# Private AI Assistant for Windows — Made in Germany | Pia > A privacy-first AI assistant for Windows, made in Germany. Multiple providers, offline speech, end-to-end encryption. Your intelligence, your rules. This file contains the complete English content of https://pia-ai.de as structured Markdown, intended for large language models and other automated readers. The website itself is available in English, German and French; this file is English only. A short index of the same site is at https://pia-ai.de/llms.txt. - Product: Pia, a Windows desktop AI assistant with an optional self-hostable server - Vendor: neo42 GmbH, Germany - Licence and code: open source, https://github.com/Pia-Ai-dev/Pia.Wpf - Documentation: https://docs.pia-ai.de - Contact: kontakt@pia-ai.de - Last updated: 2026-09-12 ## Contents 1. [Home](#home) 2. [Features](#features) 3. [Pricing](#pricing) 4. [Download](#download) 5. [Pia for business](#pia-for-business) 6. [Security and compliance](#security-and-compliance) 7. [Self-hosting](#self-hosting) 8. [About](#about) 9. [Site-wide](#site-wide) --- ## Home Source: https://pia-ai.de/ ### Hero **Your AI, your device, your rules** # Your private AI assistant. *Only one hotkey away.* Use any AI model you want. Dictate with your voice — even offline. Your data stays on your device — or syncs to a server, ours or one you run yourself — end-to-end encrypted if you want it. Calls to action: "Download for Windows" (https://pia-ai.de/download.html), "Pia for business" (https://pia-ai.de/business/). Hero badges: Multi-provider · Offline speech · E2E encryption · Open source ### The three mechanics (animated hero) 1. **Voice input — created on your device.** Your voice *never leaves* your machine. 2. **Conversations — stored on your device.** Your chats *stay private* on your device. 3. **Encrypted sync — end-to-end encrypted.** With encryption on, *not readable* on the server. ### Trust markers Open source · Made in Germany · Offline capable with local models · No usage data collected ### Beyond the hotkey: the heavy lifting Knowledge, meetings, agentic work, governance — the four pillars that make Pia more than a chat window. Each one runs where you decide: on your device, or on your server. **Knowledge over your own documents.** Drop files in, ask questions, get answers with citations from your own material. A private vault on your device — or shared knowledge bases on your server, fed by a REST API. **Meetings & live transcription.** Pia joins your Teams meetings, transcribes live, tells speakers apart, and writes the summary. Or transcribe the room around you — entirely on-device, behind a spoken consent gate. **Agentic work, under your control.** Every tool Pia can use is a permission you grant — and can revoke at any time. Put recurring questions on a timer and the answers arrive as chats. Or hand Pia a whole goal: it plans, you approve the plan, it executes step by step while you steer. **Governance & security.** Guardrails route risky requests to protected models. Groups carry policy — down to the model that answers. Audit logs notice anomalies. SSO, encryption at rest — and it all runs on a server you control. Call to action: "Explore all features" (https://pia-ai.de/features.html). ### The problem **Your AI assistant shouldn't spy on you.** Most AI tools send every conversation to servers you don't control, lock you into a single provider, and require a constant internet connection. Your data becomes their business model. **Your conversations stay on your device.** The app does not report back on what you do: no usage data, no tracking, no profile of you. What you write stays on your device until you send it out — by syncing, by asking a cloud model, or by reporting an answer. With end-to-end encryption, which Pia suggests when you set it up, your device encrypts the content you sync before it leaves, and our server holds the key only in encrypted form. What sync itself needs, such as timestamps and order, stays readable. **Switch AI providers without losing your history.** Connect OpenAI, Anthropic, Mistral, Azure, OpenRouter, or your own model. Your conversations, memories, and templates remain intact — no matter which provider you use. **Talk to Pia even without internet.** Dictation and read-aloud run entirely on your device. For speech recognition you can pick Whisper or Parakeet, and the voice comes from Piper — three speech models, all running locally. Pia needs no internet connection for speech. ### How it works — up and running in three steps 1. **Download & install.** Free, no account required. Installs in under a minute. 2. **Pick your AI.** Either use Pia Cloud models with no key at all — we run those on European providers — or connect your own account: OpenAI, Mistral, Azure, or any compatible provider. 3. **Press your hotkey.** Pia sits in your system tray. One hotkey and she is ready for use — optimize text or chat. ### Common questions — your intelligence, your rules **Is my data really private?** Yes. Pia is open source — you can audit every line of code. Your conversations, memories and files stay on your device unless you send them out. Cloud sync is optional, and so is end-to-end encryption, which Pia suggests when you set it up: with it, your device encrypts the content you sync before it leaves, and our server holds the key only in encrypted form. What sync itself needs, such as timestamps and order, stays readable. If you use a Pia Cloud model, your prompt passes through our server on its way to the AI provider. Our server does not store it; one of our model providers keeps it for 30 days to detect abuse, then deletes it. Bring your own provider and it never touches our server at all. **Is it hard to set up?** Not at all. Download, install, and a guided setup wizard walks you through provider configuration. You'll be using Pia in under two minutes. **What if I want to switch away?** Your data is yours. Everything is stored locally in standard formats. Switch AI providers anytime without losing a single conversation, memory, or template. ### Closing **Try Pia free — no account required.** No account needed. No credit card. Just download and go. --- ## Features Source: https://pia-ai.de/features.html **Capabilities** # Every feature, built on privacy. Privacy was the first question we asked of every feature — not the last. ### Foundations **Your data stays on your device — by default.