Membria.AI · Partnerships

Build with the memory layer for AI agents.

We are looking for technology and infrastructure partners to bring persistent, auditable agent memory to more teams, clouds and data centres.

02

Company

Who We Are

Actiquest Labs

Applied AI Systems Company

Practical automation, intelligent workflows and enterprise-grade AI — built for real results.

Membria.AI

AI Operating Environment

Our core product — agents, memory, knowledge and verification combined into one enterprise-ready AI platform.

Vertical Expertise

Code · Fintech · Government · Audit · EPC

We specialize in complex domains where AI needs precision, context and process understanding.

How We Work

Applied AI Engineering

We ship enterprise AI projects that stress-test and fund Membria's core — concept to production.

03

Company Profile

Actiquest Labs at a Glance

Key facts, production footprint and enterprise AI capabilities.

10+

years enterprise product, AI engineering and venture-building

4

verticals — Fintech · Government · Audit · Engineering/EPC

100+

seats deployed across production AI use cases

Metric	Value
Founded	February 2023 · California, USA
European Presence	Belgium entity · relocation to Luxembourg planned
Core Product	Membria.AI — memory & experience layer for AI agents
Production Verticals	SDLC · Fintech/Banking · AI Accounting/Audit · Engineering/EPC
Deployment	Cloud SaaS · self-hosted · on-premise enterprise
Clients & Partners	OES · Wowcube · Hiscox · K-Telco · Kazakhstan Government · industrial enterprises across EMEA/CIS
Technology Partners	NVIDIA · Amazon Web Services · LuxProvide
Team	core team of 4 · 20+ years enterprise software & audit · 9 years applied AI — finance, government, industrial, deep-tech

04

Opportunity

Why partner with Membria

1.

Agents became the workforce

Claude Code, Codex and Cursor do real daily work in code, engineering and finance — but they ship without memory. Membria adds it.

2.

One integration, every agent

MCP plugs a memory plane into any agent on the market — technology partners connect once instead of building per-vendor integrations.

3.

Sovereign & regulated by design

EU AI Act and ISO 19650 require defensible decisions and audit trails. Membria runs cloud, self-hosted or on-premise — a fit for sovereign and regulated infrastructure.

4.

Experience compounds with every partner

Nobody owns the decision → outcome graph yet. Every deployment strengthens the shared knowledge graph that all partners build on.

05

Product

Membria Reasoning Graph Workforce

Institutional knowledge Memory pillars

Memory

Decisions — every choice captured with its reasoning
Consistency — behavior chains keep teams aligned
Skills — wins distilled into reusable know-how
NegativeKnowledge — failures become rules

Multi-agent harness Reasoning pillars

Reasoning

Mesh — many agents work in parallel
Coordination — agents hand off via A2A
Routing — each task to the right model
Quality gates — verification blocks bad output

Domain-agnostic foundation Graph pillars

Graph

GraphRAG — semantic search over a property graph
Multi-domain — one schema across every domain
Orchestration — work runs as a dependency graph
Adaptive — memory that strengthens with use

06

How it works

One loop, every stage

Not a memory bolted onto one step — every shipped outcome feeds the next decision.

01

Plan

Recalls decisions and outcomes from similar work — the agent starts from what already worked.

02

Execute

Injects validated skills and blocks known anti-patterns as the work is being done.

03

Review

Checks the result against past failures and standards — deterministic critics, auditable output.

04

Ship

Records the real outcome and links it back to the decision that caused it.

↺ Every outcome feeds the next decision. One MCP connection: npx @membria/cli init

07

Why Membria?

Core Capabilities

The full stack — from memory and reasoning to deployment and governance

AI Agent Orchestration

Multi-agent BBS mesh, WorkGraph DAG, A2A protocol coordination

Causal Memory

Decision / Outcome / NegativeKnowledge graph with time-decay and compounding

Verification Engine

Cross-document consistency checks, rule-based normative validation, quality gates

Graph Intelligence

Memgraph property graph, symbol-level CodeGraph, policy graph with Hebbian co-activation

LLM Integration

Claude / GPT factory, structured output, behavior chains, context injection

Product Engineering

Full-stack: FastAPI + React + Node.js, MCP protocol, Telegram, Web Dashboard

Domain AI Systems

Vertical-specific schemas, critics, standards compliance (ISA / API / ASME / IEC)

Security & Governance

PolicyEngine, RBAC, OIDC/SSO, prompt injection defense, secrets management

Bottom line: Generic AI forgets. Membria remembers, reasons, and governs.

08

Focus

One core, many domains

Verticals are distribution of one product — not divergence. The same graph schema ships verbatim in every codebase.

Product	Who buys	Delivery	Status
Membria CE	solo developers on Claude Code / Codex / Cursor	cloud SaaS · zero-install MCP	SaaS · code.membria.ai
Membria Enterprise	engineering & product teams	self-hosted platform · own UI	Demo · design partners
AI-EPC	EPC contractors & design institutes	vertical app on the same core	Live demo · epc.membria.ai
Glass	accounting & audit teams	vertical app on the same core	Design-partner stage

Proof of substrate: Decision · Outcome · NegativeKnowledge · Skill — one schema, one causal experience loop, shared verbatim across every codebase. A vertical competitor can't follow us across domains; we can.

09

Projects

What we are building

[One sentence: how these projects show the platform in production.]

Project	Customer / domain	What we built	Status
[Project 1]	[Customer · industry]	[What we built — one line]	[Status]
[Project 2]	[Customer · industry]	[What we built — one line]	[Status]
[Project 3]	[Customer · industry]	[What we built — one line]	[Status]
[Project 4]	[Customer · industry]	[What we built — one line]	[Status]
[Project 5]	[Customer · industry]	[What we built — one line]	[Status]
[Project 6]	[Customer · industry]	[What we built — one line]	[Status]

[Takeaway]: [what these projects prove for a technology or infrastructure partner.]

