Mace Innovations
Fabric · Multi-Agent Dev Platform

Run a matrix of AI coding agents.

Fabric runs a configurable matrix of live Claude Code sessions — a tidy 3×3 by default, or as many panes as you (and your hardware) can handle — all building, testing, and shipping in parallel on infrastructure you control.

Book a demo →See our results
// The Matrix — configurable panes · 3×3 shown
agent-01RUN
auth · middleware
● editing verify.ts
✓ 24 tests passing
agent-02
api · /quote
● writing handler
→ zod schema added
agent-03
ui · dashboard
● <DataTable/>
✓ build clean
agent-04
db · migration
● 0007_index.sql
→ applied
agent-05
infra · terraform
● main.tf
✓ plan ok
agent-06
review · PR #482
✓ 0 findings
→ approved
agent-07
tests · e2e
● contact flow
✓ 12 / 12
agent-08
docs · runbook
● README.md
→ 3 sections
agent-09
deploy · preview
→ vercel build
✓ live
1 · 2×1 · 1×2 · 2×2 · 3×3 — pick your layout, then scale to whatever your machines can take
// What you get

One screen. An entire AI dev team.

Persistent pane grid

Pick a layout — 1, 2×1, 2×2, 3×3 and beyond. Each pane is its own Claude Code session that keeps state and history, auto-reconnects on drop, and can be dragged, labeled, and color-coded.

Fabricator

Describe a change in plain English. An agent spins up an isolated workspace, branches, commits, pushes, and opens a PR — with full logs and diffs the whole way.

Mend

PRs that need work get a one-shot, context-aware fix — or promote to interactive chat and steer it turn by turn. Review → fix → merge without leaving Fabric.

Hypervisor agents

Overnight, supervisor agents read the day's transcripts and commits and surface ranked recommendations — new rules, tighter permissions, docs — with one-click actions.

MCP connectors

Wire your databases, APIs, and custom tools into every agent over the Model Context Protocol — local or remote, with encrypted credentials.

Your context, inherited

Every agent automatically inherits your org, company, and project rules — so a whole wall of sessions builds the way your team does.

// Compliance & audit

Every session, on the record.

Every keystroke, command, agent response, and tool call — in every pane and every Mend session — is captured to an append-only, encrypted transcript: input and output, per user, per project. When compliance asks what the AI did and when, you have the receipts.

Append-only & encryptedSecrets auto-redactedTenant-isolatedAudit-ready
matrix_pane_events · agent-02
14:02:11user▸ refactor the /quote handler
14:02:13agent● editing app/api/quote/route.ts
14:02:19tool✓ 24 tests passing
14:02:24agent→ opened PR #482
14:02:25redact[redacted: GITHUB_TOKEN]
// Run it anywhere

Your cloud, or your hardware.

Fabric is the orchestration layer; the compute is yours. Each user gets an isolated Linux workspace with hard resource limits, and a new host joins the matrix with a single install script — so your code and context never leave your environment.

AWS

Your AWS account

Spin up workspace hosts on EC2 or Fargate inside your own VPC. Fabric orchestrates the grid; AWS keeps the metal.

AZURE

Your Azure tenant

Run the matrix on Azure VMs or Container Apps in your subscription, with your networking and policies.

BYO

Bring your own hardware

Point Fabric at bare-metal or on-prem boxes. Perfect for air-gapped or compliance-bound teams.

Ready to scale your AI development?

See Fabric run a live matrix against your stack. We'll stand it up on your cloud or ours.

Book a demo →