Postman

The Context Graph API is Postman’s private, authenticated knowledge graph for giving coding agents a machine-readable map of an organization’s API ecosystem. It connects services, endpoints, schemas, consumers, owners, deployments, environments, telemetry, and runtime call relationships, resolving data from connected sources into a traversable graph. The graph is refreshed nightly and can expose dependencies beyond the repositories checked out locally, including observed runtime relationships and likely change blast radius. Agents query the graph through the asynchronous `/asks` endpoint with a natural-language question. A request returns a job ID, which the caller polls until completion; the result contains a written answer and structured data that the agent can use to investigate affected repositories, services, teams, or other resources before changing code. Postman describes it as a context layer that can be used with an existing model, IDE, or coding agent rather than requiring a replacement stack.

Pizza Bot is a local-first inbox for long-running AI-agent work, developed at Amazon. It lets users start or schedule tasks, switch conversations, and return to completed work in an Unread queue or approval requests in an Action queue. Its stateful DeepAgents/LangGraph runtime checkpoints runs so they can continue after a client disconnects; cron and webhook triggers can also start work. Electron, browser, and terminal clients communicate with an api-server over HTTP/SSE, while skills provide tool-scoped subagents and MCP servers extend the system. The project supports model providers including Amazon Bedrock, Anthropic, Google Gemini, OpenAI, OpenRouter, and Ollama. It stores application state locally, requires explicit folder permissions for local file access, and is distributed under the Apache 2.0 license with desktop installers for macOS, Windows, and Linux.

Unkey is a developer platform that combines API deployment, gateways, and observability into a single service for building and operating modern APIs. It presents tools for deploying, managing, and monitoring APIs under one platform.

Amazon Nova Act is an AWS service for building and managing AI agents that automate production UI workflows in web browsers. Workflows combine natural-language act() calls with Python code: each act() runs an agentic loop in which the model observes a page and takes sequential actions, while sessions group browser or API-client interactions and workflows orchestrate the overall task. Nova Act supports browser data entry, extraction, checkout flows, and web QA testing, can escalate to a human supervisor, and connects to external tools through API calls, remote MCP, and agentic frameworks such as Strand Agents. Workflows can be explored in a web playground, developed with an IDE extension and Python SDK, deployed to AWS, and monitored in the AWS Management Console. Introduced as a research preview, Nova Act is now offered as a production service on AWS through the Amazon Nova API.

Zapier is an automation and AI orchestration platform for connecting business applications, data, AI models, and agents. Its workflows use triggers and actions to move information between tools and perform tasks such as formatting new Asana projects, connecting incoming email to OpenAI for a customer-service workflow, scheduling recurring scrapes, and sending notifications when qualifying data appears. The Zapier site says it supports workflows and agents across more than 9,000 app integrations, with governed access, model management, and guardrails. It also provides Zapier MCP for connecting AI clients such as Claude, ChatGPT, Cursor, and OpenClaw to configured tools, plus a beta Zapier SDK and SDK CLI for building integrations.