Art & Design

Open-source Claude Code agent multiplexer — run dozens of parallel AI coding agents unattended via tmux

practical patterns for agentic coding: hooks, agents, automation. built from hundreds of claude code sessions

AI pair-programming IDE for macOS — native SwiftUI app with a project-aware Claude Agent SDK runtime.

Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.

Plan-first development partner for Claude Code: interview-driven plans, tier-routed agents (haiku/sonnet/opus), and an adversarial review chain that verifies through real usage.

Complex Autonomous agent , with builtin skills , safety protocols , complex agentic loop and easy to use in every social media you use

Curated library of AI context artefacts for the OL AI Services platform — including prompts, skills, agent configurations, and workflow instructions. Designed as a code-free, installable collection for use across OntoLedgy's LLM-orchestrated chemical engineering workflows.

Build, share, and reuse skills for AI agents.

AscendIQ is a multi-agent AI career copilot that analyzes skills, goals, and experience to create personalized roadmaps, opportunities, and career guidance.

Agent-agnostic template for a personal knowledge monorepo your coding agents read, write, and maintain: charter-routed sub-hubs, prime/capture/maintain skills, deterministic hygiene loop. AGENTS.md contract + plain CLIs work with any agent.

An MCP server and SKILL.md pair for using the Bonsai Ternary Image Generation model

Build in-context RL for skill internalization, improving agent learning on ALFWorld and Search-QA with fewer updates

Control Hermes Agent with a single-file React UI for chat, file browsing, skill management, logs, and memory inspection

Standardize AI agent behavior across IDEs and CLI tools using a single configuration file to reduce token usage and build persistent skill libraries.

Skill for building memory by agent itself

Design engineering skill for AI Agents — build interfaces with craft-level quality

Usage and cost visibility for Claude Code and Codex — native macOS menubar app + cross-platform terminal CLI (npm, cargo, crates.io). ccusage-class reports, live 5h-block TUI, pure-Rust engine. Cost numbers are API-equivalent estimates.

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

AI agent that analyzes your resume against any job description — returns match score, skill gaps, and recommendations. Built with LangChain, LLaMA3, ChromaDB, and Streamlit.

A modular multi-agent system built around skills as the core execution unit. It emphasizes clear skill orchestration, reusable capabilities, and structured agent collaboration for scalable, transparent, and maintainable workflows.

Hermes Agent ecosystem: hermes-agent + skills + plugins, ported to Alpine Linux

AI skills for building on VeChain — skills, plugins, and agents for any coding agent.

A production-ready knowledge graph system for software engineering that connects design patterns, refactoring techniques, and software laws through semantic relationships. Built for AI agents first — integrate software engineering expertise directly into Claude Code, Cursor, and other MCP-compatible tools.

A SQLite persistent memory layer for any coding agent. Stop-hook extraction captures sessions, MCP tools expose them mid-session, hybrid search retrieves them, and a tiered L0/L1 recall block injects identity + top-ranked records at session start. Works across any AI harnesses like Claude Code, Opencode, & Pi from one database.