kitfunso/hippo-memory

Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.

What it solves

Hippo provides a unified, long-term memory layer for AI coding agents, preventing the need to re-teach agents the same information across different tools. It solves the problem of fragmented memory where knowledge is locked in specific tools (like Cursor or Claude Code) or where outdated information persists alongside new facts.

How it works

Hippo uses a local SQLite database as its backbone, with markdown mirrors for human readability and git-tracking. It integrates with agents via hooks and the Model Context Protocol (MCP), allowing it to function as a shared memory store. The system employs a brain-inspired approach to memory: it strengthens memories that are frequently recalled and allows mistakes or outdated facts to decay or be superseded. It supports BM25 search by default (no network calls required) and offers optional local or API-based embeddings for advanced retrieval.

Who it’s for

Developers using multiple AI coding agents (e.g., Claude Code, Cursor, Codex, OpenCode) who want a consistent, portable memory across their projects and tools.

Highlights

  • Cross-Tool Portability: Syncs memories across different agents so that knowledge learned in one tool is available to others.
  • Learning from Outcomes: Allows users to mark memories as "bad" to lower their rank and use supersede to replace old facts.
  • Local-First Privacy: Keeps proprietary data local in SQLite and markdown files with zero runtime dependencies.
  • Broad Ingestion: Imports data from ChatGPT, Claude, Cursor rules, Slack, and raw conversation logs.
  • Automated Maintenance: Includes a hippo sleep process for memory consolidation, deduplication, and learning from git commits.

Related

  • Project
    vshulcz/deja-vu

    deja-vu is a local, private memory engine for coding AI agents. It indexes transcripts from 41+ agent harnesses (Claude Code, Codex, Cursor, etc.), stripping secrets, and provides instant search, recall, and MCP integration so agents remember past fixes, commands, and file changes across sessions and tools. It features a fast CLI/TUI, proactive session-start recall, and benchmarks showing 97.2% R@5 on LongMemEval-S.

  • Project
    MemoriLabs/Memori

    A persistent, structured memory layer for AI agents that captures conversations and and agent execution traces to eliminate session amnesia and reduce token costs.

  • Project
    beilusaiying/always-accompany

    A multi-purpose AI agent framework focused on context and attention mechanisms, providing layered memory and dynamic retrieval for long-term companionship, coding, and work.

  • Project
    fuyuxiang/echo-agent

    Echo Agent is an open‑source, self‑hosted AI‑agent runtime that provides long‑term memory, automatic skill extraction/evolution, and pluggable tool integration. It can run interactively in a terminal, as a long‑living Gateway service with a web dashboard and API, or be embedded in a desktop application (EchoAgent Desktop). The core runtime manages the agent loop, session context, model routing, permissions, and automation channels, while the memory system recalls past facts and the evolution system turns execution traces into reusable Skills. Install via `pip install "echo-agent[all]"`, configure an LLM API key, and start with `echo-agent run` or `echo-agent gateway`.

  • Project
    agentic-box/memora

    An MCP memory layer for AI agents that provides persistent collective memory through structured storage, semantic retrieval, and a knowledge graph.