Lists (1)
Stars
Convert Claude Code session logs into clean, readable markdown — with an interactive picker, terminal rendering, and GFM export.
L2M2 is a minimal Python library for asynchronous, multi-provider LLM inference.
A high performance authentication and access-control gateway for LLM API backends
Collect, review, and upload redacted pi session files to a Hugging Face dataset
A local-first microVM sandbox for running AI agents safely on macOS & Linux
DSLCad is a programming language & interpreter for building 3D models.
A workflow for reproducible and open scientific articles
Desktop app to manage markdown knowledge bases
Advanced DNS tunneling VPN for censorship bypass, optimized beyond DNSTT and SlipStream with low-overhead ARQ, resolver load balancing, high packet-loss stability and speed.
SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Pebble C-app to send app-messages and python side scripts to receive those on linux
An app to use ChatGPT on your Pebble Time or Pebble 2 watch
zamuz / QuickAuth4
Forked from JumpMaster/QuickAuthAuthenticator for the Pebble Smartwatch
A Very Precise Analog Watchface for Pebble Time
Enhanced SSH client with TUI — manage connections, keys, and sessions
Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.
A tool providing additional ECC protection for optical media (unofficial version)
AdaLLM is an NVFP4-first inference runtime for Ada Lovelace (RTX 4090) with FP8 KV cache and custom decode kernels. This repo targets NVFP4 weights and keeps the entire decode path in FP8