Agent-agnostic record & replay skill: watch a user demonstrate a workflow (browser via Playwright, desktop via OpenAdapt) and turn it into a reusable AI-agent skill. Works with Claude Code, Codex CLI, opencode.

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

AI said it finished. Flyto2 shows the proof.

The AI toolkit for building reliable browser automations

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

BitDive Model Context Protocol (MCP) server. The Autonomous Quality Loop for AI agents. Provides real runtime context, before/after trace comparison, and integration testing workflows.