omega-memory and shodh-memory
These two tools are competitors, as both provide persistent, cognitive memory systems for AI agents, differing in their specific approaches to learning, forgetting, and strengthening information.
About omega-memory
omega-memory/omega-memory
Persistent memory for AI coding agents
Provides semantic search over locally-stored memories using ONNX embeddings, with 25+ tools for decision tracking, lesson retention, and relationship graphs—all in a single SQLite database. Integrates as an MCP server with Claude Code via stdio, automatically surfacing relevant context across sessions without cloud dependency. Optional pro modules add multi-agent coordination, intelligent LLM routing across providers, and RAG-based knowledge ingestion, all running in the same process.
About shodh-memory
varun29ankuS/shodh-memory
Cognitive memory for AI agents — learns from use, forgets what's irrelevant, strengthens what matters. Single binary, fully offline.
Implements local embeddings and Hebbian learning to achieve sub-200ms memory storage without LLM API calls, with automatic activation decay and spreading activation for relevance-based recall. Available as MCP server for Claude/Cursor, HTTP API, or native Rust/Python libraries; also supports robotics frameworks (ROS2/Zenoh) and includes a TUI dashboard for memory visualization and GTD task management.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work