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
truefoundry/cognita
Cognita is an open-source Retrieval Augmented Generation (RAG) framework developed by TrueFoundry designed to build modular, scalable, and production-ready RAG applications. It addresses the challenges faced when transitioning RAG systems from experimental Jupyter notebooks to production environments by providing a structured, API-driven, and extensible codebase. Cognita leverages popular libraries like Langchain and LlamaIndex under the hood but enhances them by organizing RAG components into modular units that can be easily scaled and extended. The framework supports incremental indexing, allowing efficient batch processing and avoiding redundant re-indexing of documents. Cognita includes a user-friendly no-code UI for non-technical users to upload documents and perform question-answering tasks, making it accessible beyond developers. It supports multiple document retrievers using techniques such as similarity search, query decomposition, and document reranking, and integrates state-of-the-art open-source embeddings and reranking models from mixedbread-ai. The system supports LLMs through Ollama and offers a model gateway to manage model configurations centrally. Cognita also features its own metadata store powered by Prisma and PostgreSQL, enabling full UI-based management of collections, data sources, and indexing without code changes. Deployment is simplified with one-click local deployment using Docker Compose, and the framework supports scalable vector database deployment and hosting of LLM and embedding models as separate services. Additional features include audio and video parsers, multi-modal vision parsing with GPT-4, and integration with Infinity Server for embedding and reranking services. Cognita is designed to be fully API-driven, allowing easy integration with other systems and providing logging, metrics, and feedback mechanisms when used with TrueFoundry AI Gateway. Overall, Cognita is a comprehensive solution for building, customizing, and deploying RAG systems in production environments with ease and flexibility.
https://github.com/truefoundry/cognita
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.
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.