DCYFR Labs

Open-source AI agent infrastructure, built by a security architect. Multi-provider agents with plugin sandboxing, delegation, and quality gates — TypeScript-strict, tree-shakeable, MIT.

Think Freely. Build Securely. Ship Boldly.

Explore DCYFR AI Browse open source

Years security architecture

Industry certifications

Open-source packages & components

DCYFR AI

Portable multi-provider agent framework with telemetry, quality gates, and a plugin marketplace.

Explore

Open Source

MIT-licensed npm packages for AI agents, CLI tooling, RAG, and code generation.

Explore

Release notes for the @dcyfr/ai v3 line of the AI agent harness

Latest Research

What's New in @dcyfr/ai: The v3 Line

A catch-up release note on where the AI harness landed across the v3.x releases

A short, honest changelog: what shipped in the @dcyfr/ai v3.x line, what changed for people building on it, and what comes next — catching the blog up with work the package already produced.

June 22, 20267 min read

By Drew (dcyfr) · 25 certifications · 6+ yrs security architecture

Read post

From the blog

All articles

DevSecOps

Kill Switches for Autonomous Agents

Aug 202618 min

Autonomous AI Agents: From Assistants to Automation

Jul 202615 min

AI Assistants as Development Partners

Mar 202613 min

@dcyfr/ai · Open Source · MIT

DCYFR AI

Portable framework with plugin architecture, multi-provider support (OpenAI, Anthropic, Ollama), built-in telemetry, and quality gates. TypeScript-strict, tree-shakeable.

Plugin ArchitectureMulti-ProviderBuilt-in TelemetryQuality Gates

Browse by topic

Next.js6 AI5 TypeScript5 Security4 Agents3 Architecture3 MCP3 React3 DevSecOps2 Automation2

DCYFR Labs

Explore DCYFR Labs

What's New in @dcyfr/ai: The v3 Line

From the blog

DCYFR AI

Stay in the loop

Browse by topic