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.

#2870 submission_evaluation succeeded

https://github.com/QwenLM/Qwen-Drive-1.0

complete 2026-09-05 15:33:41
#2869 submission_evaluation succeeded

https://github.com/luiscleto/weherd

complete 2026-09-05 15:33:31
#2868 submission_evaluation succeeded

https://ephemerals.dev

complete 2026-09-05 15:33:21
#2867 submission_evaluation succeeded

https://github.com/lovaxi/Rubato_Device

complete 2026-09-05 15:33:16
#2866 submission_evaluation succeeded

https://openspender.com/agent-to-agent

complete 2026-09-05 15:33:05
#2865 submission_evaluation succeeded

https://lanes.sh/showcase/personal-context-mcp

complete 2026-09-05 15:32:54
#2864 submission_evaluation succeeded

https://moadim.io

complete 2026-09-05 15:32:45
#2863 submission_evaluation succeeded

https://github.com/NeoLabHQ/context-engineering-kit

complete 2026-09-05 15:32:37
#2862 submission_evaluation succeeded

https://github.blog/ai-and-ml/github-copilot/project-hydrafusion-frontier-quality-via-multi-model-orchestration/

complete 2026-09-05 15:32:26
#2861 submission_evaluation succeeded

https://github.com/anthropics/fermats-last-theorem

complete 2026-09-05 15:32:18
#2860 submission_evaluation succeeded

https://github.com/gioblu/NPC-Forge/blob/main/docs/development.md

complete 2026-09-05 15:32:06
#2859 submission_evaluation succeeded

https://www.anthropic.com/research/formalizing-fermats-last-theorem

complete 2026-09-05 15:32:01

Processing logs

Newest worker events first.

info / complete Processing job completed. https://hugovergnes.github.io/little-lm-3-8b/ / 2026-09-10 15:32:26
info / screenshot_captured Screenshot captured and linked. https://hugovergnes.github.io/little-lm-3-8b/ / 2026-09-10 15:32:26
info / capturing_screenshot Capturing screenshot for Training a 3.8B LLM to 0.384 CORE for $998. https://hugovergnes.github.io/little-lm-3-8b/ / 2026-09-10 15:32:21
info / complete Accepted and published Training a 3.8B LLM to 0.384 CORE for $998. https://hugovergnes.github.io/little-lm-3-8b/ / 2026-09-10 15:32:21
info / publishing Publishing accepted listing. https://hugovergnes.github.io/little-lm-3-8b/ / 2026-09-10 15:32:21
info / evaluation_saved Saved accepted evaluation with score 78. https://hugovergnes.github.io/little-lm-3-8b/ / 2026-09-10 15:32:21
info / queued Submission evaluation queued. https://calmscroll.com / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://app.geosurge.ai/login / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://www.buymydeadstartup.com / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://www.bryanpg.com/pragma_twice/ / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://waiting.club / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://botbin.io/?v=next / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://gayanhewa.github.io/dbq/ / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://www.promptone.ai/blog/agent-should-never-choose-its-own-tools/ / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://github.com/gauravapiscean/agentic-kv-cache / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://github.com/markusbug/Orchestrator / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://huggingface.co/Saanora/mark-1x-9b / 2026-09-10 15:32:18
info / queued Submission evaluation queued. https://benchmarks.bespokelabs.ai/autoresearchexam/ / 2026-09-10 15:32:17
info / queued Submission evaluation queued. https://a90.com/blog/a-guestbook-for-humans-and-ai-agents/ / 2026-09-10 15:32:17
info / queued Submission evaluation queued. https://pwnc.it/en/home.php / 2026-09-10 15:32:17