Skip to content
View akapug's full-sized avatar

Organizations

@importantmedia @discspace

Block or report akapug

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

A desktop GUI for CLIProxyAPI and a tool for automatically configuring popular AI agents.

TypeScript 3,644 334 Updated Nov 16, 2026

A desktop VM for agents: wrap's base image + XFCE, shared Chrome, agent-browser and agent-desktop. Containerfile + Smolfile.

Dockerfile 382 18 Updated Nov 4, 2026

NInfer with NVFP4 DSpine for RTX 5090 on Windows / Linux.

C++ 8 2 Updated Nov 12, 2026

Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21, DSpark + FLy verification and top_p 1.0: 463 tok/s single-stream agent decode at 30k-120k contex…

Python 62 11 Updated Nov 12, 2026

Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.

Python 58,445 7,638 Updated Nov 15, 2026

Check whether your self-hosted LLM performs as expected.

Python 11 2 Updated Nov 16, 2026

Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fabric.

Python 226 52 Updated Nov 16, 2026
Python 110 8 Updated Nov 9, 2026

LLM inference in C/C++

C++ 17 2 Updated Nov 8, 2026

A small, fast container runtime for macOS, Windows and Linux with free Ngrok alternative

Rust 7,803 344 Updated Nov 16, 2026

A simulator for LLM Inference prefix cache

C++ 77 10 Updated Nov 10, 2026
C++ 131 17 Updated Nov 16, 2026

Inter-session communication extension for pi coding agent

TypeScript 628 116 Updated Oct 29, 2026

Agent Skill for fine-tuning an agentic model on your own Claude Code sessions with Tinker. Works in Claude Code, Codex and OpenCode.

Python 324 39 Updated Nov 7, 2026

A brain that learns from live experience. System 1 by default: perception, memory, plasticity and action. Optional System 2 for self-observation and slow corrections.

Python 633 80 Updated Nov 16, 2026

Skills I use to execute long-running coding agents without breaking my back.

Python 137 12 Updated Oct 22, 2026

Fast, local, simple voice typing for macOS.

Swift 397 42 Updated Nov 16, 2026

Send data with sound

TypeScript 969 94 Updated Nov 9, 2026

LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint on Apple silicon Macs

Python 44 1 Updated Nov 4, 2026

SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding

Python 197 11 Updated Nov 3, 2026

extremely fast web remote desktop streaming

Rust 1,717 99 Updated Nov 14, 2026

Qwen3.5-2B with a filesystem compiled and inserted directly into its weights.

Python 96 11 Updated Nov 4, 2026

Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention

Python 467 60 Updated Nov 16, 2026

Tiny self-hostable URL shortener: one Rust binary, sharded-folder key/value store, API + web app + CLI. Runs hop.rip.

Rust 2 Updated Nov 14, 2026

An NES CPU compiled into the weights of a stock Qwen3.5 model

Python 295 10 Updated Oct 30, 2026

A local coding agent with a web UI that builds itself while it runs, on Pi Durable

TypeScript 572 97 Updated Nov 16, 2026

Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK

Jupyter Notebook 2,784 430 Updated Nov 13, 2026

A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the model picks one at a time until it can answer.

TypeScript 445 31 Updated Oct 30, 2026
Next