← back to the directory
Library / SDK Observability & Evaluation

Agenta

1Prompt 2engineering, 3evaluation, 4and 5observability 6platform

the six Ws · specification

W1 Who

Maintained by Agenta AI.

W2 What

An LLMOps platform for prompt engineering, evaluation, and tracing.

W3 Where

Self-hosted via Docker or Agenta Cloud.

W4 When

When teams iterate on prompts and measure quality.

W5 Why

Puts a playground, evals, and observability in one place.

W6 With

Docker, an LLM provider, and the Agenta SDK.

W7 Watch

Company-maintained; open-source (MIT), self-hostable, with a hosted cloud (open-core). Self-hosted keeps prompts and traces on your infrastructure.

LLMOpsEvaluationPrompt-engineering

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.