๊ฐ์ธ ๊ฐ๋ฐ์์ด์, ๋์์ AI Agent OS Lab์ด๋ผ๋ ๊ฐ๊ฐ์ผ๋ก ํ๋ก์ ํธ๋ฅผ ๋ง๋ค๊ณ ์์ต๋๋ค.
I build practical things around AI agents, MCP, research workflows, and developer tooling.
์ฝ๊ฒ ๋งํ๋ฉด,
- ์๋ก์ด AI workflow๋ฅผ ์คํํ๊ณ
- ์ธ๋งํ ๊ตฌ์กฐ๋ก ์ ๋ฆฌํ๊ณ
- ์ค์ ๋๊ตฌ์ ํ๋ก์ ํธ๋ก ๋ง๋๋ ์ฌ๋์ ๋๋ค
- AI Agents
- MCP tooling
- Research automation
- Agentic workflows
- Developer tools for the AI-native era
AI Agent OS Lab๋ ๊ฑฐ์ฐฝํ ๊ธฐ๊ด ์ด๋ฆ์ด๋ผ๊ธฐ๋ณด๋ค,
์ ๊ฐ AI agent systems, workflows, interfaces, and applied experiments๋ฅผ ๊ณ์ ์์๊ฐ๋ ์์
๊ณต๊ฐ์ ๊ฐ๊น์ต๋๋ค.
์ฌ๊ธฐ์๋ ๋ณดํต ์ด๋ฐ ๊ฑธ ํฉ๋๋ค:
- ideas โ prototypes
- prototypes โ usable tools
- tools โ repeatable workflows
๋ณต์กํ AI ํ๋ฆ์ ๊ทธ๋ฅ ์ ๊ธฐํ ๋ฐ๋ชจ๋ก ๋๋ด์ง ์๊ณ ,
people can actually use ํ๋ ํํ๋ก ๋ฐ๊พธ๋ ๋ฐ ๊ด์ฌ์ด ๋ง์ต๋๋ค.
-
clawfit
Agent + LLM + Hardware recommendation engine and evidence hub -
hello-mcp
Beginner-friendly MCP onboarding utility for real-world use -
plugin-for-claude-research
A structured research framework for Claude Code -
claude-agents-power-mcp-server
Project-specific role recommendation and agent setup via MCP
AI Agents AI Agent OS MCP Research Automation Agentic Workflows Developer Tooling Applied AI Experiments Builder
- AI Agent OS Lab
projects, experiments, direction, and the broader story behind what I'm building
Turning complex AI workflows into practical tools, usable systems, and lab-style experiments.
One of my recent contributions is improving OpenClaw Talk Mode for CJK languages and real-world voice use.
Related PRs:
- #53553 โ
fix(talk): Talk Mode TTS improvements for CJK languages(open) - #53511 โ
fix(talk): prevent double TTS playback when system voice times out(merged)
What this work focused on:
- better Talk Mode TTS behavior for CJK languages
- preventing double playback in edge cases
- making spoken interaction more stable and usable
- refining real-world voice UX instead of stopping at a demo