Stars
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
DeepSeek Harness: Everything is a Plugin.
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
Code for the paper "Defeating Prompt Injections by Design"
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- …
FlashInfer: Kernel Library for LLM Serving
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
[VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
Implementation of the Cedar Policy Language
TL2cgen (TreeLite 2 C GENerator) is a model compiler for decision tree models
#1 Persistent memory for AI coding agents based on real-world benchmarks
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
AI agents running research on single-GPU nanochat training automatically
Open-source implementation of Google's TurboQuant (ICLR 2026) — KV cache compression to 2.5–4 bits with near-zero quality loss. 3.8–5.7x memory reduction on Mistral-7B, no training required.
See your claude code logs in clear details in your dashboard
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
KV cache store for distributed LLM inference
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A simple, fast and robust program-aware agentic inference system.
The batteries-included agent harness.
A Model Context Protocol server for searching and analyzing arXiv papers
CLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agents
The context API to search, scrape, and interact with the web at scale. 🔥