project
    AgentMemoryRepo/agentmemoryrepo

    A Git-based memory standard that allows AI agents to maintain persistent, linked knowledge across sessions, users, and agent swarms.

  • Project
    rtk-ai/icm

    A long-term memory system for AI coding agents that stores project decisions and preferences in a local SQLite file, shared across multiple AI tools.