Gemini web → OpenAI-compatible + native Gemini API, self-hosted, no API key. Reverse-proxies gemini.google.com into /v1/chat/completions + /v1beta generateContent: single Go binary, Chrome TLS fing…

On-device Speech AI for Apple Silicon

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

Reverse engineer anything with agents, from app behavior down to native binaries.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Utility to generate PoTokens and run BotGuard attestation challenges.

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

Go support for Google's protocol buffers

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…

Bộ sưu tập code Javascript "paste" vào DevTools để thay đổi cách hoạt động của Zalo Web/PC.

Full reverse-engineering of TikTok's X-Gnarly request signature (webmssdk 5.1.3-ZTCA) with a pure-JavaScript reference encoder and decoder.

Reverse engineering TikTok's JavaScript VM - 77 opcodes mapped, string deobfuscation, bytecode disassembly, and crypto function identification. Educational VM analysis toolkit.

Overview of TikTok's Anti-Bot Encrypted Values - X-Argus, X-Bogus and more. Encryption Algorithms

JavaScript-based web UI to decode ad-hoc Protobuf data

A PyTorch-based Speech Toolkit

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Parse MySQL binlog to SQL you want

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

A vector index built on TurboQuant, written in Rust with Python bindings

Lightpanda: the headless browser designed for AI and automation

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place

AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

Golang PDF library for creating and processing PDF files (pure go)

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

Multilingual Document Layout Parsing in a Single Vision-Language Model