Sanbu 散步

Sanbu 散步

Think Different, Building @walkinglabs

GitHub 285 repos 1.1k followers

Explained projects

The Autopsy of a Frontier Agent: Inside learn-coding-agent
The Autopsy of a Frontier Agent: Inside learn-coding-agent
How a massive reverse-engineering project exposed the telemetry pipelines, remote killswitches, and secret employee-only modes hidden inside Anthropic's CLI architecture.
8 min read · Apr 2, 2026
 learn-coding-agent: The 512,000-Line X-Ray: Inside sanbuphy/claude-code-source-code
learn-coding-agent: The 512,000-Line X-Ray: Inside sanbuphy/claude-code-source-code
How a simple packaging error gave the open-source world an unfiltered look at the architecture, killswitches, and undercover operations of Anthropic's terminal-native agent.
8 min read · Apr 1, 2026

Yet to be explained

nanoMCP
If you can read ~200 lines of Python, you understand MCP.
Python76 stars
Explain
nanoSkills
If you can read ~100 lines of Python, you understand Skills.
Python21 stars
Explain
nanoMemory
If you can read ~200 lines of Python, you understand agent memory.
Python18 stars
Explain
iluvatar-quick-start
天数智芯 GPGPU 常见环境配置、信息收集
4 stars
Explain
LLM2IBDeck
AI tool to generate standard investment banking editable PPT outputs.
Python2 stars
Explain
relationship-compass-macos
Local-first macOS CRM built through a spec-to-tickets agent workflow
Swift0 stars
Explain