[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents, and automatic verification

The ngrok alternative for Mac, Windows & Linux. Public URLs (tunnels), .local domains, automatic HTTPS, traffic inspector, MCP server for AI agents. Free plan.

Claude Code plugin for multi-step workflow orchestration — automatic task decomposition, parallel agent execution, and specialized agent delegation with native plan mode integration.

Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.