AI-кодинг и инструменты для разработчиков
paulduvall/ai-development-patterns
A comprehensive collection of AI development patterns for building software with AI assistance, organized by implementation maturity and development lifecycle phases. Includes Foundation, Development, and Operations patterns with practical examples and anti-patterns.
★ 638⑂ 53Python
MITQ82
Инференс, развёртывание и среда выполнения
theopenco/llmgateway
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
★ 1,6K⑂ 172TypeScript
NOASSERTIONQ98
AI-кодинг и инструменты для разработчиков
hotovo/aider-desk
Platform for AI-powered software engineers
★ 1,4K⑂ 128TypeScript
Apache-2.0Q88
Агенты и мультиагенты
elizaos/eliza
Open source agentic operating system
★ 19,1K⑂ 5,7KTypeScript
MITQ98
Агенты и мультиагенты
0xplaygrounds/rig
⚙️🦀 Build modular and scalable LLM Applications in Rust
★ 8,3K⑂ 937Rust
MITQ98
Инференс, развёртывание и среда выполнения
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
★ 32,2K⑂ 8,1KPython
Apache-2.0Q98
Дообучение, обучение и данные
kaito-project/aikit
🏗️ Fine-tune, build, and deploy open-source LLMs easily!
★ 535⑂ 57Go
MITQ94
MCP и вызов инструментов
berriai/litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
★ 56,8K⑂ 10,8KPython
NOASSERTIONQ98
Агенты и мультиагенты
wukongim/wukongim
More than just IM 不只是即时通讯(IM)
★ 4,9K⑂ 702Go
Лицензия не обнаруженаQ79
MCP и вызов инструментов
langgenius/dify
Dify is an LLM application development platform for visually building workflows, RAG pipelines, and tool-using agents. It combines model management, prompt development, observability, and application APIs in a collaborative workspace that can be used as a hosted service or self-hosted.
★ 151,2K⑂ 23,9KTypeScript
NOASSERTIONQ98
Инференс, развёртывание и среда выполнения
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 89,5K⑂ 21KPython
Apache-2.0Q98
AI Applications & Automation
oceanbase/oceanbase
The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.
★ 10,2K⑂ 1,9KC++
Apache-2.0Q88