whereismyai
IAI Memory Engine
IAI Memory Engine is a local MCP-compliant server that provides long-term memory for AI agents by capturing conversations and injecting relevant context.
IAI Memory Engine is a local server that utilizes the MCP protocol to grant AI agents long-term memory. It captures session conversations verbatim, organizes them, and injects relevant memory slices into new interactions to eliminate repetitive context setting. The system categorizes data into episodic fragments, semantic summaries, and learned behavioral parameters. It operates entirely on your machine without cloud accounts, telemetry, or external API keys for its core storage and retrieval functions. The engine includes tools for search, document ingestion, and graph introspection, supporting various MCP-compatible clients.
IAI Memory Engine at a glance
Key features
- Local-only storage with AES-256-GCM encryption
- MCP protocol support for agent communication
- Automatic capture of conversation turns and sessions
- Semantic and episodic memory classification
- Community detection for organizing related data
- Native Rust-based graph and storage engine
- Dashboard for memory management and introspection
Use it for
- Retaining precise details from past coding sessions
- Maintaining context across multiple AI agent conversations
- Automating recall of specific project constraints or decisions
- Building a searchable repository of personal digital interactions
Alternatives to IAI Memory Engine
- Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
- IHMT MEMORY — It shares one local memory across multiple AI agents without cloud storage or databases.
- Memory MCP server — Simple local memory that carries facts across chats
- DocuMemory — Turns messy AI chat transcripts into clean, reusable context for future sessions.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- AgentMemory — It runs locally with zero external databases and achieves high retrieval recall.
- Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- Turnbook — Saves every chat turn locally with zero model tokens and shares memory across AI apps.
- LongMemory — Provides immutable, temporal, and governed recall instead of simple vector retrieval.
- Engram — Single Go binary with zero dependencies and built-in full-text search.
All IAI Memory Engine alternatives