{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "Continuum-AI-Corp/OrcaReplay",
 "name": "OrcaReplay",
 "owner": "Continuum-AI-Corp",
 "slug": "continuum-ai-corp-orcareplay",
 "github": "https://github.com/Continuum-AI-Corp/OrcaReplay",
 "what": "OrcaReplay is a TypeScript npm tool that records an AI agent run through a local proxy and lets you replay it offline, fork it onto other models, and inspect what happened.",
 "why": "",
 "language": "TypeScript",
 "requirements": [
  "Node.js and npm, to install the orcareplay package",
  "A coding agent installed locally, such as Claude Code or Codex CLI, to record a run",
  "A model API key and network access for recording and for live forked turns",
  "A terminal with permission to install a global npm package"
 ],
 "audience_note": "Developers and engineering teams who run coding agents and need to find out why a run went wrong or compare models on the same run.",
 "risk": "dual-use",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcareplay/",
 "use_case_count": 5,
 "use_cases": [
  {
   "id": "continuum-ai-corp-orcareplay--find-the-step-that-broke-an-agent-run",
   "title": "Find the exact step that broke an agent run",
   "best": true,
   "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcareplay/find-the-step-that-broke-an-agent-run/",
   "json": "https://dedupedai.com/use-cases/u/continuum-ai-corp-orcareplay/find-the-step-that-broke-an-agent-run.json"
  },
  {
   "id": "continuum-ai-corp-orcareplay--fork-run-to-compare-models-at-one-step",
   "title": "Fork a run at one step and compare models",
   "best": false,
   "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcareplay/fork-run-to-compare-models-at-one-step/",
   "json": "https://dedupedai.com/use-cases/u/continuum-ai-corp-orcareplay/fork-run-to-compare-models-at-one-step.json"
  },
  {
   "id": "continuum-ai-corp-orcareplay--try-orcareplay-without-an-agent-or-key",
   "title": "Try Orca Replay with a sample run and no key",
   "best": false,
   "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcareplay/try-orcareplay-without-an-agent-or-key/",
   "json": "https://dedupedai.com/use-cases/u/continuum-ai-corp-orcareplay/try-orcareplay-without-an-agent-or-key.json"
  },
  {
   "id": "continuum-ai-corp-orcareplay--capture-agent-system-prompt-by-model",
   "title": "Capture an agent's system prompt for each model",
   "best": false,
   "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcareplay/capture-agent-system-prompt-by-model/",
   "json": "https://dedupedai.com/use-cases/u/continuum-ai-corp-orcareplay/capture-agent-system-prompt-by-model.json"
  },
  {
   "id": "continuum-ai-corp-orcareplay--record-codex-cli-that-cannot-be-redirected",
   "title": "Record a Codex CLI run that cannot be redirected",
   "best": false,
   "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcareplay/record-codex-cli-that-cannot-be-redirected/",
   "json": "https://dedupedai.com/use-cases/u/continuum-ai-corp-orcareplay/record-codex-cli-that-cannot-be-redirected.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}