AI open source rankings.

Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

An end-to-end open ecosystem for robot learning

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

Sequence-to-Sequence learning using PyTorch

Object detection project for real-time (webcam) and offline (video processing) application.

Demo showing how to use the OpenAI Realtime API to navigate a 3D scene via tool calling

@deprecated 已不维护

Turn Antigravity / codex / github copilot into Anthropic & Openai API compatible server. Usable with Claude Code / Xcode etc.

A Vietnamese Voice Cloning Text-to-Speech Model ✨

Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.

Web UI for ExLlamaV2

🚀CNN-based image retrieval built on Keras

Mimic Recording Studio is a Docker-based application you can install to record voice samples, which can then be trained into a TTS voice with Mimic2

This is a private learning repository for reinforcement learning techniques used in robotics.

Train high-quality text-to-image diffusion models in a data & compute efficient manner

A Gym for Agentic LLMs

⚠️ No longer maintained The official Stagehand Python source has moved here. Documentation can be found here This version of the Stagehand Python SDK is no longer maintained and will not receive updates, bug fixes, or security patches.

Python wrapper for the Codegen API - run code agents at scale

A general and flexible factor graph non-linear least square optimization framework

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.

Claude Code Skill that turns any idea into a cinematic, model-ready video prompt — Sora · Kling · Veo · Seedance. 21 genre templates, 5-stage structure, eval-tested. Distilled from the AI short Hollywood director PJ Ace called "one of the best short films I've seen in years."

Turn docstrings into LLM-functions

Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.

Pytorch implementation of SIREN - Implicit Neural Representations with Periodic Activation Function

🕵️‍♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.

ICPR 2020: Facial Expression Recognition using Residual Masking Network