TAFFEE: The Agent Factory Framework for Enterprise Enablement

Bootstrap your enterprise AI, without sinking the bootstrapping cost.

An open foundation for enterprise AI agents. Up and running in hours, entirely inside your enterprise. A path to production, not a prototype.

Apache-2.0Runs inside your enterpriseYour data stays yoursNo lock-in

The cost you skip

Building the foundation yourself ⓘOur estimate: five engineers for six months at about $200K per engineer per year, fully loaded (US mean software-developer wage from the BLS, plus benefits).

~$500K · ~6 months

of engineering before the first agent delivers value

With TAFFEE

Up in hours

Start from an open foundation, inside your enterprise. Free and Apache-2.0.

The TAFFEE Opportunity

Why a shared foundation, and why now.

Agents are going mainstream faster than enterprises can build the foundation underneath them. Select a step to see the evidence.

TAFFEE · The opportunity

Build the foundation once. Every team builds on it.

Before the first agent does useful work, every enterprise builds the same five things. Build them once, as open software inside your enterprise, and every team after the first starts from a working base.

Context

One shared, up-to-date view of your code and knowledge for every agent.

Capabilities

Connect once to your tools, APIs and data, and reuse them everywhere.

Governance

One policy for what agents may do, with credentials and an audit trail.

Orchestrator

Run agents reliably, check their work and stay within budget.

Telemetry

One view of what every agent did, what it cost and how long it took.

Reference architecture

How the five pillars fit together

Five TAFFEE pillars, each independent. The grey boxes are yours to bring; TAFFEE connects to them.

TAFFEE reference architecture: Context, Capabilities and Governance on the left, the Orchestrator with its outer and inner loops in the centre, Telemetry along the bottom; clients, the AI gateway, model router, model providers and tools and data are yours to bring.

Get early access

Be first to know when TAFFEE goes public.

The repositories are private while we finish v1. Leave your details and we'll let you know.

We'll use this only to tell you when TAFFEE goes public and, if you ask, to invite you to the repositories. Never shared. To be removed, email [email protected].