Search the AI ecosystem

Graphlit is a managed context platform for ingesting documents, audio, video, images, and web data into searchable retrieval, extraction, conversation, and agent workflows. The…

BentoML packages models and inference code into production services. The Apache-2.0 project supports local and self-hosted deployments, while the managed Bento platform provides autoscaling…

DeepEval is an Apache 2.0 open-source Python framework for evaluating LLM applications, agents, RAG systems, and prompts. It runs locally, integrates with testing and…

Humata lets individuals and teams upload documents, ask questions, generate summaries, and inspect source-grounded answers across technical, research, legal, and internal knowledge files.

Twelve Labs provides video-native foundation models and APIs that understand visuals, speech, sound, motion, and text. Developers can index, search, embed, and analyze video…

Parea combines LLM evaluation, experiment tracking, production tracing, prompt management, datasets, and human review in one platform. Teams can start on a free plan,…

Sierra helps enterprises build AI agents that resolve customer requests and complete business actions across voice, chat, SMS, WhatsApp, email, and ChatGPT. Agents connect…

Mastra is a TypeScript framework and platform for building agents, workflows, memory, tools, evaluations, observability, and API services. Developers can run the Apache-2.0 core…

Arize Phoenix is an open-source platform for tracing, evaluating, annotating, experimenting with, and debugging LLM applications and agents. Teams can run it locally, in…

Docling converts PDFs, office documents, images, HTML, audio, and video into a structured DoclingDocument representation for RAG, search, extraction, and generative-AI pipelines. It runs…

Promptfoo tests prompts, models, RAG systems, and agents through declarative evaluations, assertions, red teaming, vulnerability scanning, CI/CD workflows, and provider integrations. The MIT-licensed Community…

Traceloop combines a managed AI observability and evaluation platform with OpenLLMetry, its Apache-2.0 open-source instrumentation. Teams can trace model and agent calls, monitor quality,…

Respan, formerly Keywords AI, combines agent tracing, observability, evaluations, datasets, prompt management, releases, monitoring, and an OpenAI-compatible gateway. Teams can start free, use cloud…

Cognee converts documents and application data into persistent, queryable agent memory. Teams can use the open-source engine locally or Cognee Cloud with APIs, MCP…

LlamaParse converts more than 130 document formats into structured Markdown, JSON, spreadsheets, tables, and annotated outputs using cost-effective, agentic, and agentic-plus processing tiers.

Open WebUI is a self-hosted, provider-agnostic AI workspace for local and remote models. It supports multi-user chat, retrieval, tools, functions, MCP and OpenAPI connections,…

Cleanvoice AI removes filler words, long silences, mouth sounds, breaths, stutters, and background noise from spoken audio and video. It also offers transcription, summaries,…

Explainpaper helps readers understand research papers by explaining highlighted text, formulas, and figures. It supports follow-up questions, full-paper summaries, saved notes, and Zotero library…

Ragas is an open-source Python framework for evaluating RAG pipelines and LLM applications. It provides component and end-to-end metrics, experiment workflows, integrations with popular…

Ultralytics provides the YOLO computer-vision ecosystem for training, labeling, tracking, exporting, and deploying models across cloud, edge, API, and on-premises environments.