GitHubAI Skills, Agents & MCP · Agent frameworks
Prebuilt and DIY agents that use Jev, Laya, or Cua-S1 System-1 decision models for browser, desktop, games, and routing.
Why it’s a gem
Swap chat-model decisions for faster cheaper System-1 brains via skill and MCP.
Go deep-research CLI and MCP server with a hard spend ceiling, quote-verified claims, and local CSV analysis that never sends rows to the model.
Rust SRE agent harness that investigates production incidents with scoped workers, disk-backed context, and human-gated remediations.
Open-source simulation testing and monitoring platform for voice agents, with BYO STT/LLM/TTS keys and zero markup on inference.
Agent-first CLI framework with one grammar and canonical names across SaaS providers, loading command schemas only when asked.
Local-first desktop inbox for background AI agents, with unread results, approval queues, and bring-your-own model providers.
Workflow DSL that turns repeatable agent work into inspectable steps with Jev decisions and optional full agent loops.