Agenta
MIT-licensed LLMOps platform for prompt engineering, evaluation, and tracing.
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
- OpenAI Playground
Browser-based prompt iteration environment for the OpenAI API.
- PromptPerfect
Automated prompt optimization tool for text and image models — shutting down September 2026.
- PromptHub
Git-style version control and collaboration platform for LLM prompts.
- Vellum
LLM development platform for prompt engineering, testing, and deployment.
- Sourcegraph Cody
Enterprise AI coding assistant with multi-repository context retrieval
- Arize Phoenix
Trace every step your LLM agent takes, from prompt to response