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
farizrahman4u/loopgpt
LoopGPT is a modular and extensible Auto-GPT framework designed to provide a more flexible and Pythonic approach to building AI agents. It is a re-implementation of the popular Auto-GPT project, focusing on modularity, extensibility, and ease of use. Unlike traditional command-line tools, LoopGPT offers a "plug and play" API that allows developers to add new features, integrations, and custom agent capabilities directly through Python code without relying on complex configuration files. The framework is optimized for GPT-3.5, making it accessible to users who do not have access to GPT-4, while still supporting GPT-4 for those who do. It emphasizes minimal prompt overhead to maximize efficiency and reduce token usage, which is crucial for cost-effective AI interactions. LoopGPT also supports a "Human in the Loop" feature, enabling users to provide feedback and course correct agents that deviate from desired behaviors. One of the standout features of LoopGPT is its full state serialization capability, allowing agents to save their complete state, including memory and tool states, to a file or Python object. This means users can pause and resume agent operations seamlessly without needing external databases or vector stores, although such integrations are supported if desired. Installation is straightforward via PyPI or directly from the source, with options for development versions and Docker support. Users can create and configure agents with specific names, descriptions, and goals, and run them interactively through a command-line interface or in continuous mode for autonomous operation. LoopGPT also supports custom tool creation, enabling developers to extend agent functionality by defining new tools with simple Python classes. This flexibility allows for tailored AI assistants, such as a WeatherGPT example that fetches weather data and provides dressing tips. Overall, LoopGPT is a powerful, user-friendly framework for building customizable AI agents with modular components, efficient token usage, and robust state management, suitable for both casual users and developers looking to create advanced AI applications.
https://github.com/farizrahman4u/loopgpt
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.