OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Shodh Memory

Shodh Memory is a Rust-based local memory service that stores persistent context and retrieves related information for AI agents and robots. It provides MCP and HTTP interfaces for chat agents and names Zenoh and ROS 2 integrations for robotics. Its memory processing uses local algorithms rather than an LLM in the loop.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Shodh Memory — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an agent or robot needs persistent local context, especially when memory storage and retrieval should not depend on LLM API calls. Choose the documented MCP or HTTP route for chat agents; the project also names Zenoh and ROS 2 for robotics.

Who it is for

  • AI agent developers who need context to persist between sessions.
  • Robotics developers exploring persistent context between missions.
  • Teams seeking local memory storage and retrieval without LLM calls for memory operations.

Documented uses

  • Connect an agent to memory it can use across sessions.
  • Capture chat-agent session context through the documented Claude Code hooks.
  • Retrieve related memories and construct knowledge-graph relationships locally.
  • Explore carrying persistent context between robot missions through the named robotics integrations.
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. The README documents a single-binary setup and a Docker option; it does not establish specific operating-system compatibility.

  • Memory storage and recall are described as LLM-free, using local algorithms and models.
  • The project describes usage-based memory strengthening and decay of irrelevant context.
  • The documented agent interfaces are MCP and HTTP; robotics integrations named are Zenoh and ROS 2.
  • The README provides both a single-binary setup and a Docker route for production or shared servers.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Connect Claude Code to Shodh Memory through MCP

Add the Shodh Memory MCP server to Claude Code, with optional automatic context capture.

Before you start

  • Claude Code
  • The documented @shodh/memory-mcp package and its required runtime

Steps

  1. Run claude mcp add shodh-memory -- npx -y @shodh/memory-mcp to add the MCP server.

  2. Optionally run the command below to install Claude Code hooks for automatic session-context capture.

    Documented command
    npx @shodh/memory-mcp setup-hooks

Expected outcome

Claude Code can use Shodh Memory tools; the optional hooks capture context from sessions automatically.

Guide limitations

  • The setup instructions do not establish compatibility with other agent clients.
  • Automatic capture is an optional additional setup step.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
varun29ankuS/shodh-memory · Official homepage title · retained in its source language
How we review sourcesSuggest a correction