← Latest products

Shodh– AI memory that learns from use

no LLM calls, single Rust binary. Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.

Open source

317 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Unify memory across agents and improve context rot

    github.com

    written in Rust

    Hacker News5 pts

  2. Local Coding Agent with LLMs to Delegate Tool Calls to Small AI Models

    github.com

    Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.

    Hacker News9 pts

  3. A memory database that forgets

    github.com

    consolidates, and detects contradiction

    Hacker News48 pts

  4. Mnemosyne Local hierarchical memory engine for AI agents (MCP Native)

    github.com

    Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.

    Hacker News10 pts

  5. Mnemo

    github.com

    local-first AI memory layer for any LLM (Rust, SQLite,petgraph)

    Hacker News60 pts