Top Finds

An AI-powered e-commerce agent that can handle complex user queries about products, inventory, and order status. Built with a FastAPI backend and a React (Vite) frontend, featuring integration with LLMs for natural language understanding and automated task execution.

📊 Evaluate image quality and performance with Vectalab's vectorization tools for premium outputs and benchmarking capabilities.

🤖 Collaborate using AI agents for comprehensive A-share investment analysis, providing timely insights and risk management support.

🌐 Streamline web scraping with Scraper MCP, a server that optimizes content for AI by filtering data and reducing token usage for LLMs.

Swarm — evolutionary AI forecasting swarm that finds mispriced YES/NO odds and generates paper trades for now. Polymarket-first, Kalshi next.

📈 Build and operate your own quant hedge fund with this complete Python-based algorithmic trading system.

🧠 Enable real-time surgical phase recognition with AI-NeuroAdvisor, leveraging a unique dataset for improved neurosurgical workflow and feedback.

AI-powered biomedical text summarization using extractive NLP, biomedical entity recognition, and transformer-based abstractive summarization.

A zero-trust, deterministic orchestration layer that secures AI reasoning behind immutable Domain Physics — giving the LLM exactly one job: high-weight reasoning.

🚀 Build a high-performance MCP server for CompText DSL with a REST API, offering robust caching, type safety, and production readiness.

🛠️ Create interactive AI agents easily with a feature-rich CLI, offering token tracking, prompt templates, and customizable configurations.

📊 Empower your quantitative research with Qlib, a comprehensive library for AI-driven stock market analysis and prediction.

🛠️ Enable offline NLP workflows with Local-LLM, a lightweight Python library for secure environments using the BERT model, ensuring reproducibility and reliability.

VEX Protocol — The trust layer for AI agents. Adversarial verification, temporal memory, Merkle audit trails, and tamper-proof execution. Built in Rust.

1M+ downloads Linux reference app with basics, tips and formatted man pages

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with token-level streaming halt. Drop-in for any LLM backend.

🔍 Evaluate AI models' ability to detect ambiguity and manage uncertainty with the ERR-EVAL benchmark for reliable epistemic reasoning.

AI agents running research on single-GPU nanochat training automatically

Transform your documents into a searchable knowledge base for AI agents with Gnosis MCP. Easily install, ingest, and serve your data.

👁️ Enhance AI agent performance with Argus, the open-source tool for observability that provides clear insights into agent actions and efficiency.

🌐 Leverage Multifidelity Kolmogorov-Arnold Networks for efficient training with less high-fidelity data in PyTorch, enhancing model accuracy and performance.

AgentLens — Observability and Explainability for AI Agents

Data Science project - python-nlp-sentiment-analysis

🧪 Evaluate uncensored LLMs for offensive security with targeted questions and clear criteria to ensure effectiveness in real-world penetration testing.

AI networking co-pilot -- auto-syncs Gmail, Telegram, Twitter. Detects life events, drafts follow-ups. Open-source alternative to Monica/Dex.