Coding & Development

An agentic memory system implemented as an MCP server

赣东学院信息工程学院科创部活动策划案生成与验收 Skill，支持框架起草、Word 策划案生成、水印、审计和渲染检查。A Codex skill for drafting, generating, auditing, and rendering official activity proposals for the GDU School of Information Engineering.

🛡️ Explore and test prompt injection techniques safely for AI applications, enhancing your skills in ethical hacking and digital security.

Enable system-level AI agents on Android devices with on-device LLMs, secure tool control, and a conversational shell replacing the launcher

Contextual continuity infrastructure for AI coding agents — semantic memory across sessions and org-mode knowledge bases. Pi extension + Gemini Embedding 2 + LanceDB.

Bring Your Agent, Start to Fight! The Open Platform for AI Agents, Workflows, Prompts, and Battles

Tmux sidebar for vibe coding. Manage sessions and monitor agents at a glance

Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.

Open-source tool for defining and running AI agents alongside you and your team. Any model, any CLI.

🐙 AI-powered presentation builder with a conversational agent, live Marp preview, and lightweight presentation on your browser.

Browser-native agent · profiles · tools — by aratech | Zero installs, isolated, secured and self-evolving agent.

A lightweight, production-ready multi-agent framework

A community-maintained registry of Model Context Protocol (MCP) servers with structured installation configurations for easy integration.

Automated daily wisdom — picks a quote from Imam Ali (AS), generates styled images with Pillow, writes a peaceful caption with Claude, and posts a carousel to Instagram. Runs on GitHub Actions every morning.

Local-first AI memory backbone for IDE/agent assistants — Claude Desktop / Claude Code / Cursor / Cline / Continue. One-click install; never leaves your machine.

Cursor AI rules for Agentforce agent development and validation

From 10-K to DCF in one prompt. 55 production-ready Claude skills for financial services.

Build and test production-ready software from simple prompts using a reliable 9-stage pipeline with full verification and adversarial testing.

Explore Claude Code system prompts and agent architecture to study how AI coding assistants are built

Route prompts to cloud or local AI models using a multi-armed bandit router and execute agentic tasks with extensibility via tools, hooks, and MCP servers.

Add a virtual pet with persistent memory and XP evolution to your MCP-capable CLI tools like Claude Code, Cursor, and Gemini.

This is my progress of getting my hands dirty with AL agents, LLMs and automations

coevo Agent Governance Mesh — Control-plane specification and runtime for multi-agent systems atop A2A & MCP protocols.

Streamline code reviews by connecting Claude Desktop to GitHub PRs, filtering files to deliver focused AI-powered feedback on code changes.