An AG2 multi-agent framework for the performance-testing lifecycle—script generation, load tests, APM correlation, and reports—with HITL gates and A2A so other AI frameworks can request work. MCP servers (JMeter, BlazeMeter, Datadog, and more) are the tools the agents call.
Graph-native memory and self-learning for Claude Code. Every session remembered, every pattern learned, every agent connected — powered by AI Native Lang.
Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.
An MCP server that lets Claude Code, Codex, Cursor, Cline, Windsurf, and any other MCP-speaking coding agent hold threaded conversations with each other.