Browse All AI Tools

ML model testing and quality assurance platform

Kolena provides a comprehensive platform for testing and evaluating machine learning models. It enables systematic testing across data slices, regression detection, and model comparison to ensure quality before deployment.

Open-source search and RAG infrastructure

Trieve provides open-source infrastructure for building search and RAG applications. It combines full-text search, semantic search, and recommendations with built-in chunking, embedding, and reranking.

AI-powered customer support and documentation assistant

Markprompt provides AI infrastructure for customer-facing documentation and support. It ingests docs, help centers, and knowledge bases to power AI assistants that answer customer questions accurately with citations.

Simplified LLM fine-tuning platform

Finch simplifies LLM fine-tuning with a managed platform that handles data preparation, training, evaluation, and deployment. It provides best-practice defaults while allowing advanced customization for ML engineers.

Continuous evaluation platform for AI applications

Relari provides automated evaluation tools for testing LLM applications in CI/CD pipelines. It measures accuracy, hallucination rates, and safety across diverse test scenarios to catch regressions before deployment.

Baidu's open-source deep learning platform

PaddlePaddle is Baidu's open-source deep learning framework offering comprehensive tools for developing and deploying AI models. It includes pre-trained models, AutoML, and specialized libraries for NLP, CV, and speech.

ML experiment tracking and model management platform

Comet ML provides experiment tracking, model management, and production monitoring for ML teams. It captures code, hyperparameters, metrics, and artifacts to enable reproducibility and collaboration.

Open-source LLM evaluation and red teaming tool

Promptfoo is an open-source tool for evaluating and red-teaming LLM outputs. It supports systematic prompt testing, model comparison, and security assessment with customizable test suites and assertions.

Domain-specific LLM development through model merging

Arcee AI specializes in creating domain-specific language models through advanced model merging techniques. It combines multiple models to create specialized AI that outperforms individual models on targeted tasks.

Open-source MLOps platform for experiment management

ClearML provides an open-source MLOps suite covering experiment tracking, data management, pipeline orchestration, and model deployment. It integrates with any ML framework and scales from laptop to cluster.

IDE for building and deploying AI agents with natural language

Wordware is a prompt IDE that lets developers build complex AI agents using natural language programming. It supports multi-step workflows, tool integrations, and deployment as API endpoints.

High-performance vector database for AI applications

Epsilla is a high-performance vector database designed for AI applications requiring fast similarity search. It provides RAG-as-a-service capabilities with built-in chunking, embedding, and retrieval pipelines.

Next-generation AI infrastructure and Mojo programming language

Modular builds AI infrastructure including the Mojo programming language and MAX platform for deploying AI models. Mojo combines Python usability with systems-level performance for AI development.

Fine-tune and deploy LLMs from your production data

OpenPipe captures LLM API calls in production and uses them to fine-tune smaller, faster, and cheaper models. It automates the process of distilling large model outputs into efficient custom models.