Prostir
로그인
얼리 액세스

Tech

Cloud-native AI platform, built on enterprise .NET from day one.

The prompt is the easy part. The hard part is surviving a million MCP calls a week. We built that on .NET 10, Orleans, Aspire, and the Microsoft Agent Framework: today's distributed .NET for virtual actors, typed AI, and cloud-native ops.

24× less energy than Python

Measured by the Pereira study, University of Minho. Same job in each language.

99.99% uptime, on Azure

The service guarantee behind everything Prostir runs.

97M+ MCP SDK downloads a month

Real, fast-growing adoption of the protocol Prostir speaks.

100 PageSpeed on this page

A static Astro build, fast for people and crawlers alike.

The journey

Your idea is one prompt. Production is ten enterprise layers.

Every AI demo looks the same inside ChatGPT. The real gap is between that demo and a customer who keeps paying, and that is where most teams stall. So here is ours, from the compiled floor up to the public URL. Ten layers. Each one is the dull, dependable choice. Each one is a reason someone with no code can still ship a real product.

  1. 01 The Foundation

    .NET 10 and C#: fast, green, compiled.

    Every story needs solid ground. Ours is compiled .NET. We did not start with Python or Node, because at scale small differences turn into big bills. A University of Minho study measured the energy each language burns for the same task. C# uses about 3× the energy of raw C. Python uses about 76×. So one job in Python can burn the energy, and the carbon, of roughly twenty-four .NET servers. Multiply that across a fleet of 18,000 public MCP servers and the language you choose becomes your cloud bill and your climate bill at once. Safety matters too. The npm and PyPI worlds are huge, and supply-chain attacks hit them again and again. NuGet is smaller, signed, and a far smaller target. So C# is the greenest, and one of the safest, lines of code on this page, and ASP.NET Core stays near the top of every TechEmpower speed test.

    • net10.0
    • ASP.NET Core 10
    • C# 14 + Native AOT
    • Source generators
    • Top-tier TechEmpower

  2. 02 The Cloud

    Azure: enterprise-grade, compliant, global.

    A demo runs on a laptop. A product a stranger pays for has to run somewhere a regulator, a hospital, and a CFO all trust. That is Azure. It carries the broadest compliance list in the cloud: GDPR, HIPAA, SOC, ISO 27001, PCI DSS, FedRAMP. It backs the services Prostir uses with uptime guarantees up to 99.99%. Your agent and its data live in the region you pick, in the EU or the US, and Azure's global network keeps them close to your customers. You wire up no datacenters yourself. Compliance, uptime, and reach are not things you add later. They are where a paid product has to start.

    • Azure Container Apps
    • Cosmos DB Serverless
    • Azure Blob + Monitor
    • GDPR · HIPAA · SOC 2 · ISO 27001
    • 99.99% SLA · EU + US regions

  3. 03 The Local Bridge

    Aspire: one AppHost, real integration tests.

    Mocks lie. Aspire does not. One file, the Prostir.AppHost, wires together Cosmos DB, Azure Storage, the Orleans cluster, the API, the MCP gateway, and the operator console. The same setup runs on your laptop, in CI, and in the cloud. Our tests run against the real services Aspire starts, never against fakes. That is the only way a codebase an AI helped write stays honest. If it passes here, it passes in production, because here and production are the same wiring.

    • Aspire AppHost SDK
    • Aspire.Hosting.Azure.CosmosDB
    • Aspire.Hosting.Azure.Storage
    • Aspire.Hosting.Orleans
    • TUnit.Aspire

  4. 04 The Distributed Runtime

    Orleans: every agent gets a digital twin.

    Here is the one idea that makes the rest simple. Orleans gives every agent a virtual actor. Think of it as a digital twin: a software copy of a real thing, an agent, a customer, that keeps its own memory and does its own work in its own sealed room, untouched by anyone else. Once everything is a twin, the work stops being about servers and becomes about objects talking to each other. You just describe who sends what message to whom: a person to a twin, a twin to another twin. That is the whole model. It is old and proven. Erlang ran phone networks this way for decades with almost no downtime. Orleans handles the hard parts, like where each twin lives and how its memory is saved and moved between machines. So scaling is never a fragile cache trick. It is one safe, isolated twin for every thing that matters.

