The agentic workspace where people and agents work together in the loop.

Terminal Director. One lightweight app, eight features, your whole dev workflow in a single window.

Rails Engine with MCP compliant Spec.

A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable, and resumable.

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Jira toolkit for terminals, coding assistants, and bots.

Multi-Agent works on native GUI desktop. Supports skills and IM channel, build-in a IDE for light development. Built on the shared piscis-engine kernel.

An MCP server for parallel browser automation by AI agents with multiple cloud providers

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

AI-powered bug bounty hunting toolkit that works with or without subscription.

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.

List of agent orchestrators

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code. Real source first.

Turn tracker tickets into autonomous agent sessions

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

Helping the Agents Compose the Things

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

🤖🤮 Hate the yuck codes that agents generated? Try `alint`, a ESLint like toolchain for intent driven code check, freeze your skills, AGENTS.md to lint rules

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

Tools for AI agents to test, fix and optimise your codebase