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
shroominic/codeinterpreter-api
The project "codeinterpreter-api" is an open-source implementation of the ChatGPT Code Interpreter, designed to facilitate sandboxed Python code execution using CodeBoxes as the backend. It integrates with LangChain and allows users to run everything locally except the large language model (LLM), which requires an OpenAI API key. The API supports various functionalities such as dataset analysis, stock charting, image manipulation, and more. It also features internet access and automatic Python package installation, enabling users to input text and files and receive text and files in response. The system maintains conversation memory to respond based on previous inputs, enhancing interactive sessions. The project is designed for both local experimentation and production deployment. For production, it leverages the CodeBox API to enable easy scaling. The installation process is straightforward, with options to install all dependencies for local experiments or a minimal set for deployment. Usage examples demonstrate how to configure the OpenAI API key, create sessions, generate responses, and handle file inputs asynchronously or synchronously. The documentation is comprehensive, providing detailed instructions and examples, including visual outputs like Bitcoin charts and dataset analysis plots. The project encourages community contributions, including feature suggestions, code refactoring, and bug reports. It also offers contact options via email, Twitter, and Discord for support and collaboration. Additionally, the project welcomes donations to support its development. Overall, this project provides a powerful and flexible API for executing Python code in a secure, sandboxed environment with the intelligence of ChatGPT, making it suitable for data analysis, visualization, and other computational tasks within conversational AI applications.
https://github.com/shroominic/codeinterpreter-api
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.
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.