Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.

A new DSL and server for AI agents and multi-step tasks

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

AIConfig is a config-based framework to build generative AI applications.

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

Python SDK for running evaluations on LLM generated responses

An end-to-end LLM reference implementation providing a Q&A interface for Airflow and Astronomer

cluster/scheduler health monitoring for GPU jobs on k8s

Friendli: the fastest serving engine for generative AI

Miscellaneous codes and writings for MLOps

Streamlit-based chatbot leveraging Ollama via LangChain and PostHog-LLM for advanced logging and monitoring

The prompt engineering, prompt management, and prompt evaluation tool for TypeScript, JavaScript, and NodeJS.

Deploy an AI-powered chatbot for your repo in under 2 minutes.

[🚧🚧🚧WIP🚧🚧 🚧]Rework of webapp-conversation

YAML-based infrastructure manager for LLM providers and endpoints.

🚀 Python framework for orchestrating AI agents across 100+ LLM APIs (OpenAI, Claude, Gemini, Bedrock, etc.) with a unified interface. Build anything from simple chatbots to complex agent swarms!