OpenJarvis
✨A local-first personal AI agent framework from Stanford that enables offline agent orchestration, skill import, and trace-driven continuous learning through five composable primitives, supporting 10+ inference backends and four interaction modes.
OtherLarge Language ModelsModel Context Protocol
vLLM-Omni
🧠A fully disaggregated multimodal model inference and serving framework that extends vLLM to support any-to-any modality unified inference and high-performance deployment.
Deep LearningMultimodalFastAPI
Harbor
🧠A Docker Compose-based CLI orchestrator for local LLM stacks — spin up pre-wired inference backends, frontend UIs, RAG, voice, image generation, and more with a single command
Model & Inference FrameworkMultimodalLarge Language Models
Nemo Skills
✨A full-stack LLM development toolkit from NVIDIA covering synthetic data generation, multi-backend inference, model training, and 11-category benchmark evaluation, scaling from single GPU to tens-of-thousands-GPU Slurm clusters.
Deep LearningAI AgentsModel Context Protocol
RLinf
✨Flexible and scalable reinforcement learning training infrastructure for embodied and agentic AI post-training, decoupling logical workflow composition from efficient physical execution via the M2Flow paradigm.
MultimodalAI AgentsReinforcement Learning
DataFlow
✨An all-in-one data preparation system for LLMs, supporting reproducible operator pipelines for data generation, cleaning, evaluation, and filtering.
Model & Inference FrameworkNatural Language ProcessingRAG
MLflow
✨The Open Source AI Engineering Platform for Agents, LLMs & Models, providing experiment tracking, model registry, LLM observability, evaluation, prompt optimization, and a unified AI gateway.
Model & Inference FrameworkSDKAI Agents
AWorld
✨An open-source framework for building, evaluating, and training general multi-agent systems. Features natural language agent creation, distributed reinforcement learning training pipeline, and complex environment interactions. Ranks top on authoritative benchmarks including GAIA, OSWorld, and VisualWebArena.
OtherMultimodalLarge Language Models
cascadeflow
✨Smart AI model cascading library using speculative execution to dynamically select optimal models, achieving 40-85% cost savings and 2-10x latency reduction.
SDKLarge Language ModelsAI Agents
AI Data Science Team
✨An AI-powered data science team of agents that automates data loading, cleaning, feature engineering, EDA, visualization, and machine learning modeling (H2O + MLflow) through specialized agent collaboration, featuring a Streamlit visual pipeline studio to perform common data science tasks 10X faster.
OtherMachine LearningMulti-Agent System