Smilinrobin
Re:
on Sunday February 16, 2025 @12:09PM (#43069587)
We've added Playwright's Tracing capability for debugging end to end agentic test execution by our open source testing agent: https://github.com/test-zeus-ai/testzeus-hercules/. Coupled with the capability to log thoughts and inner monologue of the agent, now our users can review the direction taken by the agent; and steer it in the right direction.
Or catch hidden bugs in the application under test.
Show HN: I used DeepSeek and TestZeus to do agentic testing
https://github.com/test-zeus-ai/testzeus-hercules
Hello, Robin here. I am one of the cofounders at Testzeus, and we had built an open source testing agent. Using AG2 framework, our agent uses tools like Playwright for browser interaction, Nuclei for security scanning or AXE for accessibility. So, with the release of Deepseek R1, and earlier launch of OpenAI Operator, I was curious if we could generate UI tests using Deepseek R1, and feed them...
Show HN: Open-source end to end software testing agent
https://github.com/test-zeus-ai/testzeus-hercules
As engineers, testers and product owners, we've all felt the frustration of flaky tests, endless maintenance, and tools that don’t quite fit our needs. That’s exactly why we built Hercules, the world’s first opensource software testing agent:Why we made it?1⃣ To simplify end to end testing cycles : API, Web, Database, and Security testing—all in one place2⃣ To save time and effort: No code. No...
Re:Show HN: Hercules – Open-Source software testing agent
on Tuesday November 26, 2024 @12:18PM (#42247618)
Thanks. Also, while Hercules can do Salesforce, we've also checked it for complicated scenarios on the web (and there's an eval folder too). We'd love to know about your feedback and thoughts.
Re:Show HN: Hercules – Open-Source software testing agent
on Wednesday November 20, 2024 @03:25PM (#42197764)
In theory , yes we could, but would it yield "good enough" results for a "testing" agent- Probably not. The LLM here is actually not just responsible for tool calling, its also doing other intricate things such as planning the next steps based on the input feature file, and generating the browser/API automation code. In our experiments we found that OpenAI 4o performs best, followed by Haiku or Grok.
Re:Show HN: Hercules – Open-Source software testing agent
on Tuesday November 19, 2024 @03:16AM (#42181057)
THanks HackerNews for not letting us update the post.
But the Discord link had some bug (yes, we need more testing), so here's the link for joining our Discord server: https://discord.gg/JhSAGhfR55
Re:Show HN: Hercules – Open-Source software testing agent
on Tuesday November 19, 2024 @03:15AM (#42181051)
1 - Yes, thats the whole idea (almost)
2 - LLM based
3 - Understands and acts on multi layered DOM
4 - Its available as a docker container. Plus we offer paid solutions for real large scale deployments
5 - Yes, planning for it.
Thanks.
Re:Show HN: Hercules – Open-Source software testing agent
on Tuesday November 19, 2024 @03:14AM (#42181041)
You can already try other LLMs. Steps in docs.
Show HN: Hercules – Open-Source software testing agent
Hey HN,After spending way too many late nights wrestling with brittle test scripts and UIs that seem to change just to spite me, we decided to do something about it. So we built Hercules, an open-source testing agent aiming to make end-to-end testing of modern web applications less of a Herculean task (pun absolutely intended).P.S.- Paid solutions can cost upwords of $15000 and still struggle...
What is the future of software test automation?
What does the community think is the future of software test automation? Firestarters: Generative UI and UX, Cursor and Replits of the world, Open source frameworks, and testing versus automation.
Re:Built an AI Gateway in Rust for routing OpenAI and Groq (What do yo...
on Thursday November 07, 2024 @09:05AM (#42076742)
This rocks!!