Stars
Fully automatic censorship removal for language models
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
DeepSeek Web browser extension: AI agent workspace with MCP tools, memory, Skills, automation, web search, and conversation export.
📜 文书之力 | 专业 AI 公文笔杆子。22 文种 × GB/T 9704-2012 标准 × 四平台通用。萧何收拾秦府文书而定天下，今以 AI 续三千年文脉。
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
A Sun Tzu-based AI strategy skill for decisive unknowns, battlefield choice, opponent reactions, and stop-loss criteria.
Ideogram 4: Open image model at the forefront of design
The design language that makes your AI harness better at design.
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…
Write HTML. Render video. Built for agents.
Indicator Go delivers a rich set of technical analysis indicators, customizable strategies, and a powerful backtesting framework. No dependencies, just pure simplicity. ✨ See how! 👀
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI repl…
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
enseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture
High-performance Qwen3.6-35B-A3B-DFlash inference on NVIDIA DGX Spark (~50 tok/s)
One-command vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs (sm_121 architecture)
Run vLLM on 1-to-N NVIDIA DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs
Control panel for VLLM, Sglang, llama.cpp, exllamav3
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …
Docker configuration for running VLLM on dual DGX Sparks
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…