This week's breakouts

npm @modelcontextprotocol/sdk↗

npm package

52 of 85 hourly runs in the top 10 · peak score 78 · best #7 · 5 days

Hugging Face RecursiveSI/flint↗

text-generation model on Hugging Face

33 of 85 hourly runs in the top 10 · peak score 98 · best #1 · 5 days

Hugging Face ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF↗

text-generation model on Hugging Face

32 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 3 days

GitHub lemomo-ai/lemo-opuscar↗

A toolbox of film styles made in code for Claude Code: 59 ready to use, and your own. Each style is a style prompt plus a demo film made…

24 of 85 hourly runs in the top 10 · peak score 96 · best #4 · 3 days

Hugging Face Nanbeige/Nanbeige4.3-33B↗

text-generation model on Hugging Face

22 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

Hugging Face MiniMaxAI/MiniMax-M3.1-Flash↗

image-text-to-text model on Hugging Face

20 of 85 hourly runs in the top 10 · peak score 96 · best #4 · 3 days

PyPI mcp↗

Python package

19 of 85 hourly runs in the top 10 · peak score 92 · best #5 · 3 days

Hugging Face deepseek-ai/DeepSeek-V4.1-Flash-1017↗

image-text-to-text model on Hugging Face

18 of 85 hourly runs in the top 10 · peak score 98 · best #2 · 6 days

Hacker News Show HN: Corgi, a helpful {agent, terminal} multiplexer↗

Hacker News story from corgi.computer, 42 comments

17 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

Hacker News No Signs of AI Payoff Outside the Tech Sector↗

Hacker News story from apollo.com, 393 comments

16 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

GitHub chenxiachan/textfold↗

Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text.

16 of 85 hourly runs in the top 10 · peak score 96 · best #3 · 3 days

GitHub miuuyy/Octopus-SI-OS↗

A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harness as a path toward…

16 of 85 hourly runs in the top 10 · peak score 96 · best #4 · 2 days

Hugging Face XHToken/Spark-X2.6-4B↗

text-generation model on Hugging Face

15 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 5 days

Hacker News A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis↗

Hacker News story from lynchlab.net, 262 comments

15 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

GitHub dagoSte/squadra↗

Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and…

15 of 85 hourly runs in the top 10 · peak score 96 · best #3 · 5 days

GitHub ctoldigital/axuse↗

Accessibility-first browser & computer use for AI agents — one MCP server for every harness (Codex, Claude Code, OpenCode, Antigravity).…

15 of 85 hourly runs in the top 10 · peak score 96 · best #3 · 4 days

npm @anthropic-ai/sdk↗

npm package

15 of 85 hourly runs in the top 10 · peak score 89 · best #6 · 5 days

Hacker News Every AI model has the same "controversial" take on humans↗

Hacker News story from modelcompare.ai, 64 comments

14 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 3 days

Hacker News Cerebras Deploys Trillion-Parameter AI Models↗

Hacker News story from cerebras.ai, 113 comments

13 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

Hugging Face orcarouter/DeepSeek-V4.1-Flash-1017-abliterated-GGUF↗

text-generation model on Hugging Face

12 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 1 day

Hugging Face black-forest-labs/flux-3-image-klein-comfy↗

image-to-image model on Hugging Face

12 of 85 hourly runs in the top 10 · peak score 95 · best #6 · 5 days

Hacker News LLMs are making formal software verification feasible at a much larger scale↗

Hacker News story from anthropic.com, 275 comments

11 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

Hacker News Neural chip decodes interactions between brain regions↗

Hacker News story from actu.epfl.ch, 26 comments

11 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 2 days

GitHub reacher-z/Awesome-REA↗

Awesome Reverse Engineering Anything: tools, projects, case studies and research papers for websites, games, apps, binaries, firmware and…

11 of 85 hourly runs in the top 10 · peak score 97 · best #2 · 4 days

Hacker News PaperPilot – Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP↗

Hacker News story from github.com, 73 comments

10 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 1 day

GitHub hevnsnt/CVEngine↗

AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP…

6 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 1 day

GitHub Patch-gg/trompe↗

Texture a whole game level from a gray blockout with image models: plan cameras, paint, project, bake. Real shadows, glTF out.

4 of 85 hourly runs in the top 10 · peak score 97 · best #3 · 1 day

Hacker News AI didn't cause the tech jobs bust, but it explains why there's no recovery↗

Hacker News story from vithushansylvester.com, 31 comments

3 of 85 hourly runs in the top 10 · peak score 94 · best #7 · 1 day

Hugging Face nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB↗

text-generation model on Hugging Face

2 of 85 hourly runs in the top 10 · peak score 96 · best #2 · 1 day

Hugging Face WarmBloodAban/Minimax-h3_Singularity↗

image-to-video model on Hugging Face

2 of 85 hourly runs in the top 10 · peak score 96 · best #5 · 1 day

Hacker News Brown student maps the hidden global labor powering AI↗

Hacker News story from brown.edu, 42 comments

1 of 85 hourly runs in the top 10 · peak score 99 · best #1 · 1 day