arthi-arumugam-git/whatbroke
Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit prompts.
A library that records a program's external inputs — database, HTTP, clock, randomness — and replays them, so any past run can be reproduced and debugged exactly.
Appears on
Quick read
Latest capture 2026-10-14 09:46
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
1 observed capture since 2026-10-14. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit prompts.
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.
The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas and agent harnesses powering today's AI products. Captured with OrcaReplay.
A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.
Create polished demo videos without editing skills. Mac/Windows/Linux
Chrome extension that records your browser interactions and generates a Playwright or Puppeteer script.