Agent infrastructure

Python framework for LLM-powered agents, built on the Dapr distributed systems runtime.

Library that lets LangGraph agents extract, consolidate and search their own long-term memory.

Browser infrastructure for AI agents: stealth cloud browsers, an open-source Playwright-based framework and deployable functions.

Open-source, cloud-native distributed vector search engine for approximate nearest neighbor search.

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

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

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.

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 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.

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

Database for AI with a deep-learning storage format for embeddings, media and datasets, plus vector search.

Cloud GPU platform for AI with pods, pay-per-second serverless endpoints and clusters across 31 regions.

Open-source, datacenter-scale orchestration layer that coordinates multi-node inference across engines such as SGLang, TensorRT-LLM and vLLM.

Isolated Linux microVMs for running agent-generated or untrusted code, driven by an SDK and CLI.

Small SQLite extension that adds vector search to SQLite tables, written in pure C with no dependencies.

Managed memory layer from Redis that lets AI agents recall facts and preferences across sessions.

Open source vector database for AI apps, built on Postgres with pgvector and available self-hosted or managed.

Context and memory layer that syncs project decisions and rules selectively across coding agents and teammates.

Single OpenAI-compatible API to 100+ LLM providers, with routing, fallbacks and unified observability.

Platform to make AI agents and workflows durable, deterministic and explainable.

Open-source, code-first platform for scripts, workflows, internal apps and AI agents.