iai-personal-memory-engine
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
iai-personal-memory-engine is an MCP-compatible memory system that gives AI assistants persistent, local memory across sessions. It captures and stores every conversation word-for-word, automatically injects relevant context into new conversations, and maintains historical versions when facts change. The system runs entirely on your machine with encrypted storage, supports multiple AI clients including Claude Code, Cursor, and Codex, and provides 14 MCP tools for recall, search, and memory management. It's designed for single-user workflows with episodic, semantic, and procedural memory tiers.
Key Features
Use Cases
- 01Maintaining conversation history and preferences across multiple AI coding sessions
- 02Tracking evolving project requirements while preserving the original specifications
- 03Building long-term context for AI assistants working on extended development projects
- 04Uploading project documentation and source files for persistent agent knowledge
- 05Resolving contradictions by reviewing both current and historical information
- 06Reducing token costs by injecting targeted memory context instead of full conversation history
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
iai-personal-memory-engine — FAQ
What is iai-personal-memory-engine?+
It's an MCP server that provides persistent memory for AI assistants, storing conversations verbatim and automatically injecting relevant context. The entire system runs locally on your machine with encrypted storage.
How do I install it for Claude Code?+
Install the Python package with 'python3.12 -m pip install -U iai-pme', then run '/plugin marketplace add CodeAbra/iai-personal-memory-engine' and '/plugin install iai-memory@iai-pme' inside Claude Code. Restart the session and verify with 'iai --version'.
Which AI clients does it work with?+
It supports Claude Code, Codex CLI, Cursor, Antigravity, Hermes 0.5.0+, OpenClaw, Gemini CLI, and other MCP-compatible hosts. Full ambient behavior (auto-capture and context injection) is available for Claude Code, Codex, Antigravity, and Hermes.
Do I need an API key or external service?+
No API key is required. All processing runs locally on your machine. There's one optional REM consolidation step that can use 'claude -p' through your existing Claude subscription, capped at 1% of your daily quota.
Is it free and open source?+
Yes, it's released under the MIT license and completely free to use. The code is open source on GitHub.
What are the prerequisites?+
You need Python 3.11 or 3.12 on macOS, Linux, or Windows (beta). The all-in-one installer also requires Git, Node.js 18+, and Rust. No external database or cloud service is needed.
How do I install iai-personal-memory-engine?+
Open the source repository on GitHub and follow its README. iai-personal-memory-engine is a mcp server — MCP Agents Market links you directly to the official repo.
Is iai-personal-memory-engine free?+
iai-personal-memory-engine is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.