Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
Auto-model router middleware for the pi coding agent — routes each LLM request across local, economical cloud, and frontier tiers with session pinning and cache-aware economics.
Your agent test passed. Would it pass again? Checks whether AI agent test results are repeatable and varied enough to trust as a regression baseline. Reads Promptfoo and DeepEval runs you already have.
Open-source data protection framework for AI agent workflows in n8n. Detects, tokenizes, and reversibly anonymizes sensitive data before it reaches your models.