Arc Campaign
Arc testnetCelebrating Circle's Arc mainnet launch: DeepQA tests Arc ecosystem apps in place, with an injected test wallet on Arc testnet.
54
apps
627
scenarios
8.2k
browser actions
9.9k
model calls
66.9M
tokens
12 h
testing time
Explore
Public Runs on real apps.
Only published results appear here. DeepQA runs far more than it publishes — internal benchmark campaigns and private repos stay private, and publishing is an explicit choice. Every Run below was executed and published by the DeepQA team: scenarios driven in a real browser, findings adversarially audited by the Critic, and a report you can read end to end.
124
published runs
1463
scenarios executed
255
issues confirmed
15
criticals found
118
apps published
18.5k
browser actions
4.1k
screenshots
135M
tokens
Campaigns
A campaign puts a group of apps through the whole pipeline and publishes every report as it lands.
GitHub Agent Apps Campaign
Open sourceDeepQA tests agent apps that are trending on GitHub: workflow builders, chat UIs, coding agents, research agents and observability tools.
56
apps
631
scenarios
9.6k
browser actions
9.1k
model calls
57.2M
tokens
8.5 h
testing time
/
124 runs across 118 apps (showing 1 to 12)
rockbenben/subtitle-translatorLLM translation toolSandbox, from source
runs by DeepQA TeamOpen-source batch subtitle translator with many LLM and translation providers, multi-language output and provider settings. Run from its repository in the DeepQA sandbox.
lnkiai/m3e-canvasDesign canvas for agent promptsSandbox, from source
runs by DeepQA TeamOpen-source design canvas that turns Material 3 Expressive screens into prompts for coding agents: screens, layers, themes, preview and prompt export. Run from its repository in the DeepQA sandbox.
okisdev/ChatChatChat UISandbox, from source
runs by DeepQA TeamOpen-source unified chat and search platform across model providers with sessions, system prompts and provider settings. Run from its repository in the DeepQA sandbox.
xmanrui/OpenClaw-bot-reviewAgent fleet dashboardSandbox, from source
runs by DeepQA TeamOpen-source dashboard for a fleet of OpenClaw agents: bot wall, models, sessions, statistics and an alert rule center. Run from its repository in the DeepQA sandbox.
siteboon/claudecodeuiCoding agent web UISandbox, from source
runs by DeepQA TeamOpen-source web and mobile UI for coding agent CLIs: setup wizard, project workspaces, chat, shell, files and source control views. Run from its repository in the DeepQA sandbox.
Critcrit.mdOpen app ↗tomasz-tomczyk/critHosted appAgent feedback toolHosted, in placeOpen-source review tool for coding agents: comment on lines, reply in threads and turn the review into an agent prompt. The public site carries an interactive review demo. Tested in place without signing in.
Hugging Face Space by the llama.cpp organization that converts and quantizes a model repository to GGUF. Tested in place without signing in, so the conversion itself was not run.
Official Hugging Face Space of Qwen3 by the Qwen team: chat with a thinking mode toggle, thinking budget and conversation history. Tested in place.
patoles/agent-flowAgent run visualizerSandbox, from source
runs by DeepQA TeamOpen-source real-time visualizer for coding agent sessions: agent graph on a canvas, timeline, transcript, file attention and cost overlay. Run from its repository in the DeepQA sandbox.
Open-source local-first AI chat workspace with assistants, skills, plugins, knowledge bases, workspaces and MCP servers. Tested in place on its hosted instance.
Nutlope/logocreatorAI logo generatorSandbox, from source
runs by DeepQA TeamOpen-source AI logo generator with styles, colors, brand kits and a bring-your-own-key flow. Run from its repository in the DeepQA sandbox.
CookSleep/gpt_image_playgroundImage generation playgroundSandbox, from source
runs by DeepQA TeamOpen-source bring-your-own-key playground for GPT image models with a gallery, favorite folders, search and API settings. Run from its repository in the DeepQA sandbox.