Stars
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Native Agent CLIs manager for macOS. Ghostty Terminals + Codex App Features/UX = Ghostex! Embedded browser & IDE. Strong agents support.
LUMEN, a generative shader studio. 9 WebGL2 art modes plus synth style blending, perfect-loop animation, gradient sets, share codes and PNG/WebM/GIF export. Zero dependencies.
An extensible Vue 3 web text-editor based on Lexical.
Model export recipes, Python primitives, and Swift runtime utilities for on-device AI
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative
Zero-config, fast `io_uring`-based HTTPS server.
Official implementation of LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
Miso TTS is an 8 billion, highly emotive text-to-speech model
AI coding agent skills for building, shipping, and maintaining native macOS apps
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.
devflowinc / firecrawl-simple
Forked from firecrawl/firecrawl➖ Stripped down, stable version of firecrawl optimized for self-hosting and ease of contribution. Billing logic and AI features are completely removed. Crawl and convert any website into LLM-ready …
SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.
Unified agent memory and context compression stack for 2026 NVIDIA + edge (Vera CPU, Grace, Jetson Thor, 3090). Glues busyBee-cpu, honey-comb, and rust-brain. Better effective reasoning per token.
A pure Elixir library that turns Python ASTs into working Elixir source.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Experimental remote DuckDB Quack protocol client for Elixir, built on DBConnection with early Ecto support