Projects Recently Starred by Experts

Starred 3 hours ago by

Li Jiang(Coauthor of AutoGen; Engineer at Microsoft). Also starred by

Gregor Zunic(Cofounder of Browser Use).

andrej-karpathy-skills by forrestchang

148.7%

61k

LLM code generation guidelines for enhanced reliability

Promotes explicit reasoning, simplicity, and surgical code changes.
Leverages "Goal-Driven Execution" for verifiable success criteria and LLM autonomy.
Mitigates LLM pitfalls: wrong assumptions, overcomplication, and unintended side effects.
Integrates via CLI tool or CLAUDE.md for improved AI coding assistants.

Created 2 months ago

Updated 2 days ago

Starred 12 hours ago by

Tobi Lutke(Cofounder of Shopify).

atomic by kenforthewin

4.1%

AI-powered personal knowledge graph from markdown notes

Stores notes as semantically linked atoms for vector search and RAG.
Enables agentic chat, LLM wiki synthesis, and spatial canvas exploration.
Core Rust logic with Tauri desktop, React UI, and pluggable AI providers.
Includes browser clipper, MCP server for AI tools, and native iOS app.

Created 4 months ago

Updated 1 day ago

Starred 12 hours ago by

Samuel Colvin(Founder and Author of Pydantic). Also starred by

Dan Guido(Cofounder of Trail of Bits).

stenoai by ruzin

2.9%

672

Local AI meeting summarization tool

Generates private meeting notes using on-device transcription and local LLMs.
Integrates Whisper AI for speech-to-text and Ollama for diverse summarization model selection.
Offers multiple LLM options (Llama3, Gemma, Qwen, Deepseek) for tailored summarization performance.
Desktop app prioritizes privacy with zero cloud reliance and no associated service fees.

Created 8 months ago

Updated 1 day ago

Starred 18 hours ago by

Wes McKinney(Author of Pandas). Also starred by

Jason Miller(Author of Preact).

maclocal-api by scouzi1966

1.6%

259

Local AI API and OCR for macOS

Run MLX and Apple Foundation Models locally via an OpenAI-compatible API.
Extract text from images and PDFs using integrated Apple Vision OCR capabilities.
Aggregate other local LLM backends like Ollama and LM Studio into a single API endpoint.
Built in Swift with Metal GPU acceleration for privacy-first, cloud-free AI processing.

Created 8 months ago

Updated 1 day ago

Starred 18 hours ago by

Johannes Schickling(Cofounder of Prisma). Also starred by

Junyang Lin(Core Maintainer at Alibaba Qwen),

Simon Willison(Coauthor of Django),

Luis Capelo(Cofounder of Lightning AI), and

5 more.

browser by lightpanda-io

1.2%

29k

Headless browser for AI/automation tasks, scraping, and LLM training

Ultra-low memory footprint, reportedly 9x less than Chrome.
Fast execution speed, claims 11x faster than Chrome.
Compatible with Playwright/Puppeteer via CDP.
Implements HTTP loader, HTML parser, JS (v8), basic DOM/Fetch APIs.

Created 3 years ago

Updated 1 day ago

Starred 1 day ago by

Dan Guido(Cofounder of Trail of Bits). Also starred by

Elvis Saravia(Founder of DAIR.AI).

CLI-Anything by HKUDS

4.2%

32k

Agent-native CLI generation for any software

Automates CLI creation for any application, enabling AI agents to control them directly.
Generates structured JSON output and interactive REPLs via a 7-phase pipeline.
Integrates directly with software backends, validated by 1,400+ production tests.
Transforms software into agent-controllable tools without APIs or UI automation.

Created 1 month ago

Updated 1 day ago

Starred 1 day ago by

Elvis Saravia(Founder of DAIR.AI). Also starred by

Thomas Dohmke(Former CEO of GitHub),

Dan Guido(Cofounder of Trail of Bits), and

Travis Fischer(Founder of Agentic).

summarize by steipete

0.9%

Summarize diverse content from any URL or file

CLI tool for extracting and summarizing articles, web pages, and documents (PDFs, text).
Transcribes audio/video and summarizes podcasts, YouTube, and local media files using Whisper.
Supports multiple LLM providers (OpenAI, Gemini, Anthropic) and offers a Chrome extension.
Features streaming output, Firecrawl fallback for web scraping, and multimodal input handling.

Created 4 months ago

Updated 4 days ago

Starred 2 days ago by

Piero Molino(Cofounder of Predibase).

lucebox-hub by Luce-Org

48.2%

281

Optimized LLM inference for specific hardware

Hand-tuned CUDA kernels and fused passes for maximum throughput and energy efficiency (tok/J).
Implements advanced techniques like speculative decoding (DFlash) and hybrid Attention/DeltaNet architectures.
Tailored software stack for consumer GPUs, enabling large context windows and high token generation rates.
Achieves state-of-the-art performance per watt by rewriting software for specific silicon.

Created 2 weeks ago

Updated 1 day ago

Starred 2 days ago by

Pietro Schirano(Founder of MagicPath). Also starred by

Victor Taelin(Author of Bend, Kind, HVM).

rvllm by m0at

44.7%

612

High-performance LLM inference engine in Rust

Drop-in replacement for vLLM, offering dramatically improved resource efficiency and faster startup times.
Leverages Rust's performance, JIT-compiled fused CUDA kernels, and FP8 inference for optimized throughput and reduced memory footprint.
Features advanced attention mechanisms (FA3 v3), CUDA graph replay, and cuBLAS autotuning for low-latency, high-concurrency serving.
Achieves a 31x smaller binary size and 20x faster cold starts compared to Python-based alternatives.

Created 3 weeks ago

Updated 1 day ago

Starred 2 days ago by

Kevin Hou(Head of Product Engineering at Windsurf). Also starred by

Chuan Li(Chief Scientific Officer at Lambda),

Enes Akar(Cofounder of Upstash),

Shyamal Anadkat(Research Scientist at OpenAI), and

13 more.

gstack by garrytan

8.4%

77k

Specialized AI coding assistant framework

Transforms generic AI into a team of specialized agents for planning, review, shipping, and QA.
Leverages browser automation and structured reporting for end-to-end QA and live URL inspection.
Enables parallel agent sessions and context-aware mode switching for complex software development workflows.
Integrates cookie import for authenticated testing and generates data-driven engineering retrospectives.

Created 1 month ago

Updated 1 day ago

...