Projects Recently Starred by Experts

Starred 3 hours ago by

Wes McKinney(Author of Pandas).

GitNexus by abhigyanpatwari

6.2%

22k

Browser-based code intelligence engine

Client-side code analysis engine builds interactive knowledge graphs for deep code understanding.
Full WASM stack: Tree-sitter parsing, KuzuDB graph/vector DB, and local embeddings run in-browser.
Hybrid search (BM25, semantic, graph expansion) powers a Graph RAG agent with grounded citations.
Zero-server architecture ensures code privacy and zero deployment cost.

Created 8 months ago

Updated 1 day ago

Starred 6 hours ago by

Travis Fischer(Founder of Agentic). Also starred by

Wing Lian(Founder of Axolotl AI) and

Magnus Müller(Cofounder of Browser Use).

autoagent by kevinrgu

N/A

Autonomous agent harness engineering framework

AI agents autonomously iterate and optimize their own configuration, tools, and orchestration.
Meta-agent hill-climbs performance scores on tasks, improving harnesses overnight.
Single-file harness design and Docker isolation for robust agent development.
Human guidance via Markdown (program.md); integrates with Harbor for evaluation.

Created 2 days ago

Updated 1 day ago

Starred 6 hours ago by

Travis Fischer(Founder of Agentic). Also starred by

Junyang Lin(Core Maintainer at Alibaba Qwen),

Elvis Saravia(Founder of DAIR.AI), and

Didier Lopes(Founder of OpenBB).

oh-my-codex by Yeachan-Heo

456.6%

15k

Multi-agent orchestration for OpenAI Codex CLI

Enhances Codex CLI with role-based agents, workflow skills, and team orchestration.
Manages complex tasks via staged execution, persistent state, and memory.
Extends functionality with a plugin-based hook system for additive automation.
Provides structured decomposition, lifecycle management, and operational controls for Codex.

Created 2 months ago

Updated 14 hours ago

Starred 6 hours ago by

Travis Fischer(Founder of Agentic). Also starred by

Li Jiang(Coauthor of AutoGen; Engineer at Microsoft),

Dan Guido(Cofounder of Trail of Bits),

Didier Lopes(Founder of OpenBB), and

6 more.

claw-code by ultraworkers

N/A

167k

Agent harness engineering framework

Python rewrite of Claude Code's agent harness for tool orchestration and task management.
AI-orchestrated development using oh-my-codex (OmX) and Codex for workflow automation.
Focuses on harness engineering, agent systems, and runtime context management.
Future Rust port targets enhanced speed and memory safety.

Created 5 days ago

Updated 15 hours ago

Starred 6 hours ago by

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

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

Michael Han(Cofounder of Unsloth),

Will Brown(Research Lead at Prime Intellect), and

17 more.

llm-course by mlabonne

0.4%

78k

LLM course with roadmaps and notebooks

LLM Fundamentals: math, Python, neural networks, NLP.
LLM Scientist: pre-training, fine-tuning, preference alignment, quantization.
LLM Engineer: RAG, agents, inference optimization, deployment, security.
Notebooks for auto-eval, lazy mergekit, quantization, fine-tuning.

Created 2 years ago

Updated 1 month ago

Starred 13 hours ago by

Shawn Wang(Editor of Latent Space). Also starred by

Rodrigo Nader(Cofounder of Langflow),

Didier Lopes(Founder of OpenBB),

Bryan Helmig(Cofounder of Zapier), and

22 more.

autoresearch by karpathy

8.9%

66k

Autonomous LLM research agent for single-GPU training

Automates LLM pretraining experiments by iteratively modifying and training models.
Leverages PyTorch for GPT model training with a fixed time budget and BPB metric.
Agent-driven code modification and hyperparameter tuning for efficient research exploration.
Enables overnight AI-driven research, waking to improved models and experiment logs.

Created 4 weeks ago

Updated 1 week ago

Starred 13 hours ago by

Abhishek Thakur(World's First 4x Kaggle GrandMaster). Also starred by

Tim J. Baek(Founder of Open WebUI),

Luis Capelo(Cofounder of Lightning AI),

Travis Fischer(Founder of Agentic), and

4 more.

pyannote-audio by pyannote

1.5%

10k

Speaker diarization toolkit

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, and speaker embedding.
State-of-the-art pretrained models and pipelines available on Hugging Face Hub.
Fine-tune models with PyTorch for improved performance on custom data.
Achieved 1st place in multiple speaker diarization challenges.

Created 10 years ago

Updated 3 days ago

Starred 13 hours ago by

Carl Lerche(Author of Tokio).

awesome-design-md by VoltAgent

N/A

AI agents build UIs from markdown design systems

Enables AI agents to construct pixel-perfect interfaces by interpreting plain-text DESIGN.md files.
Offers curated markdown-based design systems from popular websites for consistent visual output.
Utilizes markdown as a universal, LLM-readable format for capturing visual themes, typography, and components.
Facilitates rapid UI prototyping and development by translating design principles into actionable agent prompts.

Created 5 days ago

Updated 2 days ago

Starred 17 hours ago by

Deshraj Yadav(Cofounder of Mem0). Also starred by

Joe Walnes(Head of Experimental Projects at Stripe),

Lysandre Debut(Chief Open-Source Officer at Hugging Face),

Abubakar Abid(Cofounder of Gradio), and

9 more.

hermes-agent by NousResearch

50.3%

24k

Autonomous AI agent for persistent learning and task automation

Integrates across messaging platforms (Telegram, Discord, Slack, WhatsApp) with scheduled automations.
Supports diverse LLM providers, voice transcription/synthesis, and web browsing tools.
Offers robust sandboxing (Docker, SSH, Modal) and a skill-based knowledge system.
Research-ready for parallel batch processing and reinforcement learning model training.

Created 8 months ago

Updated 10 hours ago

Starred 17 hours ago by

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

humanize by humania-org

19.8%

377

Iterative AI code development and review framework

Enables LLM-driven code generation with independent AI review cycles for robust development.
Leverages Claude for implementation and Codex for code quality assessment and feedback.
Implements RLCR (Ralph-Loop with Codex Review) for continuous refinement and issue resolution.
Supports parallel agent teams in Swarm Mode for accelerated iterative development.

Created 2 months ago

Updated 1 week ago

...