RAG System · Python

Websearch

Jens Mittelbach@jmiba · Atlas 61.8 · #6= builder

View on GitHub Open Jens Mittelbach's Atlas

What it is

The Websearch repository provides a Dockerized, local-first web search service that integrates with LM Studio via the Model Context Protocol (MCP). It offers tools for web search, reading webpages, extracting information, mapping sites, crawling, and deep research, all with citation-safe output.

Scored from the code at its last scan, 16 Oct 2026. How merit is scored

Where it counts

NLP & LLMs90%
AI Agents50%
Data Science30%
MLOps20%
Machine Learning10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the NLP & LLMs board

Whole board

RankProjectBuilderFieldMerit

3event-aware-SAE-trainerLibrary / Framework · PythonThe repository provides a library for training JumpReLU sparse autoencoders (SAEs) per transformer layer with an event-aware optimizer scheduler and augmented Lagrangian sparsity control. It includes tools for activation capture, checkpointing, and diagnostics, demonstrated by…75.2/100AdvancedRickNLP & LLMs
04RegesMoEML Application · C++RegesMoE is an end-to-end application that enables running the RegesCore 35B mixture-of-experts model on a normal PC with a single GPU, providing an installer, local OpenAI- and Anthropic-compatible API, and web app.72.5/100AdvancedMaster MindNLP & LLMs
05WebsearchRAG System · Python70.9/100AdvancedJens MittelbachNLP & LLMs
06Fresta-DiamondLibrary / Framework · PythonFresta Diamond is a Python runtime library that provides typed contracts, persistent state management, and explicit effect controls for LLM-based applications, featuring module admission, attention continuation, and cognitive architecture concepts.69.4/100AdvancedTiago SantosNLP & LLMs
07magellanAI Developer Tool · RustMagellan is a deterministic codebase indexing tool that extracts symbols, references, AST, CFG, and other code facts from multiple languages and stores them in a SQLite database for fast querying via CLI or library API. It is designed to provide code intelligence for downstream…68.8/100AdvancedLuiz Cesar SpiesNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from Jens Mittelbach