Open-source context retrieval layer for AI agents

A structural code search engine for Al agents.

📜 An MCP server for conversation history search and retrieval in Claude Code

Deterministic context database for AI agents. Same query → same context, every time.

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

A modular Python-based search engine pipeline that fetches live web data, extracts both visible and hidden context using advanced NLP techniques, and semantically indexes content for enhanced retrieval. Perfect for powering LLMs and AI agents with up-to-date, relevant context.

Customer support chatbot for construction & home materials companies. Full-stack solution using LangChain + OpenAI LLM to provide context-driven responses from product catalogs. Flask backend, React frontend with chat history integration.

CRS-LM: Structure-aware context reduction for tiny language models under Parameter Golf constraints

A lightweight document-aware chatbot that can answer questions from PDF, DOCX, or text files using Sentence-Transformer embeddings for context retrieval, LLM models (OpenAI and Ollama here) for answer generation and Gradio chatbot UI for interaction

Examples of RAG (Retrieval-Augmented Generation) with Ethora, LangChain, and OpenAI. Build knowledge-based AI assistants fast. Powered by Ethora Chat Component.

Implement retrieval-augmented generation to enhance large language model responses with relevant external data using lightweight, single-header C++ libraries.

SEARCHD enhances the existing information retrieval mechanism and reduces the latency of LLM-based retrievers. This framework generates a partially correct document using a LLM which is clubbed along with the original query for context retrieval.

MCP server for semantic code search and codebase analysis — AST parsing, Tree-sitter, embeddings and vector search for AI assistants and LLMs

Sanitized agent-generated memory bridge design package for OpenClaw-style agents

Python MCP server connecting Claude Desktop to an Obsidian vault, 19 tools for note I/O, IDF-based relinking, tiered context retrieval, and BFS graph walk. Claude's long-term memory.

Repository containing the projects of the EPFL course "Modern natural language processing".

Local LLM agent Framework for building context-aware assistants with RAG, tool use, and database integration.

Agentic Search using multiple enterprise nature data sources

🔍 Build durable software that requires minimal maintenance by focusing on essential questions and user-centric design.