mcp-server

shodh-memory: Offline, Auditable Memory for Your AI Agents

Provides founders a deterministic Rust binary that stores, forgets, and prioritizes data locally—no cloud, no API keys required. Ideal for edge‑AI and robotics teams.

From the repo · “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.”

314 stars+5★ this week44 forksRustGuide quality 9/10 · reviewed Oct 20Updated 10/19/2026100% free · open source
What it does

Shodh-memory provides a local, auditable AI memory for deterministic AI agent learning, allowing startups to have an offline AI solution without relying on cloud services or API keys.

When to use it
  • •When you need an AI solution that operates completely offline for security or privacy reasons
  • •When you want to have full control and auditability over your AI agent's learning and decision-making process
  • •When you're working with sensitive data that cannot be sent to cloud services or external APIs
Ready-to-paste prompt
./shodh-memory learn 'This is an example sentence to learn.' && ./shodh-memory recall 'example'
Heads up: Make sure you have the necessary permissions to execute the binary and that your system meets the Rust runtime requirements, as specified in the GitHub repository's README
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/shodh-memory && curl -fsSL https://workflowstacks.com/api/skills/shodh-memory/claude-skill -o ~/.claude/skills/shodh-memory/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

26
top-level files
29
folders
78.4M
source size
Apache-2.0
license
Key files
README-python.md
README-rust.md
README.md
shodh_config.example.json
File tree
.cargo/
.claude/
.github/
assets/
benches/
benchmarks/
config/
connectors/
crates/
demo/
docker/
docs/
eval/
examples/
front/
homebrew/
hooks/
marketing/
mcp-server/
notebooks/
python/
scripts/
seat/
seps/
Quick Actions
Details
Creator
varun29ankuS
Language
Rust
Category
mcp-server
Published
12/3/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/shodh-memory.svg)](https://workflowstacks.com/skills/shodh-memory?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.