Run manual QA test cases in a real browser with an AI agent is a coding AI agent for Automate manual QA test execution in a real browser to remove the need for repetitive human interaction during testing. Pricing: Usage-based pricing. As of 2026-11-05, KanonAgent records 4 upvotes. First indexed by KanonAgent on 2026-07-31.
An AI agent automates manual QA testing by executing test cases directly in a real browser, eliminating repetitive click-through tasks.
4 upvotes
Tracked by Kanon since Jul 31, 2026
Status basis: npm_downloads_7d momentum fell to -188 per 3d from 12 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -188 per 3d from 12 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -188 per 3d from 12 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 6 per 3d from 241 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 12 per 3d from 235 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -145 per 3d from 389 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 241 in the last 3d vs 1 in the 3d before (ratio 241.0x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -145 per 3d from 390 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 235 in the last 3d vs 1 in the 3d before (ratio 235.0x, threshold 1.5x)
- Anomaly daily change -154.0 is -4.6 standard deviations from this entity's own prior mean (5.2±35.0, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 389 in the last 3d vs 1 in the 3d before (ratio 389.0x, threshold 1.5x)
- Anomaly daily change 129.7 is 4.1 standard deviations from this entity's own prior mean (3.0±31.1, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 390 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 129.7 is 4.1 standard deviations from this entity's own prior mean (3.0±31.1, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -102.0 is -5.3 standard deviations from this entity's own prior mean (3.5±20.0, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 7 per 3d from 22 (<= 40% of the prior window)
- Anomaly daily change -102.0 is -5.3 standard deviations from this entity's own prior mean (3.5±20.0, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 5 per 3d from 142 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -7 per 3d from 183 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 22 per 3d from 154 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 142 in the last 3d vs 29 in the 3d before (ratio 4.9x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 22 per 3d from 154 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 183 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 154 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 62.5 is 3.6 standard deviations from this entity's own prior mean (-0.2±17.3, baseline excludes this point) — unusual, not necessarily adoption
🔎 Known / Unknown
12 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | 1 | inferred | 1 quote(s) |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | chrome,anthropic,openai,ollama | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · coding
Job to be doneAutomate manual QA test execution in a real browser to remove the need for repetitive human interaction during testing.
AutonomyL2 · tool-calling(evidence: "The agent opens Chrome and executes each step.…")
Who it is forQA engineers and software testing teams in product-focused companies who handle frequent regression testing.
Prerequisitesopen source · bring your own API key
Integrationschrome · anthropic · openai · ollama
PricingUsage-based pricing
Traction · why it is risingAttracting attention from teams tired of manual testing workflows looking for practical AI automation.
Why it matters
It bridges the gap between AI agents and real-world testing environments, delivering tangible automation where most tools stop.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Needs: ... and an Anthropic API key — or any OpenAI-compatible endpoint”— readme
“The agent opens Chrome and executes each step.”— readme
“Needs: ... Google Chrome, and an Anthropic API key — or any OpenAI-compatible endpoint (Qwen, vLLM, Ollama”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Building Run manual QA test cases in a real browser with an AI agent? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is Run manual QA test cases in a real browser with an AI agent?
An AI agent automates manual QA testing by executing test cases directly in a real browser, eliminating repetitive click-through tasks.
What does Run manual QA test cases in a real browser with an AI agent do?
Automate manual QA test execution in a real browser to remove the need for repetitive human interaction during testing.
Why does Run manual QA test cases in a real browser with an AI agent matter?
It bridges the gap between AI agents and real-world testing environments, delivering tangible automation where most tools stop.
How much does Run manual QA test cases in a real browser with an AI agent cost?
Usage-based pricing
Is Run manual QA test cases in a real browser with an AI agent open source?
Yes — Run manual QA test cases in a real browser with an AI agent is open source.
What does Run manual QA test cases in a real browser with an AI agent integrate with?
chrome,anthropic,openai,ollama
How popular is Run manual QA test cases in a real browser with an AI agent?
As tracked by KanonAgent: 4 upvotes (first indexed 2026-07-31).
What are the best Run manual QA test cases in a real browser with an AI agent alternatives?
Similar AI agents tracked by KanonAgent: deepseek-harness, gemini-cli, Codédex, LLM Gateway, oh-my-openagent, goose.