Skip to content
View prynix's full-sized avatar
🤪
🤪

Block or report prynix

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

Starred repositories

Showing results

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.

Rust 1,336 150 Updated Oct 24, 2026

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Python 151,672 14,574 Updated Nov 21, 2026

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Python 169,336 35,263 Updated Nov 22, 2026

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Python 85,588 12,072 Updated Nov 22, 2026

Deep Eye orchestrates multiple AI providers (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 45+ vulnerabi…

Python 2,377 424 Updated Oct 30, 2026

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Python 80,267 6,285 Updated Nov 22, 2026

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Rust 87,435 5,612 Updated Nov 21, 2026

Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization

Python 1,747 159 Updated Nov 16, 2026

Reimplementation of GTA:SA 1.0 US

C++ 1,328 290 Updated Nov 20, 2026

Open source reimplementation of GTA San Andreas game engine in Unity

C# 2,706 477 Updated Jun 16, 2023

Tool for automatic PS5 executables porting to Linux and Windows

C++ 59,751 5,809 Updated Nov 22, 2026

Modern coding harness, terminal UI and web-based

Rust 9 3 Updated Nov 20, 2026

The website QA tool for your coding agent. 350+ audit rules across SEO, performance, security, accessibility and agent experience.

TypeScript 323 38 Updated Nov 22, 2026

Run Claude Code, Codex, Copilot and other agent CLIs in parallel worktrees, then check what each one did before you merge.

TypeScript 1,102 153 Updated Nov 21, 2026
TypeScript 24 6 Updated Oct 15, 2026

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

TypeScript 18,697 1,540 Updated Nov 22, 2026

Automatic, model-driven permission review for OpenCode

TypeScript 43 16 Updated Nov 15, 2026

Dynamic context pruning plugin for OpenCode - intelligently manages conversation context to optimize token usage

TypeScript 4,513 284 Updated Nov 16, 2026

runs anywhere. uses anything

TypeScript 34,479 9,115 Updated Nov 21, 2026

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.

C++ 136 10 Updated Nov 21, 2026

GitHub (Primer) look-and-feel theme for Gitea 1.27.x and 28.x — light, dark, auto

CSS 15 3 Updated Nov 2, 2026

DirectStorage for Windows is an API that allows game developers to unlock the full potential of high speed NVMe drives for loading game assets.

C++ 914 113 Updated Nov 19, 2026

Your Pwnagotchi, Now on iOS

Python 52 7 Updated Nov 4, 2026

Repurpose Walmart Hanshow Stellar e-ink price tags with a Flipper Zero or Python. Requires ATC_TLSR_Paper firmware on the tags.

C 11 5 Updated Apr 15, 2026

A tool to unlobotomize your NVIDIA card!

Shell 942 286 Updated Oct 28, 2026

llama.cpp fork tuned for Qwen 3.8 Flash-Next on AMD Strix Halo — RDNA3.5 kernel patches, true QSA sparse gather, working MTP, 27 GB engram table on SSD. 23.5 → 39 tok/s.

C++ 51 3 Updated Oct 14, 2026

LLMs + Lean, on your laptop or in the cloud

Lean 224 33 Updated Nov 13, 2026

Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀

Rust 33,560 5,043 Updated Nov 22, 2026

Open WebUI Desktop 🌐

Svelte 3,233 302 Updated Nov 2, 2026

Qwen3.5-2B with a SIMT GPU inside its weights, 45 compiled layers in front of Qwen’s own, using its Gated DeltaNet layers as registers and memory.

Python 121 21 Updated Nov 1, 2026
Next