8000 KrE80r / Starred · GitHub
[go: up one dir, main page]

Skip to content
View KrE80r's full-sized avatar

Block or report KrE80r

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable cards.

Python 49 5 Updated Nov 21, 2026

A quantization compiler that delivers 12× lower KL than Q4_K_M at the same file size

Python 433 19 Updated Nov 22, 2026

Inkling 2 Mini on one RTX 3090: 128 tok/s, 344K context, images and tools. A Project Maya engine (maya-ik2) with every expert in VRAM.

Cuda 83 14 Updated Nov 22, 2026

97 tested hypotheses on making huge MoE LLMs fast on consumer GPUs (4x RTX 3090 + experts in RAM): what worked, what failed and why. A playbook for people and a ready skill for coding agents.

Python 69 12 Updated Nov 21, 2026

A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise ide…

Python 16,887 1,905 Updated Nov 22, 2026

A simple, lightweight PowerShell script that allows you to remove pre-installed apps, disable telemetry, as well as perform various other changes to declutter and customize your Windows experience.…

PowerShell 63,517 2,836 Updated Nov 15, 2026

My agent skills and harness setup for Claude Code, Codex and T3 Code

Python 2 Updated Nov 20, 2026

Autonomous penetration-testing agent (AGPL-3.0). Authorized targets only.

Go 4 Updated Nov 20, 2026

Burp Suite Professional

Rust 8 1 Updated Nov 17, 2026

AI 自主渗透测试平台 · 多智能体自主渗透测试(二次开发自 ARTEX)

Go 848 545 Updated Nov 17, 2026

Safely run your agents using any coding harness

Python 413 42 Updated Nov 18, 2026

Abliterates models quickly and efficently, Qwen2.5-7B: 95%→2% refusal at 0.095 KL

Python 48 9 Updated Nov 2, 2026

English and Traditional Chinese version of enhanced ARTEX

Go 59 96 Updated Nov 2, 2026

Reversible HTML and JavaScript prompt decoys with opaque per-insertion keys.

JavaScript 179 16 Updated Nov 2, 2026

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generat…

Python 4,362 559 Updated Nov 21, 2026

A native control plane for Claude Code, Codex, Cursor, Devin and other coding agents.

Rust 3,730 388 Updated Nov 22, 2026

One-menu RTX 5090 installer for fafstmobel with Cinference, DFlash2, K8V4, and vision.

Shell 55 2 Updated Oct 2, 2026

MUCH Improved version of the Python Chasing Your Tail Tool to help you determine if you're being followed

Python 2,540 451 Updated Nov 3, 2026

Accelerate high-latency GEO inflight Wi-Fi via warm BBR TCP multiplexing + 1-RTT Ground-TLS + zlib (zero dependencies)

Python 1,104 54 Updated Nov 7, 2026

Open-source AI-powered offensive security harness for automated penetration testing.

TypeScript 3,677 646 Updated Nov 21, 2026

An agent skill that keeps other skills lean and correct: a checklist for every edit, and a tested diet for bloated ones.

JavaScript 262 10 Updated Nov 6, 2026

Qwen3.8-Flash-Next on 2x RTX 3090: 150 tok/s on code, 262K context. Strata 0.2.10 + unsloth UD-IQ4_XS + DFlash2. Full recipe, refusal vectors, session patch, raw benchmark traces.

Python 10 1 Updated Nov 5, 2026

📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达

Python 14,899 2,164 Updated Nov 22, 2026

让你的命令行 Agent 在后台自己接活、自己跟进到底;平时不烦你,遇到拿不准的事才发卡片找你拍板。

TypeScript 6,255 1,160 Updated Nov 22, 2026

Towards a More Autonomous Agent System

TypeScript 24,204 3,012 Updated Nov 3, 2026

ARTEX - AI autonomous penetration testing system (English translation; upstream: Autumn-27/ARTEX, AGPL-3.0)

Go 15,667 5,960 Updated Nov 22, 2026

Easiest way to give your coding agents VMs - locally, remote, or cloud sandboxes

JavaScript 117 6 Updated Nov 15, 2026

ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.

Python 128 16 Updated Nov 18, 2026

A Claude skill that turns vibecoded, AI-looking UI into a designed interface

JavaScript 19,989 1,218 Updated Nov 15, 2026

A framework for few-shot evaluation of language models.

Python 14,519 3,824 Updated Nov 4, 2026
Next
0