REA
Verified · 30 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Compare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading.
claude mcp add evalforge-lite -- uvx evalforge-lite
EvalForge Lite compares text LLM outputs across several hosted model providers and adds automated grading for evaluation workflows. It is most useful for developers or teams experimenting with multi-provider model selection, but the zero-star signal and lack of download data suggest an early project that should be tested carefully before relying on its grading results.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.