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
MCP и вызов инструментов
agentscope-ai/agentscope
A production-ready, easy-to-use agent framework designed to leverage the reasoning and tool-use abilities of increasingly agentic LLMs without constraining them with strict prompts or opinionated orchestrations.
★ 28,6K⑂ 3,3KPython
Apache-2.0Q98
RAG и системы знаний
lancedb/lancedb
An open-source, developer-friendly embedded retrieval library and multimodal AI lakehouse designed for fast, scalable, and production-ready vector search, built on the Lance columnar format.
★ 11,1K⑂ 994Rust
Apache-2.0Q98
Агенты и мультиагенты
0xplaygrounds/rig
⚙️🦀 Build modular and scalable LLM Applications in Rust
★ 8,3K⑂ 937Rust
MITQ98
Агенты и мультиагенты
sno-ai/llmix
A production LLM call layer for AI agents and tools that wraps existing provider SDKs with config-driven model presets, caching, resilience patterns, and key rotation across Python, TypeScript, and Rust.
★ 131⑂ 28Python
Apache-2.0Q91
AI-кодинг и инструменты для разработчиков
rtk-ai/rtk
A CLI proxy that compresses command output to reduce context usage in AI coding workflows.
★ 78,6K⑂ 5KRust
Apache-2.0Q90
RAG и системы знаний
infino-ai/infino
Infino is a fast retrieval engine that executes SQL, full-text search, and vector search over a single copy of data stored natively as Parquet on object storage.
★ 67⑂ 18Rust
Apache-2.0Q89
Агенты и мультиагенты
0xlazai/alith
A simple, composable, and high-performance AI agent framework designed for Web3 and Crypto, enabling developers to build, deploy, and manage on-chain AI agents with multi-language support and LazAI Gateway integration.
★ 44⑂ 31Rust
Apache-2.0Q88
AI-кодинг и инструменты для разработчиков
openai/codex
Lightweight coding agent that runs in your terminal
★ 107,1K⑂ 16,3KRust
Apache-2.0Q86
Инференс, развёртывание и среда выполнения
openai/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
★ 19K⑂ 1,6KRust
MITQ86