llm
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Biomni: a general-purpose biomedical AI agent
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Dapr, Rancher Desktop, and Kuberne…
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Diagnostic Reasoning Knowledge Graph for Large Language Model Diagnosis Prediction
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Integrate the DeepSeek API into popular softwares
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Reference implementations of MLPerf® training benchmarks
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
No fortress, purely open ground. OpenManus is Coming.
Performance-optimized AI inference on your GPUs. Unlock superior throughput by selecting and tuning engines like vLLM or SGLang.
Fast and memory-efficient exact attention
Copilot Chat extension for VS Code
Chat2Graph: Graph Native Agentic System.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
General technology for enabling AI capabilities w/ LLMs and MLLMs
A research prototype of a human-centered web agent
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.