:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
- auto-research
- benchmark
- deep-learning
- language-models
Repository Index
85,081 visible repositories in the index
673–696 of 777 · Most stars
A curated library of high-quality, professionally crafted prompts for common development tasks. Save time and improve your AI interactions with battle-tested prompt templates. You can install it as an Gemini CLI Extension.
A Unified Framework for Efficient RSI Research
- agent
- recursive-self-improvement
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.
- artificial-intelligence
- clip
- pathology
- vision-and-language
A Java library to use the OpenAI Api in the simplest possible way.
- httpclient
- java
- openai
- simple
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
- ampere
- consumer-gpu
- cuda
- ggml
Can AI agents rebuild websites through browser exploration?
- benchmark
- harbor
- website-reconstruction
- agent-evaluation
UCE is a zero-shot foundation model for single-cell gene expression data
AI Agent failure replay and root cause analysis platform
TranslatedCodex&GPT desktop pet data center | Your desktop dragon girl little assistant
- codex
- desktop-assistant
- desktop-pet
- pyside6
Agent Skill for fine-tuning an agentic model on your own Claude Code sessions with Tinker. Works in Claude Code, Codex and OpenCode.
From a universe of models to Collective Model Intelligence.
- collective-model-intelligence
- model-capabilities
- model-collaboration
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
- ai
- ai-interpretability
- ai-safety
- aisafety
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.
- legal
- legal-ai
- legal-tech
- legaltech
Calibrain Harness: a forward-testing harness for trading crypto perpetuals with fast classification models (Kairos today) on Bybit testnet. Under development.
Our lightning-fast inference engine.
A customizable Windows desktop island for music, focus, live lyrics and your own AI companion.
- desktop-app
- dotnet
- dynamic-island
- windows
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".
- game-ai
- hearthstone
- reinforcement-learning
- rust
A ChatGPT, Gemini, Claude, and Ollama(offline) plug-in for Embarcadero RAD Studio IDE XE5 to 12.1
- chatgpt
- chatgpt-api
- delphi
- embarcadero
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.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.
- ai-agents
- browser-automation
- data-extraction
- firecrawl
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.