shodh-memory

by varun29ankuS · Rust · ★ 203

Cognitive memory for AI agents — learns from use, forgets what's irrelevant, strengthens what matters. Single binary, fully offline.

#agentic-ai#ai-agents#ai-memory#boston-dynamics-spot#claude#cognitive-architecture#cognitive-memory#context-engineering#graphrag#knowledge-graph#local-first#mcp#model-context-protocol#robot-memory#robotics#ros2#rust#vector-database#vector-search#zenoh

Install

cargo install --git https://github.com/varun29ankuS/shodh-memory.git

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "shodh-memory": {
      "command": "npx",
      "args": [
        "-y",
        "github:varun29ankuS/shodh-memory"
      ]
    }
  }
}

From the README

Shodh-Memory Persistent cognitive memory for AI agents and robots. Remembers what matters, forgets what doesn't, gets smarter with use. |---|---|---|---| | LLM calls to store a memory | **0** | 2+ per add | 3+ per cognify | 2+ per episode | | External services needed | **None** | OpenAI + vector DB | OpenAI + Neo4j + vector DB | OpenAI + Neo4j | | Time to store a memory | **55ms** | ~20 seconds | seconds | seconds | | Learns from usage | **Yes** (Hebbian) | No | No | No | | Forgets irrelevant data | **Yes** (decay) | No | No | Temporal only | | Runs fully offli…

Read full README on GitHub →