10

Case study · 01

[Project name] [result in 2–4 words]

[Customer · industry · country · year]

1.

Challenge

[What problem the customer had — 1–2 sentences.]

2.

What we built

[Solution and how Membria is used — agents, memory, verification, deployment model.]

3.

Result

[Measured outcome in production — time saved, errors avoided, adoption.]

[00%]

[metric 1]

[00x]

[metric 2]

[00]

[metric 3]

Stack & partners: [technologies, cloud / infrastructure, partners involved]

11

Case study · 02

[Project name] [result in 2–4 words]

[Customer · industry · country · year]

1.

Challenge

[What problem the customer had — 1–2 sentences.]

2.

What we built

[Solution and how Membria is used — agents, memory, verification, deployment model.]

3.

Result

[Measured outcome in production — time saved, errors avoided, adoption.]

[00%]

[metric 1]

[00x]

[metric 2]

[00]

[metric 3]

Stack & partners: [technologies, cloud / infrastructure, partners involved]

12

Case study · 03

[Project name] [result in 2–4 words]

[Customer · industry · country · year]

1.

Challenge

[What problem the customer had — 1–2 sentences.]

2.

What we built

[Solution and how Membria is used — agents, memory, verification, deployment model.]

3.

Result

[Measured outcome in production — time saved, errors avoided, adoption.]

[00%]

[metric 1]

[00x]

[metric 2]

[00]

[metric 3]

Stack & partners: [technologies, cloud / infrastructure, partners involved]

13

Team

The people behind it

[One sentence: combined experience and why this team can deliver for partners.]

Michael Aprossine

CEO · Co-Founder

[2–3 sentences: background, years of experience, what Michael owns at Membria.]

Focus: platform architecture, enterprise delivery
Previously: [companies / projects]

Philippe Khomenok

COO · Co-Founder

[2–3 sentences: background, years of experience, what Philippe owns at Membria.]

Focus: strategic vision, go-to-market and growth
Previously: [companies / projects]

Mike Keer

CTO

[2–3 sentences: background, years of experience, what Mike owns at Membria.]

Focus: memory & reasoning systems — fast, reliable, built to scale
Previously: [companies / projects]

Mayya Aprosina

UI/UX

[2–3 sentences: background, years of experience, what Mayya owns at Membria.]

Focus: product design across CE, EPC and Code surfaces
Previously: [companies / projects]

14

Partnership models

Technology & infrastructure

Two partner tracks — pick one or combine them.

Technology

Agent & developer platforms

Agent, IDE and workflow platforms embed Membria memory through MCP and A2A — your users get persistent, auditable experience out of the box.

Technology

AI, data & tooling vendors

Connect your models, data pipelines or engineering tools to the shared knowledge graph: memory, verification and standards as a service inside your product.

Infrastructure

Cloud & HPC providers

Host Membria for sovereign, self-hosted and on-premise deployments — with a joint route to enterprise and public-sector buyers.

Infrastructure

GPU & hardware vendors

Co-optimise graph and inference workloads for your platform and publish reference deployments for AI-agent memory at scale.

Flexible by design: commercial terms are agreed per partner. Start with a pilot, scale what works.

15

Moat

Three EMPIRIA graphs, day one

Cold start is the hardest problem in agent memory. We don't have one — every vertical ships with a pre-loaded PK/NK library before a single client session runs.

Vertical	PK — best practices	NK — anti-patterns / prohibitions	Source	Status
Engineering (EPC)	~1.3M	~1.2M	20,000+ standards — ISO · IEC · ASTM · ГОСТ · API · ASME · NFPA · DNV	Live · Scaling · epc.membria.ai
Code	~250K Skills	~320K AntiPatterns	96.5K mined repos + curated sources, CWE-mapped	Live · Scaling · code.membria.ai
Audit / Glass	schema live	schema live	materiality & provenance graph — seeding from client engagements	Design-partner stage

Same schema, same loop, three domains. A generic memory startup starts every client at zero. We start every client already knowing what fails.

16

How we start

From first call to co-launch

A short, low-risk path — you see the value before committing.

01

Align

Share your platform or infrastructure and the customers you serve; we map where memory, verification or knowledge add value.

02

Pilot

Connect with one command and run a scoped pilot on your own stack, with our engineers alongside.

03

Integrate

Embed Membria or deploy it on your infrastructure; agree deployment model, support and security review.

04

Co-launch

Go to market together: reference deployments, joint case studies and a shared pipeline.

Start in minutes: npx @membria/cli init — then talk to us at hi@actiq.ai

17

Let's build the layer
agents can't work without.

Partner with us

Let's Build Together

Michael Aprossine

CEO · Co-Founder

Platform architecture, enterprise delivery

Philippe Khomenok

COO · Co-Founder

Strategic vision, go-to-market and growth

Mike Keer

CTO

Memory & reasoning systems — fast, reliable, built to scale

Mayya Aprosina

UI/UX

Product design across CE, EPC and Code surfaces

Partner with us	Detail
Who we look for	technology: agent & developer platforms, AI, data and tooling vendors · infrastructure: cloud, HPC, GPU and hardware providers
Proof	1 bank + 1 government live enterprise · 100+ seats deployed · technology partners NVIDIA · AWS · LuxProvide
Next step	30-minute intro call, then a scoped pilot
Contact	hi@actiq.ai · membria.ai · code.membria.ai · epc.membria.ai