Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Trending repositories
Hand-picked tools to improve your workflow.
Modern open-source time-tracking app
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
📂 Web File Browser
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
小说下载|网文下载 | 网络小说
A native, user-mode, multi-process, graphical debugger.
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
A Datacenter Scale Distributed Inference Serving Framework
Unified Policy as Code
A podcast manager for Android