Independent Product Company · Cloudflare Edge Native

Data, commerce, and automation products built to be used.

BirruLabs builds and operates edge-native digital products. Our focus is commerce intelligence, shared agent infrastructure, and auditable operational automation that can mature through sustained use.

Product Focus
  • Data & Commerce Intelligence
  • Edge-Native Products
  • Shared Agent Infrastructure
  • Operational Automation
BL / SYS-01

Reference architecture

Controlled flow
01 / INPUTStructured brief
02 / ROUTEOrchestrator
01Research
02Create
03Validate
03 / APPROVEHuman gate
04 / TRACERelease + audit log
Agents execute the work. People retain every critical decision.

01 / Product principles

A product earns trust when its status, boundaries, and operational evidence can be inspected.

That is why we treat AI and automation as product infrastructure—not as standalone marketing claims.

01

Boundaries before intelligence

Permissions, data sources, failure conditions, and completion criteria are designed before a model or agent receives execution access.

02

Evidence before claims

Release stages, decisions, tests, and usage evidence matter more than marketing numbers that cannot be verified.

03

Operations before expansion

Products are strengthened through observability, data ownership, recovery paths, and real feedback before scope is expanded.

02 / Flagship products

Three systems that define the BirruLabs product direction.

Flagships are selected for their proximity to real use, sustained operation, and verifiable value—not simply because the technology looks impressive.

01
15ms EDGE
SYS-BF / AMAZON & TG
LIVE SCHEMATIC
BL / ARCH-VECT
ProductionEdge CommerceEdge Execution: < 15ms Worldwide

BirruFinds & Affiloom

Problem
Autonomous affiliate product discovery engine built on Cloudflare Edge Workers, D1, and R2.
Product System
BirruFinds is an autonomous edge commerce engine automating product curation, brand CDN metadata extraction, Amazon affiliate tag injection, and broadcast distribution to Telegram channels and Pinterest with zero server overhead.
02
SYS-SYS / AGENT-CONTEXT-MCP
LIVE SCHEMATIC
BL / ARCH-VECT
ProductionAI InfrastructureSync Latency: Instant / Global

Agent Context Hub & Zero-Amnesia Vault

Problem
Encrypted multi-agent memory and shared task coordination protocol synced 24/7 to Cloudflare Edge and GitHub.
Product System
Standard MCP protocol infrastructure solving multi-session agent amnesia. Coordinates shared task boards, inter-agent handoff notes, architecture decision records (ADRs), and encrypted credential vaults across disparate agent runtimes.
03
CEORESEARCHCREATIVEQCPUBLISH
SYS-SMM / MULTI-AGENT CEO
LIVE SCHEMATIC
BL / ARCH-VECT
Live BetaAI AgentsAgent Nodes: 4 Specialized Workers

Social Media AI Manager (Hermes Swarm)

Problem
Multi-agent system for end-to-end social media orchestration using the CEO/Worker pattern.
Product System
Distributed multi-agent AI system managing the entire content lifecycle: real-time trend research, brief crafting, visual asset generation, automated QC validation, and scheduled publishing across Meta & Threads.
View the portfolio by maturity level
VERIFIABLE EDGE ARCHITECTURE

Cloudflare services are used where they solve a verified product need.

Each product documents its actual runtime, data store, deployment evidence, and recovery path. Planned services remain clearly separated from production architecture.

Cloudflare Workers

Request handling, APIs, server rendering, and controlled background work.

Cloudflare D1

Relational product state, catalog records, and auditable application events.

Cloudflare R2

Object storage for owned media, raw snapshots, exports, and recovery evidence.

Cloudflare KV

Non-secret configuration and coordination metadata. Credentials stay in approved secret stores.

Edge Commerce Product

BirruFinds Commerce

Product catalog, editorial discovery, and affiliate redirect workflows running through Cloudflare Workers and D1.

CURRENT STACK:
Cloudflare WorkersD1 SQLiteR2 StorageGitHub Actions
birru-finds.edge.ts
REFERENCE FLOW
// Cloudflare Worker: verified catalog response
export default {
  async fetch(request: Request, env: Env) {
    const products = await env.DB.prepare(
      "SELECT slug, title, category FROM products WHERE status = ? LIMIT 20"
    )
      .bind("published")
      .all();

    return Response.json({
      source: "birrufinds-d1",
      products: products.results
    });
  }
};

03 / How we build

From a real problem to a verified operational product.

  1. 01

    Frame

    Map users, problems, risks, data sources, and success criteria before choosing technology.

  2. 02

    Architect

    Define data contracts, execution permissions, failure modes, ownership, and recovery paths.

  3. 03

    Validate

    Test product flows under realistic conditions and retain outcomes as evidence and improvement input.

  4. 04

    Operate

    Run with observability, rollback, and operator intervention before expanding users or features.

04 / Operating infrastructure

Not one giant prompt. A traceable operating chain.

Every stage has an input, owner, evidence, and completion condition so agents can continue work without turning the owner into a courier.

01ACTIVE STAGE

The brief enters as structured data.

Goals, constraints, sources, and the definition of done are set before any agent acts.

SYSTEM EVIDENCEInput schema + explicit scope

06 / Product roadmap

Follow the products we are maturing toward real use.

Our portfolio separates flagships, active products, and experiments transparently. Explore the status, architecture, and available evidence for every system.

Explore All ProductsFlagship products · Active releases · Transparent experiments