Shared vocabulary, pure logic, and port interfaces for the Agent Architecture Board.

Pricing tables and spend metering for the Agent Architecture Board.

Valibot wire contract shared between the Agent Architecture Board frontend and backend.

Tenancy base services (workspaces and accounts) for the Agent Architecture Board.

Agent catalog, routing, prompts and fragment library for the Agent Architecture Board.

AI Agent runtime — Harness Agent architecture + Agentic Loop engine

External-system integration domain logic for the Agent Architecture Board (GitHub, documents, tasks, environments, runners).

Cross-agent architecture skills for @adobe/data — installable as a Claude Code plugin or copied into any Agent-Skills-compatible agent (Cursor, Codex).

Core AI chat agent with multi-agent architecture, ReAct pattern, and modular tool system powered by Gemini

Delivery-workflow engine for the Agent Architecture Board (execution, bootstrap, pipelines, board, boardScan, requirements, and composition root).

Curated skill pack — 20 skills imported from ECC (github.com/affaan-m/ECC). Agent architecture, autonomous loops, testing patterns, DevOps patterns.

Opt-in AWS Bedrock model registry for the Agent Architecture Board's AI provisioning facade. Mix into a CompositeModelProvider to add the `bedrock` provider.

Opt-in OpenTelemetry (OTLP) trace + metrics publisher for the Agent Architecture Board. Streams LLM generations and container tool spans to any OTLP/HTTP backend — the workerd-safe fetch exporter on the Cloudflare Worker facade, the official @opentelemetr

Reusable Nuxt layer for the Agent Architecture Board SPA (components, stores, composables, pages). Consume it from a thin deployment app via `extends: ['@cat-factory/app']` and point it at your backend with NUXT_PUBLIC_API_BASE. See deploy/frontend for an

Opt-in AWS S3 blob backend for the Agent Architecture Board's binary-artifact storage abstraction. Implements the kernel BinaryBlobBackend port over an S3 bucket.

Opt-in Langfuse trace sink for the Agent Architecture Board. The workerd-safe OTLP/HTTP exporter pointed at Langfuse's OpenTelemetry endpoint, so LLM generations and container tool spans stream unchanged on both the Cloudflare Worker and Node facades.

Evolve SDLC CLI — Multi-Agent Architecture Lifecycle & Governance Tool for AI Coding Agents

Super multi-agent architecture: files are messages, adoption replaces all-hands-on-deck failure, term leases replace single points, invariants replace trust, timelines replace non-reproducibility, one file serves humans and machines. Every claim carries a

Node.js runtime facade for the Agent Architecture Board: serves the shared @cat-factory/server Hono app via @hono/node-server, wiring Node implementations of the runtime ports (persistence, gateways, model provisioning).

Runtime-neutral HTTP layer for the Agent Architecture Board: the Hono controllers, middleware (auth/authz/CORS/error), request helpers and the gateway seams shared by every deployment facade (Cloudflare Worker, Node service).