Skip to content
View lghupan's full-sized avatar
13 followers · 1 following

Achievements

Achievement: Pair Extraordinaire

Achievements

Achievement: Pair Extraordinaire

Block or report lghupan

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
lghupan/README.md

Hi, I'm Pan Hu 👋

I build infrastructure for AI coding agents.

Currently working on AgentProxy — a transparent token compression proxy that sits between your agent and the Anthropic/OpenAI API. It compresses tool results before they hit the context window, so your agent solves more problems and costs less to run.

  • +40% more problems solved on SWE-bench style tasks
  • −25% token cost on real coding workloads
  • Zero code changes — just prefix your command with agentproxy run
pip install agentproxy
agentproxy run claude

Projects
AgentProxy — Token compression proxy for LLM agents. +40% task success, −25% cost. cc-automode — Standalone re-implementation of Claude Code auto mode with Docker benchmark suite.
intro-to-agentic-security — An introduction to agentic AI security. CloudEval-YAML — Benchmarking LLMs for cloud config generation. ☁️

Tech

Python FastAPI Claude

AgentProxy stats

Stars Commits Top Language

Pinned Loading

  1. agentproxy agentproxy Public

    Python 3

  2. cc-automode cc-automode Public

    Standalone re-implementation of Claude Code auto mode (v2.1.81) with Docker benchmark suite

    JavaScript 3

  3. intro-to-agentic-security intro-to-agentic-security Public

    An introduction to agentic AI security.

    TeX 1

  4. alibaba/CloudEval-YAML alibaba/CloudEval-YAML Public

    ☁️ Benchmarking LLMs for Cloud Config Generation ｜ 云场景下的大模型基准测试

    Python 41 1