A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
54,141 visible repositories in the index
1–24 of 34 · Most stars
Get your documents ready for gen AI
SGLang is a high-performance serving framework for large language models and multimodal models.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
- semantic-search
- emacs
- obsidian-md
- chat
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
- agent-skills
- ai-agents
- context-engineering
- document-processing
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
The Modular Platform (includes MAX & Mojo)
- ai
- language
- machine-learning
- mojo
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
- a2a
- a2a-mcp
- a2a-protocol
- a2a-server
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
An Application Framework for AI Engineering
- artificial-intelligence
- java
- spring-ai
Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free
Home of StarCoder: fine-tuning & inference!
TranslatedOpen-source manuscript of 《深入理解 AI Infra：量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
- accelerator
- ai-infra
- ai-infrastructure
- book
An open, programmable decision layer for models and compute.
- mixture-of-models
- semantic-router
- vllm
- ai-gateway
OpenDeepWiki is the open-source version of the DeepWiki project, aiming to provide a powerful knowledge management and collaboration platform. The project is mainly developed using C# and TypeScript, supporting modular design, and is easy to expand and customize.
- chatgpt
- deepwiki
- docs
- fine-tuning
Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.
TranslatedOne-click replacement of the built-in prompts of four AI clients: DSH / WorkBuddy / ZCode / Codex. Double-click to use, self-verifiable, backs up before changes, one-click restore. A single-file exe that needs no Python installation, open source under the MIT license; activation codes are used for server operation and maintenance, and are issued through self-service on the official website.
- deepseek-harness
- persona
- python
- windows
This project is a plugin that supports ChatGPT running on JetBrains series IDE.
- chatgpt
- chatgpt-jetbrains
Native Ubuntu control center for agent usage, system utilities, media, clipboard, emoji and GNOME integration.
- gnome
- linux
- productivity
- rust
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
- ai-gateway
- anthropic
- claude-code
- codex
Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
- cpu
- diffusion-models
- gguf
- inference
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.