Skip to content
View PanQiWei's full-sized avatar
😃
😃
251 followers · 70 following
  • Shanghai

Achievements

Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: Pair Extraordinairex4Achievement: Starstruckx4Achievement: YOLO

Achievements

Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: Pair Extraordinairex4Achievement: Starstruckx4Achievement: YOLO

Block or report PanQiWei

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
PanQiWei/README.md

English · 简体中文

Qiwei Pan builds Agent Harness. His path drawn on two axes: model capability, and the direction orthogonal to it.

My path

Where I worked, and where my commits went each month: Gemsouls, Shanda, Kimi, Shanda.

My two axes

Do not fight a force you cannot control. Find the direction perpendicular to it, and do what it cannot.

If the model suddenly became ten times stronger on this dimension tomorrow, would what I am doing today become more valuable, or unnecessary?

Cross-scale rule invariance is the true generator of self-similarity.

From my book Advanced Agentic Dev Patterns: Orthogonality · Fractal

My agent workflow

An illustrative replay: a main session dispatches three agents into separate git worktrees, independent reviewers pass each change, and three pull requests merge.

Delivery runs as a map-reduce across agent sessions. The same five-step loop repeats at four scales. Contribution calendar for the last year, colored by the agent that produced most commits each day. Commits and merged pull requests per year.

My most-used skills

Share of skill loads across my Claude Code and Codex sessions.

My selected work

  • omne-harness-lite. A lightweight Agent Harness, built the way the charts above show.
  • AutoGPTQ. LLM quantization based on GPTQ. 5k+ stars, integrated into Hugging Face Transformers, now archived.

Pinned Loading

  1. AutoGPTQ/AutoGPTQ AutoGPTQ/AutoGPTQ Public archive

    An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

    Python 5.1k 547

  2. nemori-ai/omne-harness-lite nemori-ai/omne-harness-lite Public

    更轻量、更高性能的 OMNE harness 系统，以 Cordis 为内核

    TypeScript 5

  3. pqw-skills pqw-skills Public

    Agent skills for large changes: a define-then-deliver dev flow with handoff, slices and thinking models for Claude Code, Codex, Cursor, Kimi Code, DSH and other coding agents. 给 coding agent 的单会话研发…

    JavaScript 1