Explore / GitHub Agent Apps Campaign

GitHub Agent Apps Campaign

DeepQA runs its QA engine against agent apps that are trending on GitHub: workflow builders, chat UIs, coding agents, research agents and observability tools. Open-source apps are cloned and booted from their repository, hosted apps are tested in place, and every report is published here.

A team that wants its report taken down can ask us and we will remove it.

56
apps
56
public reports
631
scenarios
562
scenarios passed
28
issues confirmed
54
re-verified live
2k
screenshots
9.6k
browser actions
9.1k
model calls
57.2M
tokens
8.5 h
testing time

56 apps (showing 25 to 36)

easy-dataset in the browser during the run
Easy Dataseteasy-datasetConardLi/easy-datasetLLM dataset builderSandbox, from sourcerun by DeepQA Team

Open-source app for building fine-tuning datasets with LLMs: projects, document splitting, question generation and distillation. Run from its repository in the DeepQA sandbox.

Run #1succeeded12 scenarios, 9 pass, 3 fail
2 issues11
omniroute.online in the browser during the run
OmniRouteomniroute.onlineOpen app ↗diegosouzapw/OmniRouteHosted appLLM gateway catalogHosted, in placerun by DeepQA Team

Public site of OmniRoute, an open-source AI routing gateway: model catalog with search, filters and sorting, routing presets and client examples. Tested in place.

Run #1succeeded12 scenarios, 12 pass, 0 fail
0 issues
chat.webllm.ai in the browser during the run
WebLLM Chatchat.webllm.aiOpen app ↗mlc-ai/web-llm-chatHosted appIn-browser chatHosted, in placerun by DeepQA Team

Open-source chat app by MLC that runs language models fully in the browser with WebGPU. Tested in place on its hosted instance.

Run #1succeeded12 scenarios, 11 pass, 1 fail
1 issue1
johnsmith9982-chuanhuchatgpt.hf.space in the browser during the run
ChuanhuChatGPTjohnsmith9982-chuanhuchatgpt.hf.spaceOpen app ↗GaiZhenbiao/ChuanhuChatGPTHosted appChat UIHosted, in placerun by DeepQA Team

Public Hugging Face Space of ChuanhuChatGPT, an open-source multi-model chat UI with history, templates, file upload and agent tools. Tested in place.

Run #1succeeded12 scenarios, 12 pass, 0 fail
0 issues
demo.open-slide.dev in the browser during the run
open-slide demodemo.open-slide.devOpen app ↗1weiho/open-slideHosted appAgent slide builderHosted, in placerun by DeepQA Team

Public demo of open-slide, an open-source slide framework built for coding agents: deck dashboard, folders, search, presenter view and themes. Tested in place.

Run #1succeeded12 scenarios, 11 pass, 1 fail
0 issues
scira.ai in the browser during the run
Scirascira.aiOpen app ↗zaidmukaddam/sciraHosted appAI searchHosted, in placerun by DeepQA Team

Open-source AI search engine with search groups and model choice. Tested in place on its hosted instance without signing in.

Run #1succeeded12 scenarios, 11 pass, 0 fail, 1 blocked
0 issues
chat.langchain.com in the browser during the run
Chat LangChainchat.langchain.comOpen app ↗langchain-ai/chat-langchainHosted appRAG chatHosted, in placerun by DeepQA Team

LangChain's open-source documentation chat agent. Tested in place on its hosted instance.

Run #1succeeded12 scenarios, 12 pass, 0 fail
0 issues
research.u14.app in the browser during the run
Deep Researchresearch.u14.appOpen app ↗u14app/deep-researchHosted appResearch agentHosted, in placerun by DeepQA Team

Open-source deep research agent with a bring-your-own-key workflow from topic to final report. Tested in place on its hosted instance.

Run #1succeeded11 scenarios, 10 pass, 1 fail
1 issue1
bettergpt.chat in the browser during the run
BetterChatGPTbettergpt.chatOpen app ↗ztjhz/BetterChatGPTHosted appChat UIHosted, in placerun by DeepQA Team

Open-source bring-your-own-key chat UI with folders, roles, prompt library and import and export. Tested in place on its hosted instance.

Run #1succeeded12 scenarios, 10 pass, 2 fail
2 issues2
hermes-studio in the browser during the run
Ekko Studiohermes-studioEKKOLearnAI/hermes-studioMulti-agent workspaceSandbox, from sourcerun by DeepQA Team

Open-source multi-agent workspace with chat, model providers, usage and theme settings. Run from its repository in the DeepQA sandbox.

Run #1succeeded11 scenarios, 10 pass, 0 fail, 1 blocked
0 issues
repomix.com in the browser during the run
Repomixrepomix.comOpen app ↗yamadashy/repomixHosted appLLM context packerHosted, in placerun by DeepQA Team

Open-source tool that packs a repository into one AI-friendly file, with a web form for remote repositories, folders and archives. Tested in place on its hosted instance.

Run #1succeeded11 scenarios, 11 pass, 0 fail
0 issues
gitdiagram.com in the browser during the run
GitDiagramgitdiagram.comOpen app ↗ahmedkhaleel2004/gitdiagramHosted appRepository visualizerHosted, in placerun by DeepQA Team

Open-source tool that turns a GitHub repository into an interactive architecture diagram with an LLM. Tested in place on its hosted instance.

Run #1succeeded12 scenarios, 12 pass, 0 fail
0 issues

Put an agent team on your next pull request.

Connect a repo, dispatch a Run, and read an audited, evidence-backed report the same day.