Lets-Fafo · Hugging Face
You can FAFO.
Your AI shouldn't.
FAFO™ is Fully Autonomous Foundational Orchestration: a self-hosted platform where AI agents complete assigned work inside explicit scope, budgets, independent review and an audit trail. The operator defines intent. AgentOS derives execution.
Why governed work
AI can answer questions. Organizations need work completed.
Ungoverned AI keeps organizations in pilot mode. Autonomous work needs the accountability human teams already have. A leader should be able to answer these seven questions in seconds.
- Who
Who did the work?
- Why
Why was it allowed?
- Grounding
What grounding was used?
- Change
What changed?
- Evidence
What evidence exists?
- Cost
What did it cost?
- Trust
Can you trust it?
Products
Four parts. One governed loop.
The platform, code, weights and local models run inside your perimeter. Frontier model use is optional and governed.
Governs the workFAFO™ AgentOS
Authority, evidence, recovery and economics for each unit of work. Self-hosted, on Linux.
Learn more ↗
Grounds the workFAFO™ Memory
Code, decisions and references, retrieved by meaning and handed to each worker before it acts.
Learn more ↗
Runs the workFAFO™ Agent Swarm
Specialized AI agents, governed end to end and replaceable when they fail.
Learn more ↗
Powers the workFAFO™ Inference Fabric
A GPU saturation layer for NVIDIA inference.
Learn more ↗
What we publish here
Models we adapted and measured on our own hardware.
Each model card says exactly what changed, which hardware and software it was tested on, and what we measured. Nothing beyond that.
Quantized model · Apache-2.0
Qwen3.8-27B-FAFO-W4A16-G32-B70
1,798 tokens per second total throughput from one Intel Arc Pro B70 (32 GB). Qwen3.8-27B reduced from 55.6 GB of BF16 weights to a 20.6 GB W4A16 checkpoint, validated only on the B70 with Intel's XPU build of vLLM.
Open the model card ↗in + out, 32 clients, prefix caching on
from 55.6 GB BF16
generated tokens, sustained, 64 clients
single card, no failures
MeetFAFO · public experiment
AI runs the businesses. We publish the results.
AI teams build products, run marketing and serve customers. Humans approve the direction. We publish the revenue, the costs and the lessons.
FAFO's work orchestration and evidence systems, applied to creating and operating real businesses. Status: preparing the first release.
Convergence Information Foundry Research Systems LLC · Sheridan, Wyoming, United States. Model releases in this organization are published by Neuro Forge, LLC.
FAFO™ is a trademark of Convergence Information Foundry Research Systems LLC. Patent pending.