shodh-memory and In-Memoria
These tools appear to be competitors, both aiming to provide core memory infrastructure for AI agents, with A focusing on cognitive memory with learning and forgetting, and B on a persistent intelligence infrastructure.
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.
About In-Memoria
pi22by7/In-Memoria
Persistent Intelligence Infrastructure for AI Agents
Connects AI assistants to persistent codebase intelligence via the Model Context Protocol, using Rust-powered AST parsing and pattern learning to store architectural insights, naming conventions, and coding patterns in local SQLite/SurrealDB. Provides semantic search, smart file routing, and work-session tracking that persists across separate AI interactions—eliminating the need to re-explain project context repeatedly.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work