Search awesome repositories

An open source multi-tool for exploring and publishing data

Effing package management! Build packages for multiple platforms (deb, rpm, etc) with great ease and sanity.

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Kimi Code CLI is your next CLI agent.

Cross-platform lib for process and system monitoring in Python

LAVIS - A One-stop Library for Language-Vision Intelligence

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

QUANTAXIS 支持任务调度 分布式部署的 股票/期货/期权 数据/回测/模拟/交易/可视化/多账户 纯本地量化解决方案

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claude to generate and manage its own tools, continuously expanding its capabilities through conversation. Available both as a CLI and a modern web interface

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Give your agents the power of the Hugging Face ecosystem

NumPy aware dynamic Python compiler using LLVM

Linux/OSX/FreeBSD resource monitor

Point Cloud Library (PCL)

Multi-Agent Harness for Production AI

Spug is a lightweight agent-free automatic operation and maintenance platform designed for small and medium-sized enterprises. It integrates host management, host batch execution, host online terminal, file management, application release and deployment, pipelines, online task planning, configuration center, monitoring, alarm and so on.

🛡️ Open-source and cloud-native Web Application Firewall (WAF)

Python Serverless Microframework for AWS

Fast subdomains enumeration tool for penetration testers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

QLoRA: Efficient Finetuning of Quantized LLMs

Credentials recovery project

Python bindings for FFmpeg - with complex filtering support

利用 AI 大模型，一键解说并剪辑视频

Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.