Agent infrastructure

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.

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.

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

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

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

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

Web search API for AI applications, available through one API call or deployed inside your own cloud.

Managed search database for AI agents and apps, covering semantic, sparse, full-text and hybrid queries.

Cloud platform to build, deploy and distribute MCP servers and MCP apps for ChatGPT and Claude.

Voice AI agents for regulated, high-stakes phone calls, run end to end on Bland's own speech, language and voice models.

One real-time API for voice agents combining speech-to-text, LLM orchestration and text-to-speech, priced at $4.50/hr.

API that parses PDFs and images into grounded Markdown and extracts typed fields with a schema.

AI gateway and agent observability for 250+ LLMs, with tracing, analytics, guardrails and cost controls.

Agentic document platform for parsing, extracting, splitting, classifying and editing documents.

Code execution API that lets LLM-generated code run in isolation and returns its output.

Isolated Linux devboxes for running AI agents and their code, with snapshots and reusable blueprints.

Governed platform for every agent, model and tool a company runs, deployable in its own cloud.

Context layer for building AI agents that reason over technical documents and institutional knowledge.