Inside PixiJS, AT Protocol, and Modern Game Development with Trezy Who

A high-performance content optimization system that serves pre-rendered markdown versions of web page content to LLM bots.

Repo

A high-performance content optimization system that serves pre-rendered markdown versions of web page content to LLM bots.

Marianne Dillard

Forward Deployed Engineer

Repo

Markdown Prerender Template

Marianne Dillard

A high-performance content optimization system that serves pre-rendered markdown versions of web page content to LLM bots.

Repo

Markdown Prerender Template

Marianne Dillard

Repo

Markdown Prerender Template

A high-performance content optimization system that serves pre-rendered markdown versions of web page content to LLM bots.

Marianne Dillard

Harper 5.1 ships three layered AI capabilities: a provider-agnostic Models API supporting OpenAI, Anthropic, Bedrock, and Ollama; a built-in agentic loop via toolMode: 'auto' with hard budget controls; and an opt-in Harper Agent component. Switching providers is a config change, not a code change.

Harper's AI Stack: Models API, Agent Loop, and Built-in Agent

A.I.

Tutorial

Harper 5.1 ships three layered AI capabilities: a provider-agnostic Models API supporting OpenAI, Anthropic, Bedrock, and Ollama; a built-in agentic loop via toolMode: 'auto' with hard budget controls; and an opt-in Harper Agent component. Switching providers is a config change, not a code change.

Kris Zyp

SVP of Engineering

Harper 5.1 ships three layered AI capabilities: a provider-agnostic Models API supporting OpenAI, Anthropic, Bedrock, and Ollama; a built-in agentic loop via toolMode: 'auto' with hard budget controls; and an opt-in Harper Agent component. Switching providers is a config change, not a code change.

Harper's AI Stack: Models API, Agent Loop, and Built-in Agent

Harper 5.1 ships three layered AI capabilities: a provider-agnostic Models API supporting OpenAI, Anthropic, Bedrock, and Ollama; a built-in agentic loop via toolMode: 'auto' with hard budget controls; and an opt-in Harper Agent component. Switching providers is a config change, not a code change.

Harper's AI Stack: Models API, Agent Loop, and Built-in Agent

Harper 5.1 ships three layered AI capabilities: a provider-agnostic Models API supporting OpenAI, Anthropic, Bedrock, and Ollama; a built-in agentic loop via toolMode: 'auto' with hard budget controls; and an opt-in Harper Agent component. Switching providers is a config change, not a code change.

Harper's AI Stack: Models API, Agent Loop, and Built-in Agent

Harper 5.1 introduces native MCP support, auto-generating secure tools from your application schema so agents can access data, invoke operations, and connect through standard clients without adapter code or infrastructure.

Harper 5.1 Makes Your Applications MCP-Native

Blog

Harper 5.1 introduces native MCP support, auto-generating secure tools from your application schema so agents can access data, invoke operations, and connect through standard clients without adapter code or infrastructure.

Kris Zyp

SVP of Engineering

Harper 5.1 introduces native MCP support, auto-generating secure tools from your application schema so agents can access data, invoke operations, and connect through standard clients without adapter code or infrastructure.

Harper 5.1 Makes Your Applications MCP-Native

Harper 5.1 introduces native MCP support, auto-generating secure tools from your application schema so agents can access data, invoke operations, and connect through standard clients without adapter code or infrastructure.

Harper 5.1 Makes Your Applications MCP-Native

Harper 5.1 introduces native MCP support, auto-generating secure tools from your application schema so agents can access data, invoke operations, and connect through standard clients without adapter code or infrastructure.

Harper 5.1 Makes Your Applications MCP-Native

Harper was named a 2026 Gartner Hype Cycle for Digital Commerce Sample Vendor, recognized in Front-End Cloud for its unified runtime combining data, application logic, messaging, and agent development together.

Harper Named a Sample Vendor in the Gartner® Hype Cycle™ for Digital Commerce, 2026

Announcement

News

Harper was named a 2026 Gartner Hype Cycle for Digital Commerce Sample Vendor, recognized in Front-End Cloud for its unified runtime combining data, application logic, messaging, and agent development together.

Harper

Harper was named a 2026 Gartner Hype Cycle for Digital Commerce Sample Vendor, recognized in Front-End Cloud for its unified runtime combining data, application logic, messaging, and agent development together.

Harper Named a Sample Vendor in the Gartner® Hype Cycle™ for Digital Commerce, 2026

Harper

Harper was named a 2026 Gartner Hype Cycle for Digital Commerce Sample Vendor, recognized in Front-End Cloud for its unified runtime combining data, application logic, messaging, and agent development together.

Harper Named a Sample Vendor in the Gartner® Hype Cycle™ for Digital Commerce, 2026

Harper

Harper was named a 2026 Gartner Hype Cycle for Digital Commerce Sample Vendor, recognized in Front-End Cloud for its unified runtime combining data, application logic, messaging, and agent development together.

Harper Named a Sample Vendor in the Gartner® Hype Cycle™ for Digital Commerce, 2026

Harper

Rails proved that opinionated frameworks make developers faster. Now AI-native, distributed applications need the same kind of defaults for data, logic, caching, and messaging.

Rails Won Because It Had Opinions. AI-Native Apps Need the Same Thing.

A.I.

Blog

Rails proved that opinionated frameworks make developers faster. Now AI-native, distributed applications need the same kind of defaults for data, logic, caching, and messaging.

Aleks Haugom

Senior Manager of GTM