Agent systems, developer tools, and public experiments.

Agent Arena — 让 Agent 在真实任务中比赛、被裁判审查、留下证据、积累声誉的智能体竞技场。Real-task evaluation harness for LLM agents with judge review and reputation.

• TypeScript
• CSS
• HTML
• +3

AI-native software engineering harness — 18 agents, 9 workflows, one closed loop: Issue → Worktree → Plan → Build → Review → Evidence → Merge → Memory.

• Shell
• HTML
• JavaScript
• +3

A low-token visual evidence compiler for text-only coding agents. Convert images into compact Visual Evidence Packets (VEP) for DeepSeek, Codex, Claude Code, and other text-only models.

• TypeScript
• JavaScript
• Shell
• +3

Autonomous multi-agent economic sandbox — A2A protocol agents compete, trade, and govern inside a simulated economy with a God's Eye observability dashboard.

• Python
• Go
• TypeScript
• +3

Personal second-brain dashboard — Obsidian vault sync, knowledge graph, daily notes, and task tracking in one local-first UI.

• JavaScript
• CSS
• Rust
• +3

多模态人体状态感知 → 中医体质分析 → 智能按摩方案推荐 | OPLRI + TCM + EEG pretrained models · Gradio demo

• Python
• HTML
• TeX
• +3

AMD Hackathon contribution: an AI-native live-event poster engine that combines music rhythm, stage lighting, and real-time visual composition.

• TypeScript
• Multimodal
• Image Generation
• +2

An interactive Chinese source-code guide to LLM inference: 13 browser experiments make continuous batching, KV cache, paged attention and scheduling visible.

• JavaScript
• Shell
• Python
• +3

A personal trading operations dashboard that brings market data, positions, backtests and execution checks into one TypeScript workspace.

• TypeScript
• CSS
• JavaScript
• +3

An image-to-collectible skill that turns a supplied subject into a faithful, commercially believable packaged object.

On-chain agent intent verification for a Monad hackathon: deterministic evidence checks followed by a fail-closed human signing gate.

• TypeScript
• CSS
• Solidity
• +1