varun29ankuS/shodh-memory

View on GitHub ↗

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.

273 ★37 forksRustUpdated 19d ago

What you need to know

A single-prompt multi-agent research paper workspace that combines AI agents, semantic text analysis, OntoNotes word sense disambiguation, and knowledge graph building to generate code for research papers.

Install

Provide a single natural-language research prompt; system wires agents, text analysis and knowledge graph tooling together

Usage

  • Paste a research paper requirement and let the multi-agent workspace generate code
  • Leverage OntoNotes-based word sense disambiguation and knowledge-graph construction for deeper understanding

Key features

  • Single-prompt multi-agent research paper workspace
  • AI agent orchestration plus semantic text analysis
  • OntoNotes word sense disambiguation and knowledge graph building
  • Generates code for research papers

Best for

Researchers who want an AI-assisted pipeline that goes from a research paper description to generated code with structured knowledge graphs.

Platforms: Web

Reviewed 2026-08-11

Topics

agent-memoryagentic-aiai-agentsai-memoryclaudecognitive-memoryedge-aigraphragknowledge-graphllm-freelocal-firstmcpmodel-context-protocolrobot-memoryroboticsros2rustvector-databasevector-searchzenoh
Stars
273★
Forks
37
Language
Rust
License
Apache-2.0
Created
2025-12-03
Last push
2026-08-17