Whamp/pi-extensions
Will Hampson's Pi coding agent extensions: pstack, quiet, and personal packages
Motorcycles. Dogs. Bonds. Autodidact. http://course.fast.ai alum
Repositories
Whamp/chirp-stt
Whamp/pi-subagents
Pi extension for async subagent delegation with truncation, artifacts, and session sharing
Whamp/pi-cliff
Pi extension for CliffCompaction mechanical context summaries
Whamp/skills
Public agent skills authored and maintained by Will Hampson.
Whamp/pi-observational-memory
Make Pi sessions feel endless
Whamp/cliffcompaction
CliffCompaction — autocompaction for long-horizon coding agents
Whamp/pi-token-burden
Whamp/pi-skill-toggle
Enable/disable skills from loading into pi context at startup
Whamp/herdr-web
Web-based client for https://herdr.dev/ terminal session manager
Whamp/GVS5H
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
Whamp/pi-rlm
RLM (Recursive Language Model) extension for pi - process large context files that exceed LLM context windows
Whamp/deep-swe-bench
Pi harness for DeepSWE benchmark experiments
Whamp/pi-btw
Whamp/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Whamp/TurboAgent
Whamp/napkin
🧻 Knowledge system for agents. Local-first, file-based, progressively disclosed.
Whamp/omarchy
Beautiful, Modern & Opinionated Linux
Whamp/club-3090
Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.
Whamp/pi-read-map
Whamp/forks-flash-mla-int
Ampere DeepSeek V4 FlashMLA fork
Whamp/pi-sub
Whamp/pi-brain
Whamp/eleusis-llm-benchmark
Benchmarking Large Language Models using the Eleusis card game
Whamp/auto-round
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
Whamp/compressed-tensors
A safetensors extension to efficiently store sparse quantized tensors on disk
Whamp/llm-compressor
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Whamp/plannotator
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
Whamp/modelscan
Whamp/swarm-forge
A simple tool for coordinating several AI agents.