Open source · Thoughts · Services

Turn ideas into products, turn experience into writing

I'm One PC, an independent developer. Here you'll find my open source projects, daily thoughts, and ready-to-use services — email, AI, and more. Feel free to explore and reach out.

AstroAI / LLMInfrastructureIndie dev

Featured projects

Open source projects I maintain, mostly around AI and developer productivity.

All projects
TypeScript

Anpai.Life

AI-powered cross-platform task management

A task + calendar + AI planning productivity app with PC/mobile sync, natural-language task creation, and smart scheduling.

ProductivityCross-platformAI
Shell12

OPC Skills

BiuBiuHu / One PC Codex skill template for OPC delivery

BiuBiuHu's Codex skill template for OPC / C-end and B-end delivery (github.com/BiuBiuHu/opc-skills) — not ReScienceLab / opc.dev. It chains requirement clarification, product design, B-side ops pages, architecture governance, development, testing, integration, and release gates into one reusable workflow — so agents keep making correct calls in complex business contexts.

SkillDelivery PipelineAgent
TypeScript

AI Gateway

Unified multi-model gateway

Connect multiple LLMs in one place, centralizing keys, rate limiting, logging, and cost governance so the business side only cares about calling.

AIGatewayLLM

Latest posts

Thoughts on AI development, indie dev, and engineering.

All posts
10-26-2026

What Anpai Calendar Actually Does: Month/Week/Day, Goals, Review, Agent

Anpai.Life is a personal rhythm system: month/week/day calendar, a daily AI image-calendar poster, yearly goals and milestones, weekly review + AI insights, and an Agent that schedules and breaks down goals — synced across PC and phone. TickTick free is a fair hook; this post still stands if you never used TickTick.

10-23-2026

A2A — Agent-to-Agent Protocol

A2A lets agents in different processes, orgs, and vendors collaborate via a task state machine. This post covers Agent Cards, the four-step flow, and a runnable TypeScript sample.

10-23-2026

RAG — Retrieval-Augmented Generation

RAG lets an agent answer questions from a private knowledge base. This post covers chunking, embeddings, vector stores, hybrid BM25+vector+RRF, rerank, OpenSearch, and ACL / Permissions Collapse.

Services

Use these capabilities directly, or ask for something custom.

All services

Mail Service

Ready-to-use email sending — verification codes, notifications, and marketing in one place, with deliverability tracking and template management.

Learn more

AI Service

A unified multi-model gateway with agent capabilities — connect once to call every major model, with rate limiting, logging, and cost governance built in.

Learn more

Friends

A few independent sites I also read.