    • Microsoft.Orleans.Server 10.1
    • ManagedCode.Orleans.SignalR
    • ManagedCode.Orleans.Identity
    • Cosmos persistence
    • Reentrant grains

  5. 05 The MCP Boundary

    ManagedCode.MCPGateway: remote MCP that scales.

    The MCP spec describes a protocol. It does not describe multi-tenant logins, audit trails, cost caps, or rate limits, which is exactly what a real deployment needs. ManagedCode.MCPGateway is the edge layer Managed Code wrote so Prostir does not have to. It handles secure transport, per-customer access, per-tool limits, and clean error replies, all sitting in front of the Orleans runtime it routes calls into. One clean, guarded URL faces the world.

    • ManagedCode.MCPGateway 0.4.2
    • ModelContextProtocol 1.3
    • Streamable HTTP
    • OAuth 2.1 + PKCE
    • Per-tenant quotas

  6. 06 The Knowledge Layer

    ManagedCode.MarkdownLd.Kb: knowledge, not prompt paste.

    Uploaded files do not belong inside the prompt. ManagedCode.MarkdownLd.Kb takes a source, whether a Markdown file, a Word doc, a PDF, or structured data, and turns it into clean, typed knowledge plus a graph the agent can search. ManagedCode.Storage keeps it on Azure, and every tool's input is checked against a schema before it runs. The creator sees a library. The runtime sees a graph. The customer gets an answer with a citation, not a hallucination.

    • ManagedCode.MarkdownLd.Kb 0.2.5
    • ManagedCode.Storage.Azure
    • JsonSchema.Net 9.2
    • PdfPig + OpenXml
    • Cited answers

  7. 07 The AI Brain

    One interface for every AI model.

    Every model speaks a slightly different language. Microsoft built one .NET interface that hides those differences, so an agent can call OpenAI, Anthropic, or Azure with the same code. The Microsoft Agent Framework sits on top and runs the agent loops: it plans, calls tools, and remembers. Prostir ships both, wired to every major provider. The point is simple. You pick the model that fits the job, and you can switch it next week without touching anything else. The brain changes; the body stays.

    • Microsoft.Extensions.AI
    • Microsoft.Agents.AI 1.7
    • Anthropic + OpenAI
    • Workflows + Declarative
    • IChatClient middleware

  8. 08 The Builder Loop

    Claude Code and Codex: the agents that shipped this.

    We did not type Prostir line by line. The rules are plain. AGENTS.md is the long-term memory. Integration tests are the source of truth. Work ships in small vertical slices. Nothing merges until the tests are green. Claude Code writes and OpenAI Codex reviews, two agents checking each other until they agree. The agents are commercial. The product you are reading about is real. This is the loop that built it.

    Claude Code OpenAI Codex
    • AI-assisted delivery
    • AGENTS.md as memory
    • Vertical slices only
    • Claude Code + Codex
    • Integration tests gate

  9. 09 The Product Edge

    Blazor, Pay, Stateless, Jint: the creator-facing surface.

    The creator never sees the gateway. They see a Blazor workspace. The operator never sees the grain map. They see a Blazor Server console. Stateless gives a conversation rails. The agent is always in some state, and the state decides what can happen next. Put it in a "gather the details" state and it will not jump to "give the answer" until the details are in, the same way you would not send a quote before you have heard what the customer needs. Jint runs small JavaScript snippets in a sandbox when a tool needs an exact number. payment-provider integration turns paid access into real permissions, with webhooks, checkout, and usage limits. This plain product layer is what makes the AI usable, and sellable.

    • Blazor WebAssembly 10
    • MudBlazor 9.5
    • payment-provider integration + webhooks
    • Stateless 5 transitions
    • Jint 4 sandbox

  10. 10 The Static Story

    Astro landing for crawlers, structured data for AI.

    The page you are reading is a static Astro build. It is indexed for a perfect PageSpeed score and crawled by the same answer engines that fetch llms.txt. Every public route ships structured data, language tags, a sitemap, and an LLM discovery file, because the gap between a great backend and a backend people can find is metadata. Static where it should be, dynamic where it must be. The story ends where it was meant to be read, by people and machines alike.

    • Astro static landing
    • JSON-LD + sitemap
    • IndexNow + llms.txt
    • Lighthouse 100 target
    • Localized hreflang

The Result

One hosted, observable, sellable MCP endpoint per agent.

