Yacong Gu

llm-api-audit. Python

llm-idiosyncrasies. Code release for "Idiosyncrasies in Large Language Models"

arena-hard-auto. Arena-Hard-Auto: An automatic LLM benchmark.

arena-rank. Source Code of Arena Leaderboard Methodology

VulnGym. VulnGym: A Real-World, Project-Level Vulnerability Benchmark for White-Box Vulnerability-Hunting Agents

markitdown. Python tool for converting files and office documents to Markdown.

scientific-agent-skills. Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

3x-ui. Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun, MTProto)

clash-verge-rev. A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

jianying-editor-skill. Skill for Agent automating JianYing (CapCut Chinese version) video editing.

OpenHands. 🙌 OpenHands: AI-Driven Development

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

aaron-marketing-skills. 120 marketing skills + 8 commands for Claude Code & AI agents across 7 disciplines — SEO/GEO, influencer, paid ads, email, product launch, organic social & brand narrative — on one shared contract, with 8 auditor gates: CORE-EEAT · CITE · C³ · ROAS · SEND · RAMP · ECHO · TALE.

masrouter. Python

RouteLLM. A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

semantic-router. System level intelligent runtime for Mixture-of-Models across edge, data center and cloud

E2B. Open-source, secure environment with real-world tools for enterprise-grade agents.

learn-claude-code. Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

lighthouse. Ethereum consensus client in Rust

skills. Public repository for Agent Skills

KEYSENTINEL. a secret detection tool

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) in Python

presidio. An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

LiPSBOMaker. LiPSBOMaker is an SBOM generation tool for Linux distributions. It is a command-line tool that can generate multi-stage SBOMs for Linux packages, including the source stage, release stage, and runtime stage.

syft. CLI tool and library for generating a Software Bill of Materials from container images and filesystems

HSBRiskEvaluator. Python

Awesome-LLM4Security. This project aims to consolidate and share high-quality resources and tools across the cybersecurity domain.

zotero-style. Ethereal Style for Zotero

json_repair. Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

keyhacks. Keyhacks is a repository which shows quick ways in which API keys leaked by a bug bounty program can be checked to see if they're valid.

wg-securing-critical-projects. Helping allocate resources to secure the critical open source projects we all depend on.

PyAV. Pythonic bindings for FFmpeg's libraries.

Aegis. A free, secure and open source app for Android to manage your 2-step verification tokens.

K2-Vendor-Verifier. Verify Precision of all Kimi K2 API Vendor

LibreChat. Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active

Awesome-LLM-Fingerprinting. Paper list of LLM fingerprinting, based on our paper titled "SoK: Large Language Model Copyright Auditing via Fingerprinting".

pdf2image. A python module that wraps the pdftoppm utility to convert PDF to PIL Image object

G2FUZZ. C

G2FUZZ-DATA. Python

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

libjxl. JPEG XL image format reference implementation

ProphetFuzz. [CCS'24] An LLM-based, fully automated fuzzing tool for option combination testing.

CarpetFuzz. An NLP-based fuzzing assitance tool for generating valid option combinations.

FormatFuzzer. FormatFuzzer is a framework for high-efficiency, high-quality generation and parsing of binary inputs.

APIPark. Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.🦄云原生、超高性能 AI&API网关，LLM API 管理、分发系统、开放平台，支持所有AI API，不限于OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 请求和返回，API申请与审批，调用统计、负载均衡、多模型灾备。一键部署，开箱即用。

zotero-immersivetranslate. Zotero BabelDOC plugin, for Immersive Translate Pro members.

helm. Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

llm_benchmarks. A collection of benchmarks and datasets for evaluating LLM.

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

simple-evals. Python

system-prompts-and-models-of-ai-tools. FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

HowToCook. Programmer's guide about how to cook at home.

GPT_API_free. Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

uni-api. This is a project that unifies the management of LLM APIs. It can call multiple backend services through a unified API interface, convert them to the OpenAI format uniformly, and support load balancing. Currently supported backend services include: OpenAI, Anthropic, DeepBricks, OpenRouter, Gemini, Vertex, etc.

Gemini-API. ✨ Reverse-engineered Python API for Google Gemini web app

AIstudioProxyAPI. FastAPI + Playwright + Camoufox 中间层代理服务器，兼容OpenAI API且支持参数转发。项目通过浏览器自动化将API请求转发到 Google AI Studio Chat，并同样按照OpenAI标准格式返回的工具。内置调试WebUI面板。

chat2api. A service that can convert ChatGPT on the web to OpenAI API format.

free-sophnet-api. 逆向Sophnet平台得到模型api接口，兼容openai格式，工具调用

claude2api. 将Claude 的网页服务转为 Api 服务，支持识图，文件上传，思考输出……

jetbrainsai2api. Python

api-check. Pure Front-End API Testing Tool

mcp-installer. An MCP server that installs other MCP servers for you

servers. Model Context Protocol Servers

new-api. A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥

gateway. A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

tensorzero. TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

LLMmap. Python

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

ControlNet_Plus_Plus. [ECCV 2024] ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.

composer. Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

MiDaS. Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

openai-forward. 🚀 大语言模型高效转发服务 · An efficient forwarding service designed for LLMs. · OpenAI API Reverse Proxy

diff2html. Pretty diff to html javascript library (diff2html)

subgen. Autogenerate subtitles using OpenAI Whisper Model via Jellyfin, Plex, Emby, Tautulli, or Bazarr

LLPlayer. The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!

awesome-llm-supply-chain-security. A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)

llamafile. Distribute and run LLMs with a single file.

modelscope. ModelScope: bring the notion of Model-as-a-Service to life.

BCA-Phantom. A multi-platform HTTP(S) Reverse Shell Server and Client in Python 3

mem0. Universal memory layer for AI Agents

ACE_plus. Python

In-Context-LoRA. Official repository of In-Context LoRA for Diffusion Transformers

docker-drag. Download image from the Docker Hub HTTPS API

dive. A tool for exploring each layer in a docker image

re0-kubernetes-sec-archive. :atom: [WIP] 整理过去我和K8s、容器、虚拟化相关的分享 🧐

all-the-public-replicate-models. 📦 Metadata for all the public models on Replicate, bundled up into an npm package.

CDK. 📦 Make security testing of K8s, Docker, and Containerd easier.

revshell. A reverse shell Docker Image

java-diff-utils. Diff Utils library is an OpenSource library for performing the comparison / diff operations between texts or some kind of data: computing diffs, applying patches, generating unified diffs or parsing them, generating diff output for easy future displaying (like side-by-side view) and so on.

AI-Phone-Call. Python

BCR. A Basic Call Recorder for rooted Android devices

open-r1. Fully open reproduction of DeepSeek-R1

langfuse. 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

restic. Fast, secure, efficient backup program

dify. Production-ready platform for agentic workflow development.

awesome-open-mlops. The Fuzzy Labs guide to the universe of open source MLOps

awesome-production-machine-learning. A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

awesome-mlops. A curated list of references for MLOps