io.github.varun29ankuS/shodh-memory

@shodh/memory-mcp

Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.

223 127/wk 26 tools GitHub npm PyPI

No known CVEs

No license

Actively maintained

Last commit 1d ago

Works with most clients

Transport: stdio, sse, http

26 tools · ~949 tok

Grade B · 0.5% of 200K ctx

Edit this pageView history

AI / ML Data

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

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

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-varun29ankus-shodh-memory)](https://mcppedia.org/s/io-github-varun29ankus-shodh-memory)

Read me

What io.github.varun29ankuS/shodh-memory does

AI agents forget everything between sessions. Robots lose context between missions. They repeat mistakes, miss patterns, and treat every interaction like the first one.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y '@shodh/memory-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

88/100across 5 weighted dimensions

How we score →

0255075100

−12

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked @shodh/memory-mcp against OSV.dev.

Inventory

Tools (26)

Click any tool to inspect its schema.

~949 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.varun29ankuS/shodh-memory safe to use?: io.github.varun29ankuS/shodh-memory has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.varun29ankuS/shodh-memory?: io.github.varun29ankuS/shodh-memory supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.varun29ankuS/shodh-memory do?: io.github.varun29ankuS/shodh-memory provides 26 tools: remember, recall, proactive_context, context_summary, list_memories and 21 more. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.varun29ankuS/shodh-memory?: io.github.varun29ankuS/shodh-memory is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.varun29ankuS/shodh-memory actively maintained?: io.github.varun29ankuS/shodh-memory is actively maintained — last commit was 1 day ago. It has 223 GitHub stars.

Similar servers

Others in ai-ml / data

View all →

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

87.8k 1

Memory MCP Server96

Persistent memory using a knowledge graph

87.8k 5

Dbhub96

Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.

3.1k 2

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

18.3k 6

MCP Security Weekly

Get CVE alerts and security updates for io.github.varun29ankuS/shodh-memory and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Shodh-Memory

Persistent cognitive memory for AI agents and robots — with no LLM in the loop. Remembers what matters, forgets what doesn't, gets smarter with use.

Shodh-Memory Demo — Claude Code with persistent memory and TUI dashboard

AI agents forget everything between sessions. Robots lose context between missions. They repeat mistakes, miss patterns, and treat every interaction like the first one.

Shodh-Memory fixes this. It's persistent memory that actually learns — memories you use often become easier to find, old irrelevant context fades automatically, and recalling one thing brings back related things. Works for chat agents (MCP/HTTP), robots (Zenoh/ROS2), and edge devices. No API keys. No cloud. No external databases. No LLM in the loop. One binary.

Why Not Just Use mem0 / Cognee / Zep?

Shodh

mem0

Cognee

Zep

LLM calls to store a memory

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

Learns from usage

Yes (Hebbian)

Forgets irrelevant data

Yes (decay)

Temporal only

Runs fully offline

Yes

Robotics / ROS2 native

Yes (Zenoh)

Binary size

~17MB

pip install + API keys

pip install + API keys + Neo4j

Cloud only

Every other memory system delegates intelligence to LLM API calls — that's why they're slow, expensive, and can't work offline.

No LLM in the Loop

Storing a memory makes zero LLM calls. Recalling makes zero LLM calls. Entity extraction, relation typing, knowledge-graph construction, causal tracing, ranking, decay, consolidation — all of it runs locally as algorithms, not API round-trips:

Local embeddings — MiniLM (22MB, INT8) via ONNX Runtime, on-device semantic search

Local NER — TinyBERT (14MB, INT8) extracts people, places, organizations from every memory

Typed relation extraction without an LLM — directed lexical cues + exemplar-matched

Frequently Asked Questions

Is io.github.varun29ankuS/shodh-memory safe to use?

io.github.varun29ankuS/shodh-memory has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.varun29ankuS/shodh-memory?

io.github.varun29ankuS/shodh-memory supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.varun29ankuS/shodh-memory do?

io.github.varun29ankuS/shodh-memory provides 26 tools: remember, recall, proactive_context, context_summary, list_memories and 21 more. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.varun29ankuS/shodh-memory?

io.github.varun29ankuS/shodh-memory is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.varun29ankuS/shodh-memory actively maintained?

io.github.varun29ankuS/shodh-memory is actively maintained — last commit was 1 day ago. It has 223 GitHub stars.

Shodh-Memory

Persistent cognitive memory for AI agents and robots — with no LLM in the loop. Remembers what matters, forgets what doesn't, gets smarter with use.

AI agents forget everything between sessions. Robots lose context between missions. They repeat mistakes, miss patterns, and treat every interaction like the first one.

Why Not Just Use mem0 / Cognee / Zep?

	Shodh	mem0	Cognee	Zep
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 offline	Yes	No	No	No
Robotics / ROS2 native	Yes (Zenoh)	No	No	No
Binary size	~17MB	pip install + API keys	pip install + API keys + Neo4j	Cloud only

Every other memory system delegates intelligence to LLM API calls — that's why they're slow, expensive, and can't work offline.

No LLM in the Loop

Local embeddings — MiniLM (22MB, INT8) via ONNX Runtime, on-device semantic search
Local NER — TinyBERT (14MB, INT8) extracts people, places, organizations from every memory
Typed relation extraction without an LLM — directed lexical cues + exemplar-matched

... View full README on GitHub