Ten enterprise layers collapse into a single URL. A creator pastes it into ChatGPT, Claude, Cursor, or any MCP client. Login, billing, knowledge, tools, state, memory, audit, and limits all come with it, running on today's distributed .NET: ASP.NET Core, Aspire, Orleans, the MCP gateway, and Microsoft.Extensions.AI. Built by AI. Run on .NET. Sold by you.

  • Remote MCP endpoint
  • OAuth 2.1 + entitlements
  • Per-agent quotas + audit
  • Live operator visibility

Why .NET

Same MCP server. Three different bills.

Independent benchmarks, no marketing math. What each language really costs in energy, speed, and built-in features for the same job.

CapabilityNode.js / ExpressPython / FastAPIProstir (.NET 10)
Energy per task (lower is greener) 1.4× .NET24× .NET1× (baseline)
TechEmpower composite rank Mid packBottom thirdTop tier
Distributed actor framework DIY / Akka.jsDIY / RayOrleans 10 virtual actors
Built-in DI, options, telemetry Add librariesAdd librariesMicrosoft.Extensions.*
AI abstraction layer LangChain.jsLangChain / LlamaIndexMicrosoft.Extensions.AI + Agent Framework
Ahead-of-time compilation NoNoNative AOT
Strong typing without bolt-on TypeScript transpilePydantic / mypyC# 14, source-generated
Hot reload across full stack NodemonUvicorn reloaddotnet watch + Aspire

Energy figures from the Pereira study, University of Minho (SLE'17 / SCP'21). Speed from TechEmpower Round 22.

Why Azure

Same MCP backend. Built for the cloud it runs on.

Not a price sheet, a fit sheet. These are the things a paid, multi-tenant MCP backend leans on, and where each one lands better on Azure. AWS is excellent. This is simply where the product fits.

What mattersOn AWSProstir on Azure
Compliance breadth broad portfolioGDPR · HIPAA · SOC · ISO · FedRAMP
Uptime SLA per-serviceup to 99.99%
Data residency region pickEU or US, your choice
Global distribution CloudFront add-onglobal backbone built in
First-party AI proximity Bedrock + AnthropicAzure OpenAI + Anthropic
Identity for end users CognitoMicrosoft Entra External ID
Open-source runtime alignment bring-your-own.NET, Orleans, Aspire, all open source
Static site hosting + custom domain S3 + CloudFrontAzure Static Web Apps (this site)

Azure service capabilities as of 2026. AWS has equivalents for most rows. The table shows where Prostir's workload fits best, not who is cheapest.

Open source

The open source we ship, and the open source we use.

Prostir is built by Managed Code on top of Microsoft and community open source. Every package below is a real one from our project files, not a marketing wishlist.

01

Built by Managed Code

Managed Code is not just the footer credit. The MCP gateway, knowledge pipeline, storage, and Orleans integrations under your published agent are Managed Code opensource we maintain and ship.

02

The .NET foundation

Everything Microsoft has been GA-ing since .NET 6 came together in .NET 10 and Aspire. That is the boring, dependable plumbing under every page on Prostir.

03

AI, MCP & the libraries on top

The .NET-native AI stack Microsoft has converged on since 2024: one interface, every model, one Agent Framework that replaces Semantic Kernel and AutoGen. Plus the small, sharp libraries the runtime leans on: Jint for sandboxed scripts, Stateless for state machines, payment-provider integration for billing.

기술 FAQ

이 스택으로 만들기 전에 팀이 확인하는 질문.

Orleans, Aspire, C#, MCP, 결제, 접근 제어, 지식, 운영 가시성을 실제 production 결정과 연결한 답입니다.

