-
Oceans
- Bordeaux, France
- https://it-wars.com
Lists (6)
Sort Name ascending (A-Z)
Stars
- All languages
- ASL
- Assembly
- Batchfile
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- GLSL
- Go
- Go Template
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Lua
- MDX
- Makefile
- Markdown
- Mustache
- Nix
- Nushell
- PHP
- Perl
- PowerShell
- Python
- QML
- Red
- Roff
- Ruby
- Rust
- SCSS
- Sass
- ShaderLab
- Shell
- Starlark
- Svelte
- Swift
- TeX
- TypeScript
- V
- Vala
- Vim Script
- Vue
- YAML
- Zig
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.…
Local inference engine optimized for NVIDIA Blackwell
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic …
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.
/better rewrites your prompt with Felix Rieseberg's "Depth" prompt, using your real code and files, and puts it in your input box
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Strata.
AI-agent skill for reproducible, validated GIS analysis — from authoritative data discovery to interactive maps, on an open-first geospatial stack (OSM, Overture, STAC, DuckDB, PostGIS, QGIS, MapLi…
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
SquachWatch is a firmware for the Cheap Yellow Display that gamifies detecting things like Flock Cameras, Trackers, Meta Glasses and so much more!
A suite of WiFi/Bluetooth offensive and defensive tools for the ESP32
DIY parallel 2.4 GHz WiFi capture array (Hak5 WiFi Coconut style) from spare ESP32-C3/C5 boards: one channel per node, merged live into Wireshark. Passive, stdlib Python.
A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.
Lint, search, and install Agent Skills (SKILL.md) 📝 CLI + MCP server + Engine
Lightpanda: the headless browser designed for AI and automation
Get your documents ready for gen AI
Download videos from almost any website. Lightweight, self-hosted media downloader with a clean web UI.
Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
The Omarchy ISO with a rescue mode: rescue tools plus Claude Code, Codex, and OpenCode in a live console
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !