Awesome AI AgentsLLM Framework Tools

tavily-ai/tavily-python

⭐ 1394 Python repository created 2023-09-01

Tavily Python is the official Python wrapper for the Tavily API, exposing the full range of search, extract, crawl, map, and research functionality directly from Python programs. It is aimed at developers building LLM-powered and retrieval-augmented generation applications that need current web data. The library centers on a TavilyClient, which can run in a keyless mode against the public Tavily API for the search and extract endpoints, or with an API key to unlock crawl, map, and research. The search method queries the web and returns structured results, with an exact_match option to constrain hits to quoted phrases; get_search_context produces a ready-to-use context string for RAG pipelines, and qna_search returns a concise answer suitable for feeding to an LLM. The extract method pulls raw content and images from up to twenty URLs at once, reporting any failures separately. Crawl traverses a website from a base URL with configurable depth and limits and accepts natural-language instructions to surface only relevant pages, while map discovers and visualizes a site structure. Keyless usage is rate-limited and raises a TavilyKeylessLimitError carrying structured fields such as retry_after_seconds when the cap is reached. The SDK is intended for teams that want smart search, fact-grounded context, and quick answers integrated into their applications without managing the underlying HTTP calls, and it mirrors the REST API so behavior stays consistent across interfaces.

https://github.com/tavily-ai/tavily-python

searchragweb-searchsdkpythonllm

Also in LLM Framework Tools

mudler/LocalAI

LocalAI is an open-source AI engine that enables running various AI models (LLMs, vision, voice, image, video) on any hardware, including CPU-only systems, with a composable and extensible architec...

langfuse/langfuse

Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features.

567-labs/instructor

Instructor is a popular Python library that simplifies working with structured outputs from large language models by providing validation, retries, and streaming support across multiple LLM providers.

TEN-framework/ten-framework

TEN Framework is a real-time, distributed, cloud-edge collaborative multimodal AI agent framework supporting multiple programming languages for building high-performance AI applications.

google/adk-samples

A collection of sample agents built with the Agent Development Kit (ADK) to accelerate development of conversational and multi-agent workflows, designed for customization and integration with Google Cloud services.

truefoundry/cognita

Cognita is an open-source, modular, and production-ready RAG framework by TrueFoundry that simplifies building, customizing, and deploying scalable Retrieval Augmented Generation applications with a no-code UI and extensive integration features.

lemony-ai/cascadeflow

In-process Python and TypeScript library that cascades model calls inside the agent loop, routing each query or tool call between small and flagship models by quality, cost, latency and budget.

shroominic/codeinterpreter-api

An open-source API that implements the ChatGPT Code Interpreter for sandboxed Python code execution, enabling data analysis, visualization, and interactive AI-driven computational tasks with local execution and scalable production deployment.