Agenta
MIT-licensed LLMOps platform for prompt engineering, evaluation, and tracing.
Agenta is profiled here as a Prompt Management tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
Short Intro: Agenta is an open-source LLM development platform founded in June 2023 by Akrem Abayed and Dr. Mahmoud Mabrouk through Antler's Berlin residency. In November 2025, Agenta moved all core features to MIT, including the full evaluation system, observability, and prompt management, leaving only enterprise collaboration features under a separate license. The platform targets teams where engineers and domain experts work together on prompts, giving non-technical contributors access to the same iteration tools as developers.
Key Capabilities:
Prompt versioning with branching, environment-specific deployments, and programmatic fetch via SDK
Evaluation with LLM-as-a-judge, custom code evaluators, and span-level scoring across workflow steps
OpenTelemetry-native tracing compatible with OpenLLMetry and OpenInference
Support for 50+ LLM models with no framework restrictions
Complex configuration schemas for domain expert collaboration without code access
Test set management and A/B testing for systematic prompt improvement
Python and TypeScript SDKs for application instrumentation
Self-hostable via Docker with no closed-source components in the core
Alternative tools
- W&B Weave
Trace, evaluate, and monitor LLM applications systematically
- Traceloop
OpenTelemetry-native tracing for LLM applications
- LangChain
The standard open-source framework for LLM applications
- Portkey
AI gateway with routing, guardrails, and prompt management
- Freeplay
Prompt management, evals, and observability for product teams
- DSPy
Declarative framework for programming and optimizing LLM pipelines