Agentic game development taken to the next level: plan, build and test across major engines with any coding agent🤖

Superseded by coding-agent-toolkit — see README. Preserved for reference: Claude-Code-only patterns from earlier iteration.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

A security scanner for your LLM agentic workflows

Coding standards for AI coding assistants. Auto-detect tech stack, generate project rules. Works with Claude Code, Cursor, Antigravity, GitHub Copilot.

Control 1 or more machines using computer use tools that integrates with your agents

Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

Web Graphical User Interface (GUI) for Gas Town multi-agent orchestrator - A companion interface for steveyegge/gastown

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in one self-hostable stack.

Curated list of Agent Skills for AI coding agents like Claude Code, Codex and Cursor.

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

Interactive documents from Markdown. Extends MD with forms, approvals, webhooks, and more — built for next gen apps

Multi-agent systems, memory, planning, reasoning loops

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

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.)

Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory

Computer-Use SDK for E2E QA Testing

Model Context Protocol management suite/factory. An MCP that can generate and manage other local MCPs in multiple languages. Uses the official SDKs for code gen.