Tools Directory

Score, benchmark, and stress-test LLM outputs for enterprise deployments

Detect hallucinations and agent failures across the full development lifecycle

Open-source LLMOps platform for observability, evaluation, and agent simulation.

End-to-end prompt management platform covering iteration, evaluation, deployment, and monitoring.

End-to-end AI evaluation platform with pre-production agent simulation and production observability

Collaborative AI development platform for prototyping, evaluating, and monitoring LLM features.

Tagline: Python-native LLM versioning and tracing via a single decorator.

Open-source agent observability platform with prompt engineering and auto-evaluation.

Git-style version control and collaboration platform for LLM prompts.

MIT-licensed LLMOps platform for prompt engineering, evaluation, and tracing.

LLM development platform for prompt engineering, testing, and deployment.

AI code review platform for pull requests and agent output

AI code review platform built around code integrity

AI coding platform built for large, distributed codebases

Trace every step your LLM agent takes, from prompt to response

Trace every step your LLM agent takes, from prompt to response

Scan AI agents for vulnerabilities before and after deployment

Test and red team LLM applications from the command line

Evaluate RAG pipelines without human-labeled reference answers

Open-source LLM observability platform with one-line proxy integration.

Prompt management platform for engineers and domain experts.