Projects Recently Starred by Experts

Starred 1 day ago by

Sebastian Raschka(Author of "Build a Large Language Model (From Scratch)"). Also starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research),

Jason Miller(Author of Preact), and

7 more.

qwen-code by QwenLM

0.2%

25k

AI coding agent for complex codebases

Understands and edits code beyond context window limits using enhanced parsers.
Automates operational tasks like pull requests and rebasing with workflow tools.
Optimized for Qwen3-Coder models, supporting multiple API configurations.
Features token usage management and compression for efficient interaction.

Created 11 months ago

Updated 8 hours ago

Starred 1 day ago by

Jeff Hammerbacher(Cofounder of Cloudera).

CodeWhale by Hmbown

0.7%

37k

Terminal coding agent leveraging DeepSeek models

Interactively manage code, files, and shell commands within your terminal using large context models.
Features 1M-token context, chain-of-thought streaming, and extensive tool integration for complex tasks.
Supports parallel analysis via RLM, workspace rollback, and configurable reasoning effort tiers.
Enables agentic workflows with sub-agents, custom skills, and an HTTP/SSE runtime API.

Created 4 months ago

Updated 10 hours ago

Starred 2 days ago by

Abubakar Abid(Cofounder of Gradio). Also starred by

Armin Ronacher(Author of Flask, Click, Jinja),

Alex Chen(Cofounder of Nexa AI),

Jane Manchun Wong(Security Researcher), and

30 more.

pi by earendil-works

1.0%

60k

AI agent framework and LLM deployment tools

Unified multi-provider LLM API and agent runtime with tool calling and state management.
Interactive coding agent CLI and terminal UI library with differential rendering.
CLI for managing vLLM deployments on GPU pods.
Web components for AI chat interfaces and a CORS proxy.

Created 10 months ago

Updated 18 hours ago

Starred 2 days ago by

Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML). Also starred by

Philipp Schmid(DevRel at Google DeepMind).

skills by NVIDIA

17.8%

AI agent skills for NVIDIA platforms

Enables agents to leverage CUDA-X libraries, AI Blueprints, and platform tools for diverse tasks.
Supports optimization, large-scale training, RAG, and real-time conversational AI via specialized skills.
Integrates GPU-accelerated data loading (DALI), LLM inference optimization (TensorRT-LLM), and quantum computing (CUDA-Q).
Features automated daily sync, security scanning, and a roadmap for skill signing and verifiable metadata.

Created 3 months ago

Updated 11 hours ago

Starred 2 days ago by

Didier Lopes(Founder of OpenBB).

nao by getnao

1.1%

Open-source analytics agent framework

Build and deploy AI agents for natural language data insights and analytics.
Data stack agnostic, supports self-hosting with LLM key security.
Features transparent reasoning, native data visualization, and agent reliability testing.
CLI for context building (data, metadata, docs) and agent performance evaluation.

Created 5 months ago

Updated 8 hours ago

Starred 3 days ago by

Maxime Labonne(Head of Post-Training at Liquid AI).

openmed by maziyarpanahi

4.9%

Production-ready medical NLP toolkit for structured clinical insights

Enterprise-grade entity extraction, assertion detection, and medical reasoning.
Deploys 12+ specialized transformer models for NER and HIPAA-compliant PII detection.
Offers Python API, interactive TUI, and CLI for flexible deployment and batch processing.
Features medical-aware tokenization and smart entity merging for enhanced accuracy.

Created 8 months ago

Updated 8 hours ago

Starred 3 days ago by

Didier Lopes(Founder of OpenBB). Also starred by

Jeff Hammerbacher(Cofounder of Cloudera).

Gym by NVIDIA-NeMo

1.1%

963

Library for building LLM RL training environments

Accelerates RL environment development for multi-step, multi-turn LLM interactions and user modeling scenarios.
Integrates with LLMs via APIs (OpenAI, vLLM) for scalable rollout collection and RLVR training.
Supports agentic workflows, tool calling, and LLM-as-a-judge for robust environment evaluation.
Offers diverse pre-built resource servers across domains like coding, math, and knowledge for immediate use.

Created 9 months ago

Updated 14 hours ago

Starred 3 days ago by

Didier Lopes(Founder of OpenBB). Also starred by

Georgios Konstantopoulos(CTO, General Partner at Paradigm),

Wei-Lin Chiang(Cofounder of LMArena),

Yineng Zhang(Inference Lead at SGLang; Research Scientist at Together AI), and

17 more.

SkyRL by NovaSky-AI

1.6%

RL training pipeline for multi-turn tool use LLMs, optimized for real-world tasks

Trains agents via reinforcement learning for long-horizon tasks.
Includes multi-turn RL training pipeline for Text-to-SQL.
Uses SGLang async rollout feature for optimization.
Supports SWE-Bench evaluation.

Created 1 year ago

Updated 17 hours ago

Starred 3 days ago by

Didier Lopes(Founder of OpenBB). Also starred by

Luis Capelo(Cofounder of Lightning AI),

Shizhe Diao(Author of LMFlow; Research Scientist at NVIDIA),

Vasek Mlejnsky(Cofounder of E2B), and

8 more.

OpenEnv by huggingface

10.9%

Framework for agentic RL training environments

Standardized Gymnasium-style APIs for creating and interacting with isolated RL execution environments.
Leverages Docker for containerized isolation and FastAPI for HTTP-based client-server communication.
Enables rich environment creation and deployment, supporting tools like PyTorch's torchforge.
Includes a web interface for interactive environment exploration and debugging.

Created 8 months ago

Updated 1 day ago

Starred 3 days ago by

Shizhe Diao(Author of LMFlow; Research Scientist at NVIDIA). Also starred by