Everything in the catalog

Inference and training platform for hosted and dedicated models, deployable in your cloud or Baseten's.

Open-source Python library for adding programmable guardrails to LLM-based conversational applications

Open-source browser infrastructure that runs each Chromium browser in its own VM for agents, with fast starts.

Open-source AI agent platform with a knowledge base, drag-and-drop workflows, MCP support and Docker self-hosting or a cloud service

Open-source workspace for building, deploying and governing AI agents and workflows, with 270+ integrations and self-hosting

Docker's open source MCP Gateway that runs MCP servers in isolated containers with credentials and access control.

Open-source library that optimizes LLM and visual generation inference with specialized kernels and a Python framework.

Durable runtime that runs AI agents and their tool calls in WebAssembly VMs that resume after crashes.

Observability and dev-tool platform for building, evaluating and monitoring AI agents

AI gateway giving one API to 250+ models, with observability, guardrails and prompt management.

Single-file memory layer for AI agents with persistent, versioned and portable memory and no database.

Open-source AI automation platform for agents, flows and tables, with an MCP server, 770+ apps and a cloud or self-hosted option

Open-weights 31.27B-parameter text model from farbodtavakkoli on Hugging Face (apache-2.0).

Open-source document intelligence API that converts PDFs, Office files and images into RAG-ready chunks.

Open durable execution: write async await code that runs on the database or queue you choose.

Open-source, GPL-3.0 platform for building agents with RAG pipelines, a workflow engine and MCP tool use, run from a Docker container

Open-source observability for AI apps: traces LLM calls, prompts, retrieval and agent steps via OpenTelemetry

Open-weights 4.21B-parameter text model from alibiserikbay on Hugging Face (apache-2.0).

Open-weights 2.52B-parameter text model from openbmb on Hugging Face (apache-2.0).

Open-weights 31.27B-parameter text model from farbodtavakkoli on Hugging Face (apache-2.0).

Converts any URL into LLM-friendly input and searches the web, through the r.jina.ai and s.jina.ai endpoints.

Build vector databases on Redis, with vector search combined with exact-match and full-text search.

Open-weights text model from kindlingai on Hugging Face (glm-5.3).

Open-weights text model from Cactus-Compute on Hugging Face (apache-2.0).