Every blueprint recommends
the right tools for the job.

State-of-the-art frontier models built for safe, steerable, and capable agentic use

Headless browser infrastructure for agents — reliable, scalable, cloud-native

250+ pre-built tool integrations so agents can act on external systems out of the box

MCP server that injects up-to-date library documentation into your agent's context

The most widely-adopted framework for building LLM-powered applications and agents

Open-source LLM observability — trace every agent run, score outputs, and catch regressions

The data framework for building LLM applications over custom knowledge sources

Managed vector database built for production-scale semantic search and agent memory

Deploy any containerised agent to production in minutes — zero infrastructure complexity

Open-source Firebase alternative — Postgres, auth, storage, and pgvector in one platform

Code-native background jobs and event-driven agent execution with full observability

Open-source embedding database — the fast path from prototype to local vector search

Fastest inference API for open-source models — purpose-built for speed

Lightweight LLM proxy for logging, cost tracking, and caching with zero code changes

Anthropic's reference MCP server for reading, writing, and navigating local filesystems

Run open-source LLMs locally with a simple API and no cloud dependency

The GPT model family with vision, audio, and the broadest tool-calling ecosystem

No-code automation backbone connecting 7,000+ apps for agent-triggered workflows