UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
- reinforcement-learning
- ai-infrastructure
- sglang
- vllm
111,085 visible repositories in the index
769–792 of 1,101 · Most stars
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
A simple VITS HTTP API, developed by extending Moegoe with additional features.
Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications
A @ClickHouse fork that supports high-performance vector search and full-text search.
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
企业级 AI 资源纳管平台,提供统一 AI网关、Token调度能力,纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型,并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表,帮助企业精准控制成本、量化 ROI,高效治理 AI 资产。
Local observability for AI coding agents. Agenttrail Map shows your project as a live map of what each agent is working on, in the browser or natively in Herdr.
Distill your LLM traces into a fast hybrid System 1 models. Open-source ML + LLM inference with calibrated deferral.
☁️ The fastest HTML to markdown convertor on GitHub. Optimized for LLMs and supports streaming.
An Agent Skill that makes an LLM write in ASD-STE100 Simplified Technical English. Rules, approved word list, and a check tool.
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
Build a RAG (Retrieval Augmented Generation) pipeline from scratch and have it all run locally.
CLI MCP package manager & registry for all platforms and all clients. Search & configure MCP servers. Advanced Router & Profile features.
This is the fully-functional GNU Radio software-defined radio (SDR) implementation of a LoRa transceiver with all the necessary receiver components to operate correctly even at very low SNRs. This work has been conducted at the Telecommunication Circuits Laboratory, EPFL.
End-to-End Testing Harness
Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking
AI-assisted storyboard and video generation tool. Uses Gemini for generating storyboard text and frames, Vertex AI Veo for generating transition clips, and ffmpeg for stitching the final video. Built-in logs and gallery management.
This Word Does Not Exist
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.
The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.
All Stanford Cheatsheets: Artificial Intelligence, Transformers, LLMs, Deep Learning, Machine Learning, Probabilities, Statistics, Algebra and Calculus.