Enterprise DNA
M MCP Servers Developer low

varun29ankuS/shodh-memory

by Various

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

V

MCP

varun29ankuS/shodh-memory

Added 1 June 2026

#agentic-ai #ai-agents #ai-memory #boston-dynamics-spot #claude #cognitive-architecture #cognitive-memory #context-engineering

Overview

Shodh-memory is a cognitive memory system for AI agents that runs as a single offline binary written in Rust. It learns from usage to strengthen relevant memories and forget irrelevant information over time.

Best for

Best for
Developers building offline AI agents that require adaptive, self-maintaining memory

Use cases

  • Adding persistent adaptive memory to autonomous AI agents
  • Running a memory store entirely offline without cloud dependencies
  • Building lightweight agents that prioritize learned information

How to use

Install

npx @shodh/memory-mcp setup-hooks

Tools exposed

  • remember
  • recall
  • recall_by_tags
  • proactive_context
  • context_summary
  • list_memories
  • read_memory
  • forget
  • quick_recall
  • query
  • topic
  • what_i_know
  • recent_memories
  • pending_work
  • count
  • memory_health
  • session_summary
  • session_digest
  • session_history
  • fact_na

Tested with

Claude Desktop, Claude Code, Cursor, ChatGPT

Example client config

{\n  "mcpServers": {\n    "shodh-memory": {\n      "command": "npx",\n      "args": ["-y", "@shodh/memory-mcp"]\n    }\n  }\n}

Notes

Shodh-memory is a cognitive memory system for AI agents that runs as a single offline binary written in Rust. It learns from usage to strengthen relevant memories and forget irrelevant information over time.

215 stars on GitHub. Last updated 2026-06-01. Licensed Apache-2.0.

Use cases

  • Adding persistent adaptive memory to autonomous AI agents
  • Running a memory store entirely offline without cloud dependencies
  • Building lightweight agents that prioritize learned information

Pros

  • Single binary makes deployment simple and self-contained
  • Fully offline operation preserves privacy and avoids API costs
  • Rust implementation offers good performance and low resource usage

Cons

  • Small community and limited stars suggest early-stage adoption
  • Less documentation and fewer examples compared to established memory solutions
  • Core adaptive forgetting logic may need tuning for specific use cases

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Single binary makes deployment simple and self-contained
  • Fully offline operation preserves privacy and avoids API costs
  • Rust implementation offers good performance and low resource usage

Cons

  • Small community and limited stars suggest early-stage adoption
  • Less documentation and fewer examples compared to established memory solutions
  • Core adaptive forgetting logic may need tuning for specific use cases
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks