python

Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

Stephanie is an open-source platform built specifically for voice-controlled applications as well as to automate daily tasks imitating much of an virtual assistant's work.

Learn Cloud Applied Generative AI Engineering (GenEng) using OpenAI, Gemini, Streamlit, Containers, Serverless, Postgres, LangChain, Pinecone, and Next.js

CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.

🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.

Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.

Open-source VMs-as-a-service

Free, open-source, 100% offline voice dictation for Linux. Speak and type anywhere via whisper.cpp, Whisper & VOSK engines, GPU-accelerated, works on X11 + Wayland!

Transform audio-visual content into navigable knowledge.

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.

AI-Video-Cropper is a Python-based tool that leverages the power of GPT-4 (OpenAI's language model) to automatically analyze videos, extract the most interesting sections, and crop them for improved viewing experience. This project combines the capabilities of GPT-4, FFmpeg, and OpenCV to automate the process of identifying highlights in videos

Python automation toolkit for SolidWorks API

:newspaper: Let ChatGPT Summarize Hacker News for You

MCP server for JADX-AI Plugin

Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.