Under the hood

AI queue

Watch AgentDish crawl new pages and run AI reviews in public.

Processing queue

Live queue state for crawls and AI evaluations.

#1308 submission_evaluation succeeded

https://github.com/abhavk/erlangchain

complete 2026-07-01 15:33:16
#1307 submission_evaluation succeeded

https://github.com/Toadoum/ai-research-skill

complete 2026-07-01 15:33:05
#1306 submission_evaluation succeeded

https://firstqa.dev

complete 2026-07-01 15:32:53
#1305 submission_evaluation succeeded

https://node-pad.com

complete 2026-07-01 15:32:43
#1304 submission_evaluation succeeded

https://0xff.nu/hex/

complete 2026-07-01 15:32:38
#1303 submission_evaluation succeeded

https://www.autotunellm.com

complete 2026-07-01 15:32:26
#1302 submission_evaluation succeeded

https://clusy.io

complete 2026-07-01 15:32:17
#1301 submission_evaluation succeeded

https://github.com/Tako-Research/TakoVM

complete 2026-07-01 15:32:07
#1300 submission_evaluation succeeded

https://github.com/arman-jalili/rigorix-oss

complete 2026-07-01 15:31:56
#1299 submission_evaluation succeeded

https://github.com/najaeda/naja-scope

complete 2026-06-30 15:38:12
#1298 submission_evaluation succeeded

https://play.google.com/store/apps/details?id=com.likhith.anvit&hl=en_US

complete 2026-06-30 15:37:42
#1297 submission_evaluation succeeded

https://github.com/thomaspeklak/agent-sandbox

complete 2026-06-30 15:37:30

Processing logs

Newest worker events first.

info / evaluating Running the AI evaluation. https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase / 2026-07-09 15:38:33
info / crawl_saved Saved crawl snapshot with status 200. https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase / 2026-07-09 15:38:33
info / crawling Crawling https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase. https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase / 2026-07-09 15:38:33
info / checking_duplicate Checking for an existing accepted listing. https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase / 2026-07-09 15:38:33
info / starting Started processing job. https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase / 2026-07-09 15:38:33
info / complete Processing job completed. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:31
info / complete Rejected submission decision saved. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:31
info / rejecting Saving rejected submission decision. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:31
info / evaluation_saved Saved rejected evaluation with score 8. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:31
info / evaluating Running the AI evaluation. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:28
info / crawl_saved Saved crawl snapshot with status 200. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:28
info / crawling Crawling https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:28
info / checking_duplicate Checking for an existing accepted listing. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:28
info / starting Started processing job. https://combine-lab.github.io/blog/2026/07/07/fable-is-not-a-useful-model.html / 2026-07-09 15:38:28
info / complete Processing job completed. https://microsoft.github.io/flint-chart/ / 2026-07-09 15:38:26
info / complete Rejected submission decision saved. https://microsoft.github.io/flint-chart/ / 2026-07-09 15:38:26
info / rejecting Saving rejected submission decision. https://microsoft.github.io/flint-chart/ / 2026-07-09 15:38:26
info / evaluation_saved Saved rejected evaluation with score 18. https://microsoft.github.io/flint-chart/ / 2026-07-09 15:38:26
info / queued Submission evaluation queued. https://itsnoema.com / 2026-07-09 15:38:23
info / queued Submission evaluation queued. https://www.monogram.ai / 2026-07-09 15:38:23