Agenta
Open-source prompt management & evals for AI teams
576 followers
Open-source prompt management & evals for AI teams
576 followers
Agenta is an open-source LLMOps platform for building reliable AI apps. Manage prompts, run evaluations, and debug traces. We help developers and domain experts collaborate to ship LLM applications faster and with confidence.
tbh I was evaluating Langfuse and a couple other tools last months. What sold me on Agenta's pitch is the UI-first approach for non-dev SMEs. In our org SMEs need to tweak prompts without opening PRs and that workflow matters. Approval workflows would be a killer feature for larger orgs, TBF. Would love an API hook so we can gate prompt deploys via our CI pipeline.
As a PM, have been trying several tools for evals, super excited to try this one!!
Agenta
@rakshika_bawari We build Agenta specifically to target the problem of collaboration between PMs and developers. I look forward to your feedback!
RiteKit Company Logo API
Glad to have a prompt collab tool - good work, guys!
Agenta
@osakasaul Thanks Saul! Looking forward to your feedback!
Congrats on the launch Mahmoud and team!
Agenta
@charlotteschmitt Thanks Charlotte!
Makers Page
Been juggling prompts in git and evals in notebooks. Agenta looks like the boring tooling I actually want. Open source is nice. Trace debug view = clutch. If it plays nice with PostHog/LangChain, I’m in. Saving this for next sprint.
Agenta
@alexcloudstar we have Langchain integrations. Looking forward to your feedback!
@mahmoudmabrouk Love the open-source approach! 🚀
How do you handle prompt versioning when multiple teams are collaborating? Can you roll back to previous versions easily?
Agenta
@mskyow Yes, that's one of the core functionalities in Agenta!
Everyone can create new versions of prompts. Add commit messages. We have a branching system that allows the whole team to work on prompts without touching production. Then deploy to production.
The production branch has its own history, so you can always roll back to the latest version in prod.
Tried a prompt tracing tool last year and TBH the hardest part wasn’t the traces themselves but connecting them to test suites. Agenta's evals + test-case approach sounds promising because we need deterministic tests for regression checks. In our case we was able to catch a prompt drift only after a month, so automated evals would be huge. Would love to know how easy it is to author evaluators for domain-specific metrics. IMO good CI hooks and a lightweight API make the difference between a demo and something you can rely on in production.