shodh-memory
Active·★ 215·Apache-2.0·Updated 2026-05-29
★ Trending★ RAG / Knowledge Base★ Memory & Context
Cognitive brain for Claude, AI agents & edge devices — learns with use, runs offline, single binary. Neuroscience-grounded 3-tier architecture with Hebbian learning.
Shodh-Memory provides persistent, cognitive memory for AI agents, allowing them to retain context and learn across sessions. It's packaged as a single ~17MB binary that operates entirely offline on your hardware, preventing agents from forgetting information.
#AI Memory#Persistent Storage#Local-first#Offline#Cognitive System#Knowledge Graph#GTD#Rust
01
Features
01Persistent Cognitive Memory for AI Agents
02Local-first, Single Binary & Offline Operation
03Advanced Cognitive Processing (Hebbian learning, activation decay, etc.)
04Interactive TUI Dashboard with Knowledge Graph Visualization
05Integrated GTD (Getting Things Done) Task Management
02
Compatibility
Python
Language SDK
Verified via docs
Rust
Language SDK
Verified via docs
npm
Language SDK
Verified via docs
Claude/Cursor
AI Agent Integration
Verified via docs
Linux
Operating System
Verified via docs
macOS
Operating System
Verified via docs
03
Quick start
1
$ curl -L https://github.com/varun29ankuS/shodh-memory/releases/latest/download/shodh-memory-linux-x64.tar.gz | tar -xz
2
$ ./shodh-memory
04
Use cases
↳Providing persistent memory and learning capabilities for various AI agents (e.g., Claude, GPT, LangChain, AutoGPT).
↳Enhancing robotic systems with long-term memory that runs on local hardware.
↳Deploying intelligent memory systems on cloud, edge devices, or air-gapped environments.
↳Managing tasks and projects using a GTD-inspired system integrated with AI agents.
05
Alternatives
ragflow★ 81.5k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
n8n★ 190.2k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
mcp-memory-service★ 1.9k
Stop re-explaining your project to AI every session. Automatic context memory for Claude, VS Code, Cursor, and 13+ AI tools.
flow-like★ 884
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
Related searches
Comments
Log in to leave a comment
- JJamie GarciaApr 28, 2026
Edge device support is rare in memory systems — valuable for embedded AI.
- RRowan ZhangApr 6, 2026
Cognitive memory that learns with use and runs offline on edge devices.
- LLogan GarciaMar 15, 2026
Good for privacy-sensitive applications where cloud-based memory is unacceptable.
- JJustice DavisMar 11, 2026
Learning-with-use model means the memory becomes more useful over time.