Stars
Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins
A SKILL that turns a code diff into an evidence-backed ledger of hidden assumptions, failure modes, and falsification tests.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…
Agent orchestration framework with Git-backed storage. Every turn is a Git commit - inspectable, rewindable, forkable.
Build agent that uses 80% less token and delivers better results.
Fix AI pixel art and vector images right in your browser
The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS
Safely run OpenCode, Codex, Claude Code with full permissions.
Run the coding agents inside an isolated Docker container, one persistent container per workspace. A single bash script builds the image, manages per-workspace containers with optional network isol…
atharva-again / pi
Forked from earendil-works/piMy own Pi, just the way I like.
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
A proxy MCP (Model Context Protocol) server that filters the upstream tool surface to just the tools you need.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Open-source deep-work orchestrator: a frontier planner proposes one small epoch at a time; local models grind; deterministic gates verify everything. Model proposes, state machine disposes.
The official PHP SDK for Model Context Protocol servers and clients. Maintained in collaboration with The PHP Foundation.
Probe any HTTP server for OpenAI API compliance, with an honest matrix of how the OSS implementations actually behave.
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
super expressive prompting model based on ltx2.3
nomacs is a free image viewer for windows, linux, and mac systems.
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
See what your AI sees. Framework-agnostic LLM context window visualizer.
A text-grid web renderer for AI agents — see the web without screenshots
Composite Machine: Automatic Calculus via Dimensional Arithmetic