AI Infra2025
Extends RAG beyond text: parses PDFs and Office files containing images, tables, equations, and charts, then queries them through one multimodal knowledge graph. Built on LightRAG, it replaces separate parsing and retrieval tools.
AI Infra2025
Reimplements the vLLM inference engine from scratch in ~1,200 lines of readable Python, matching its offline throughput on small models. Prefix caching, tensor parallelism, torch.compile, and CUDA graphs are all kept legible.
AI Dataset2025
1,000,000 US-focused synthetic persona records (6M persona texts) grounded to demographic, geographic and personality distributions. Contains age, sex, education, occupation and ZCTA/city fields; CC BY 4.0 license for LLM training, diversity augmentation, and bias mitigation.
A code-first collection of runnable tutorials for building production-ready generative-AI agents — step-by-step guides covering stateful workflows, vector memory, RAG, tool integrations, Docker/AWS/RunPod deployment, security guardrails, observability, and multi-agent patterns.
AI Client2025
Provides a terminal REPL that gives AI coding agents a persistent, structured context memory (a versionable context tree) which can be synced across machines. Distinguishes itself with local-first TUI workflows, Git-like versioning for knowledge, and broad multi-LLM and agent tool integrations; source-available under Elastic License 2.0.
AI Infra2025
Offline-first knowledge server that bundles local AI chat (Ollama + vector RAG), offline Wikipedia/education/maps, and utility tools behind a Dockerized management UI — designed to keep searchable knowledge available without cloud access.
AI Client2025
Browser-based AI development platform that runs tasks inside isolated cloud development environments: natural-language agents read code, run commands, modify files, and integrate results back into Git. Key features include per-task sandboxes, multi-model selection, and an enterprise private-deploy option.
AI Agent2025
Provides a visual, low-code environment to build, debug, and deploy AI agents—integrates model services (OpenAI, Volcengine), RAG, plugins, workflows, and a Chat SDK for embedding agents into apps.
AI Agent2025
Chinese-enhanced fork of TradingAgents that runs multi-agent LLM stock analysis for A-share, HK and US markets, adding domestic models (Qwen, DeepSeek) and local data sources (Tushare, AkShare, BaoStock), with report export to Word and PDF.
AI Agent2025
Terminal coding agent forked from Google's Gemini CLI, retuned for Qwen3-Coder with a custom parser and tool protocol. Runs against OpenAI, Anthropic, Gemini, Qwen or local models, and adds subagents, agent teams, auto-memory and MCP.
AI Client2025
Source code for the GitHub Copilot Chat extension in VS Code: inline chat, an agent mode that plans and edits files autonomously, next-edit suggestions, and MCP integration. Open-sourced so developers can study how Copilot connects to an editor.
Teaches agent harness engineering — the permissions, memory, persistence, and coordination layer that lets an LLM act — across 20 progressive lessons, each adding one mechanism with standalone runnable code. Chinese-first, plus English and Japanese.