#json

Python training materials and exercises for NBD, covering examples from Coding Examples from Simple to Complex - Applications in Python, followed by applied lectures on files, Excel/CSV, client-server systems, AI automation, Flask, MySQL, and encrypted database workflows.

Open-source Apple Health MCP server for the MetricBridge iOS app: query 190 HealthKit metrics from Claude, ChatGPT, Cursor, OpenClaw, Hermes and any AI agent. Zero-dependency, local-first, read-only.

SyncCanvas is an AI-powered collaborative whiteboard for real-time brainstorming, diagramming, and team collaboration on an infinite canvas. 🚀

Agent-first Bible CLI. Multi-locale, deterministic, offline. Returns canonical JSON, supports batch and multi-translation parallel lookups.

Pre-registered benchmark: HTML dialect + whole-tree rewrite (barkup) vs JSON, granular mutation tools, and two patch dialects, for LLM agents editing typed trees. 9,600 scored runs across 4 models. Findings in REPORT.md.

Manage AI workspace permissions on macOS. Control file access for Claude and Codex through a local, versioned runtime.

Professional-grade real-time AI Voice Assistant platform built with FastAPI, Next.js, and VAPI for intelligent voice call orchestration.

Protean-kit protocol ingredient for agent messaging. Dense, checkable messages for AI agents. AI agents talk to each other in English, usually wrapped in JSON. SYM-2P replaces the English with symbols: roles, actions, and states become numbers, fields become positions in a line, and payloads become s-expressions, a Lisp notation for nested structure. Every word an agent writes costs tokens, and tokens cost money and time. English is also ambiguous: no program can check a sentence the way it checks a number. Symbols are cheaper and checkable. One brief packet is a 101-byte line where the JSON took 481.

AI-powered Resume Parser and Candidate Ranking System using Groq LLM, Pydantic, and Python to extract structured resume data, compare it against job descriptions, calculate match scores, and rank candidates automatically.

Recover a structured result from an agent session: its structured_output, then the StructuredOutput inputs the CLI rejected, then the JSON in its result text and its assistant texts.

Extract structured information from unstructured text using Prompt Engineering and Google's Gemini LLM.

Fast, private, client-side developer tools and clear references — plus explainers on modern AI infrastructure (context windows, MCP, RAG, embeddings, agent patterns). Everything runs in your browser; nothing is uploaded.

把剪贴板内容无损落地成带时间戳的文件，再把路径回填剪贴板——agent 时代的大文本捕获小工具。系统原生 pbpaste/pbcopy，零渲染、零应用内搬运，自动检测并美化 JSON。

Deterministic repair and validation for LLM JSON output. 8% of malformed responses parse raw; 96% after the repair ladder.

Exchange for Protean collaboration with outside agents: SYM-2P packet mailboxes, a peer registry, and Phase 0 manual relay.

Public SYM-2P collaboration exchange profile: packet mailboxes, peer registry, procedures, and validator pointer for Protean-group agent collaboration.