Prompt & EvalOpen Source✦ Free Tier

Agenta

OSS prompt management and LLM eval platform

⭐ 2,000 stars● Health 80 — ActiveApp Infrastructure
Open in Builder →Website ↗GitHub ↗

About

Open-source platform combining prompt management, human evaluation, and automated testing. Self-hostable alternative to commercial eval platforms.

Choose Agenta when…

  • •You want an open-source LLM ops and eval platform
  • •Self-hosting your prompt management stack is important
  • •Collaborative prompt engineering with a team is needed

Builder Slot

How do you know it's working?Optional for most stacks

Tests, evals, and experiment tracking to measure and improve your AI output quality

Dev Tools
Not applicable
App Infra
Recommended
Hybrid
Optional

Other tools in this slot:

PromptFooDeepEvalRAGASVellumPromptLayerTruLensHumanloopInspect

Stack Genome Detection

AIchitect's Genome scanner detects Agenta in your project via these signals:

pip packages
agenta
env vars
AGENTA_API_KEY

Alternatives to consider (2)

Langfusecompare →PromptFoocompare →

Pricing

✦ Free tier available
CloudPaid

Badge

Add to your GitHub README

Agenta on AIchitect[![Agenta](https://aichitect.dev/badge/tool/agenta)](https://aichitect.dev/tool/agenta)

Explore the full AI landscape

See how Agenta fits into the bigger picture — browse all 207 tools and their relationships.

Explore graph →