Continuum-AI-Corp / OrcaReplay
OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
Why this job: topics: observability, llm-evaluation, llm-observability
What it does
Record any coding agent. Reproduce the run byte-for-byte with no model called. Fork it from any step onto a different model and see who gets it right.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 40 days ago
- Stars
- 472
- +151 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- TypeScript
- 88% of the code
Is it looked after?
- Contributors
- 4
- Last 90 days
- Issues
- 83% closed
- 1 still open
- Pull requests
- 124 merged
- 2 waiting
- Releases
- None
- Never published
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| comet-ml / opik | 23,293 | yesterday | Apache-2.0 | No downloads |
| jwuthri-cloud / Tracely-ai | 947 | 2 days ago | MIT | No downloads |
| JudgmentLabs / judgeval | 1,073 | 14 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- TypeScript 88%
- Python 6%
- JavaScript 5%
- Dockerfile <1%
Topics
- agent-debugging
- agent-tracing
- ai-agent
- ai-agents
- ai-debugger
- ai-debugging
- anthropic
- llm
- llm-agents
- llm-evaluation
- llm-observability
- mcp
Project record
- JobEvals and observability
- StatusListed
- Commits265
- Forks93
- Watching21
- Stars in 28 days+198
- CreatedAug 29, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026