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...
Awesome AI Agents › LLM Framework Tools
567-labs/instructor
Instructor is a widely used Python library designed to facilitate working with structured outputs from large language models (LLMs). It is built on top of Pydantic, which allows users to define clear and precise data models for the expected output from LLMs, ensuring that the responses conform to specified formats. The library supports validation, retries, and streaming responses, making it a robust tool for managing interactions with LLMs. It integrates seamlessly with various LLM providers including OpenAI, Anthropic, Cohere, and Google's Gemini models, providing flexibility and broad compatibility. Instructor also supports multiple programming languages such as Python, TypeScript, Ruby, Go, and Elixir, making it accessible to a wide range of developers. Key features of Instructor include the ability to specify response models using Pydantic, manage retry attempts for requests, validate LLM responses, and handle streaming data efficiently. The library also offers a hooks system that allows developers to intercept and log different stages of the LLM interaction process, which is useful for debugging and monitoring. Installation is straightforward via pip, and the library provides simple APIs to define output structures and extract structured data from natural language inputs. Instructor is popular in the AI and machine learning community, with over one million monthly downloads, reflecting its utility and reliability. It is designed to enhance LLM workflows by providing a transparent and user-friendly interface for structured data extraction and validation. The library's support for multiple backends and languages, combined with its robust feature set, makes it a valuable tool for developers working with LLMs in various applications, from data extraction to AI-driven automation.
https://github.com/567-labs/instructor
Also in LLM Framework Tools
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.
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.
agentscope-ai/ReMe
Local-first memory layer for AI agents that converts conversations and resources into readable markdown memory nodes and retrieves them through a hybrid of wikilinks, BM25 and embeddings.