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
dreadnode/rigging
Rigging is a lightweight and flexible framework designed to facilitate interaction with large language models (LLMs) in production environments. It aims to simplify the integration and usage of LLMs by providing a structured and efficient interface that supports both unstructured text and structured data through Pydantic models. The framework offers instant access to a wide variety of language models via LiteLLM as the default generator, and it supports models from other providers such as vLLM and Hugging Face transformers. Rigging allows developers to define prompts as Python functions with type hints and docstrings, enhancing code clarity and maintainability. It supports tool usage even for models that do not natively support them at the API level, and it manages different models and configurations using simple connection strings similar to database connections. The framework includes integrated tracing support with Logfire, enabling detailed tracking and debugging of model interactions. Additional features include chat templating, prompt forking, continuations, generation parameter overloads, segment stripping, asynchronous batching, and fast iteration capabilities for large-scale generation tasks. Rigging also supports metadata handling, callbacks, and data format conversions, all built with modern Python features such as async support, type hints, and Pydantic validation and serialization. The project is actively maintained and used daily by its creator, dreadnode. It is easy to install via PyPI and offers comprehensive documentation and examples to help users get started quickly. Rigging is suitable for developers looking to build robust, scalable, and maintainable applications leveraging the power of LLMs with a clean and flexible API.
https://github.com/dreadnode/rigging
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.
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.