A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).
dashboard python3 hypothesis-testing ai-agents automated-build autonomous-research llmops llm-agent llm-tools cursor-ide mcp-server claude-code claude-code-skills claude-code-skill autonomous-researcher cursor-ide-mcp automated-benchmarking
-
Updated
Sep 2, 2026 - Python