#agentic-ai

AI Agent 中文學習地圖 — 從零開始的結構化學習路徑，每階段有必做練習跟必修閱讀。三語對照（繁中／简中／English）。歡迎社群一起貢獻、優化內容。

Agentic research control plane with local proof, provenance packaging, and explicit audit-status reporting.

A fake CLI agent for testing orchestration tooling — emits Claude-shaped hooks, MCP traffic, and stream-json without calling any LLM.

Docs site of OpenAgent: https://github.com/the-open-agent/openagent

MCP server for the Ejentum Logic API. Exposes the four cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call.

Building smart, scalable AI agent systems. Harness AI. Reclaim Time. Amplify Impact.

Hub for AI engineering case studies: multi-agent orchestration, RAG, browser automation, observability + evaluation.

Case study: live AI consultant — typed conversation graph, source-grounded knowledge, reviewer-gated utterances, in-process cost guardian.

Spring AI starter for Cycles — runtime budget and action authority for Spring AI agents

Web interface to the Pi Coding Agent

Self-healing RAG pipeline with drift detection and auto-remediation. Built on n8n + Neon Postgres + OpenAI.

climate-agent is a command-line Python tool that automates the full pipeline for acquiring, processing, and validating climate datasets — primarily for East Africa impact modelling at ILRI (the International Livestock Research Institute).

Ten composable AI skills covering the full arc from idea to launch. Discovery hub for prd-ready, architecture-ready, roadmap-ready, stack-ready, repo-ready, production-ready, deploy-ready, observe-ready, launch-ready, harden-ready. Plug into Claude Code, Codex, Cursor, Windsurf.

The Claude Code CLI tool, wired to Deepseek as the brain. Your favourite workflow up to 200x cheaper and fully functional!

Long-loop agent experiment: Werewolf ops + AI safety research stream. Runs on Claude Code.

Live DSPM Posture Simulator — Azure AI agent data exposure risk assessment (educational tool).

Personal AI assistant powered by GitHub Copilot SDK

Code-free, multi-tool AI assistant configuration for Claude Code, GitHub Copilot, OpenAI Codex, Gemini CLI, Cursor, Windsurf, and Ollama. AGENTS.md as single source of truth, adversarial skills suite, strict token & context discipline, per-tool tactics. Drop-in via submodule or bootstrap script.

Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.