Stars
Custom node to load models in INT8 for 1.5~2X Speed gains on 30 series cards.
Analyze what you type into AI tools — prompt scoring, agent error loops, leaked credential detection. CLI + MCP server for 9 AI tools.
Understanding the OpenZFS Codebase: A Guided Walkthrough for Engineers
A web-based ZFS on-disk structure explorer
A SillyTavern extension that adds a "Delete All But This Swipe" option to the message deletion prompt, allowing you to discard every unused swipe on a message in one action while keeping the one cu…
Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.
Specify a github or local repo, github pull request, arXiv or Sci-Hub paper, Youtube transcript or documentation URL on the web and scrape into a text file and clipboard for easier LLM ingestion
A reverse compression app. Instead of making files smaller, it makes them bigger. You can easily make a 10GB png out of a 25KB one.
To analyze whether modern open-source LLMs are well-calibrated, and how calibration varies across different task types such as reasoning, common sense, binary decision making, and factual truthfuln…
I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B improves logical deduction from 0.22→0.…
Faithful ComfyUI implementation of Spectrum for WAN, using Chebyshev-based spectral feature forecasting to reduce denoiser evaluations.
Faithful ComfyUI implementation of Spectrum for SDXL, using Chebyshev-based spectral feature forecasting to reduce denoiser evaluations.
Faithful ComfyUI implementation of Spectrum for FLUX, using Chebyshev-based spectral feature forecasting to reduce denoiser evaluations.
Mount PostgreSQL as a filesystem. Build apps with files, explore databases with ls and cat.
re!think it. System prompt teaching LLMs to execute two core tasks: complex answers without hallucinations, and creative ideas without clichés. Written in math-like logic, which LLMs parse better t…
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking
Context Gateway is an agentic proxy that enhances any AI agent workflow with instant history compaction and context optimization tools
Chrome extension that dynamically adjusts video playback speed based on how fast the speaker is talking
Single-file AI chat client with tool use, streaming, and conversation management
Reliable face detection, segmentation and enhancement for ComfyUI with custom-trained models that work across anime, realism, extreme poses and occlusion.
Ai safety research showing a working bypass to Google's synthid on Nano Banana Pro
See what your AI sees. Framework-agnostic LLM context window visualizer.
reverse engineering Gemini's SynthID detection