Prostir에서 Orleans는 실제로 무엇을 하나요? Orleans는 agent, session, customer, access grant, channel conversation, wallet hold, workflow run처럼 오래 살아 있는 runtime identity를 맡습니다. 각 항목은 안정적인 id, state, behavior를 가지며 singleton, cache, background process 안에 state를 숨기지 않습니다. 읽기
Queue와 CRUD API보다 Orleans가 나은 때는 언제인가요? 작고 대부분 독립적인 entity가 많고, request-response 작업, start-monitor-complete flow, identity별 state가 필요할 때입니다. Microsoft는 user profiles, purchase orders, sessions, stocks, social pub/sub을 예로 들고, Prostir는 같은 패턴을 agents, customer sessions, workflow runs에 적용합니다. 읽기
Product 관점에서 grain은 무엇인가요? Grain은 virtual actor입니다. identity, behavior, 필요하면 persistent state를 가진 논리 객체입니다. Prostir에서는 published agent, customer conversation, access grant, workflow run이 grain이 될 수 있습니다. 읽기
Orleans는 tenant isolation에 어떻게 도움이 되나요? State는 owner, agent, customer, run identity로 key 처리되므로 작업은 shared process memory가 아니라 isolated grains 안에 들어갑니다. 실패한 session이 다른 tenant의 global mutable state가 되지 않습니다. 읽기
Orleans의 주요 위험은 무엇인가요? 위험한 패턴은 chatty grains, 하나의 bottleneck coordinator, blocking synchronous calls, 너무 큰 messages, 숨겨진 shared state입니다. Prostir는 vertical ownership, async grain calls, fan-out용 stateless workers, 실제 Gateway/API/Orleans 경로를 지나는 integration tests로 이를 드러냅니다. 읽기
Aspire는 Docker Compose보다 무엇을 더하나요? Aspire는 .NET solution에 projects, dependencies, service discovery, configuration, health, telemetry, cloud resource shape를 아는 AppHost를 줍니다. 단순 process startup이 아니라 local dev, CI, Azure deployment에서 쓰는 resource graph입니다. 읽기
Prostir는 테스트에서 Aspire를 어떻게 쓰나요? AppHost가 Cosmos DB, Azure Storage, Orleans, API, Gateway, Landing, WebApp, SuperAdmin을 띄워 real integration/browser tests에 사용합니다. MCP, billing, auth, storage, grain behavior가 production과 같은 wiring으로 검증됩니다. 읽기
왜 runtime을 C#과 .NET으로 만들었나요? Runtime에는 strong contracts, async IO, dependency injection, options, telemetry, HTTP hosting, background workers, source generation, 예측 가능한 deployment가 필요합니다. .NET은 이것을 first-party infrastructure로 제공합니다. 읽기
.NET이 Prostir를 하나의 AI provider에 묶나요? 아니요. Microsoft.Extensions.AI와 `IChatClient`가 안정적인 chat/tool abstraction을 제공하고, 실제 model은 Azure OpenAI, OpenAI-compatible, Anthropic-compatible 또는 같은 runtime boundary 뒤의 다른 provider가 될 수 있습니다. 읽기
Production에서 MCP가 어려운 이유는 무엇인가요? Protocol은 입구일 뿐입니다. 유료 remote MCP endpoint에는 OAuth, access grants, tenant checks, tool schemas, rate limits, quotas, billing, audit trails, 신뢰할 수 있는 errors, 매 request마다 전체 product database를 읽지 않는 hot path가 필요합니다. 읽기
ManagedCode.MCPGateway는 어디에 들어가나요? ManagedCode.MCPGateway는 Orleans runtime 앞의 protocol edge입니다. remote MCP endpoint를 노출하고, tool calls를 라우팅하고, visible tool boundaries를 강제하며, protocol concerns를 product-state API 밖에 둡니다. 읽기
Paid access는 어떻게 runtime permission이 되나요? Seller-owned providers의 checkout과 webhooks가 access grants를 만들거나 취소합니다. Gateway는 protected MCP calls 전에 grants를 확인하므로 payment state는 spreadsheet가 아니라 runtime permission이 됩니다. 읽기
Knowledge layer는 prompt stuffing을 어떻게 피하나요? Files는 Markdown-LD / JSON-LD knowledge artifacts와 searchable graph data가 됩니다. Runtime은 graph를 검색해 cited context를 반환하고, 전체 문서를 prompt에 붙여 넣고 model이 알아서 찾기를 바라지 않습니다. 읽기
이 stack에 맞는 실제 use case는 무엇인가요? Paid knowledge agents, customer memory가 있는 support copilots, state machines가 있는 process agents, Telegram 또는 web widgets용 channel agents, 판매 가능한 skill passports, progress, retries, audit가 필요한 workflows가 잘 맞습니다. 읽기
언제 이 stack이 과한가요? Static website, 일회성 prompt demo, auth, tools, billing, state, customer memory가 없는 private chatbot만 필요하다면 더 단순한 것을 쓰면 됩니다. Prostir는 agent가 다른 사람이 의존하는 hosted product가 되는 순간을 위한 것입니다. 읽기

Tech

Map the technology to a real case.

The case studies show where each runtime layer matters: knowledge, tools, state, memory, billing, access, quotas, and operator visibility.

얼리 액세스