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
google/adk-samples
The google/adk-samples repository is a collection of sample agents built using the Agent Development Kit (ADK), designed to accelerate the development of conversational and multi-agent workflows. These sample agents serve as functional starting points for foundational agents tailored to common application scenarios and industries. Each sample agent comes pre-packaged with core logic, including the use of different tools, evaluation mechanisms, and human-in-the-loop features, making them practical for various use cases. However, these agents typically require customization to adjust specific responses or integrate with external systems to be fully operational. The repository provides detailed instructions for getting started, including prerequisites such as installing the ADK, setting up environment variables through .env files, and configuring Google Cloud projects to leverage services like Vertex AI and BigQuery. Users can clone the repository, explore the agents located in the agents/ directory, and run specific agents by following the setup instructions in each agent's README.md file. The agents have been built and tested primarily with Google models on Vertex AI but can also be tested with other models. The repository structure is organized with individual agent samples in separate directories, each containing its own README.md for specific instructions. The project encourages community contributions, including bug reports, feature requests, documentation improvements, and code contributions. This project is licensed under the Apache 2.0 License and is intended for demonstration purposes only, not for production use. It is not an officially supported Google product and is excluded from Google's Open Source Software Vulnerability Rewards Program. Overall, the google/adk-samples repository is a valuable resource for developers looking to build and customize intelligent agents using the ADK framework and Google Cloud services.
https://github.com/google/adk-samples
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.
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.