47,133 repositories indexed
169–192 of 244 · Most stars
TranslatedA completion of the landscape-format full character reference sheet based on the ZipZipPipe (胖次狐, "Panties Fox") AI girl character art: it is broken down into separate assets for three-view turnarounds / expressions / outfits / props, the side and back views are inferred and completed, and everything is stitched together at native pixels 1:1. CC BY-NC-SA 4.0, non-commercial.
AI Agent Identity and Access Management and Inference Firewall
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
A 1:1 Replica & 100% Open Source Claude Desktop
🧱 Experimental library for building inference engines
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and GPT-6 Astra Ultra.
Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
OpenAI-compatible async gateway for muse.ai with pluggable drivers (mock / browser-CDP / http)
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
OpenAI (and DeepSeek, Azure OpenAI, YandexGPT, Ollama, GigaChat, Qwen) API wrapper for Delphi. Use ChatGPT, DALL-E, Whisper and other products.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
Lancer — desktop AI workspace based on pi-gui and pi
Our lightning-fast inference engine.
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
Uncensored AI API and models — one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM and Kimi, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
From a universe of models to Collective Model Intelligence.