** Conversations, memories and data live on your device. The app sends no usage data and does no tracking. What you write stays there unless you send it out — by syncing, by asking a cloud model, or by reporting an answer. Cloud sync is optional and always under your control. With end-to-end encryption, your device encrypts the content you sync before it leaves, and our server holds the key only in encrypted form; what sync itself needs, such as timestamps and order, stays readable. **End-to-end encrypted sync.** Your conversations on every device you use. With end-to-end encryption, the server — ours or yours — receives their content only encrypted. **Use any AI model. Switch anytime.** Connect OpenAI, Anthropic, Mistral, Azure, OpenRouter — or run local models via Ollama. Switch anytime without losing a single conversation. **Voice input that works offline.** Dictate and listen without an internet connection. Your voice never leaves the machine. **Pick up where you left off, on any machine.** Sessions, memories, todos, templates, providers, personas — seamlessly synchronized across every device. Optional, always under your control, and end-to-end encryptable at your choice. **Make it yours.** Build custom templates, organize knowledge with typed schemas, and design workflows that fit your actual working method. ### Two modes: one assistant, two workflows Polish an email in seconds, or think out loud with an AI that remembers your last conversations — all from one keystroke. **Optimize.** Turn rough notes into polished emails, articles, or messages — and auto-type the result into any app. - Text templates — emails, articles, code prompts - Dictate instead of typing — speech recognition runs on your device, not in the cloud - Auto-type results into any app - Side-by-side comparison view **Assistant.** An AI to talk things through with: it remembers what came before, offers actions right in the chat, and thinks along with you. - A searchable memory that sticks — with @ references to your files - Kanban board with drag-and-drop, priorities, and voice input - Suggestions right in the chat — accept or decline without losing your thread - Smart suggestions for quick actions - @-mentions to reference memories, todos, and reminders inline ### The rest of the product: everything else in the box More capabilities that ship with Pia today — for one person on a laptop or a whole team on a server. **Knowledge & documents.** Drop files into your knowledge library and Pia turns them into knowledge it can recall — you see exactly what it learned, and you can pull any source back out. Nothing stays in memory against your wishes. You can also attach files to any chat. The memory itself sits on your own disk as plain text: browsable, editable, yours. **Meetings & transcription.** Pia joins Teams meetings, transcribes live speaker by speaker, and writes a summary you can keep. Live-transcribe the room around you entirely on-device, behind a spoken consent gate. Or just talk — voice conversation mode takes turns and uses tools. **Flow & reminders.** One calm rail for everything that wants your attention — notifications, reminders, and background updates arrive as actionable cards, grouped by due date. Snooze, act, or dismiss. **Personas.** Reusable identity and voice profiles. Pick one per chat, and always see which persona wrote which answer. **Coding tools.** Point Pia at a folder you choose: it reads, searches and edits the text files inside — and shows you every change before it is saved, old and new side by side. To bring in a single file, type @ mid-sentence. **Plugins, MCP & REST.** Extend Pia with server-delivered tool packs, MCP servers — on the server or running locally on your own machine — or a REST API wired in as a tool source, all enabled and disabled per user. **Agentic work.** Every tool is a permission: grant it once, until Pia closes, or always — and revoke any of it from a full inventory. Put recurring questions on a timer; answers arrive as chats. For bigger jobs, hand Pia the goal: it plans, you approve the plan, and it executes step by step while you watch and steer. Running Pia for a team? See Pia for business (https://pia-ai.de/business/). Closing: **Start using Pia in under two minutes.** Download for Windows, or view on GitHub. --- ## Pricing Source: https://pia-ai.de/pricing.html # Honest pricing. No surprises. The Windows app is always free. With your own provider key it runs with no server and no account at all — what follows is about the server behind it. ### On your server You run the server. Every edition is the same container image — the signed licence decides what it unlocks. Both editions are coming soon and cannot be ordered yet. #### Community Edition — self-hosted, 5 users, 1 admin **Free, forever. Coming Soon — not available yet.** - Local login with MFA and passkeys - AI proxy with your own provider keys - Sync and chat history across devices - End-to-end encryption, recovery and device revocation - Admin dashboard, audit log and token board Call to action: Available soon. #### Enterprise Edition — self-hosted, seats per contract **Custom, on request. Coming Soon — not available yet.** - Everything in Community, plus: - Microsoft Entra ID single sign-on - Your own groups: quotas, provider routing, plugin allowlists - Guardrails with a decision log - Knowledge bases with cited answers, managed personas, client policies ### On Pia Cloud We run the server — on European providers, in Europe (EEA and Switzerland), with no US companies among our providers. With end-to-end encryption, the content you sync reaches us only encrypted. All Pia Cloud plans are coming soon and cannot be booked yet. Pia Cloud plans are business offerings — prices are net, plus VAT. Pro will be billed per user, from five users up. None of the plans is bookable yet; the Windows app stays free for everyone. #### Free — cloud-hosted **0 € / month. Coming Soon — not available yet.** - Cloud sync across devices — sessions, memories, todos, templates, providers, personas - Basic access to Pia Cloud models — requests run through our server - Credit-metered usage with hourly, daily & weekly limits - One knowledge base with cited answers - End-to-end encryption (optional) Call to action: Available soon. #### Pro — power users **42 € net / seat / month. Coming Soon — not available yet.** Pro will be a team plan — from five users up. - Everything in Free, plus: - Priority access to Pia Cloud models Call to action: Available soon. #### Pro ×5 — 5× the credits, per member **210 € net / seat / month. Coming Soon — not available yet.** - Everything in Pro, plus: - Same knowledge base, document, storage and provider quotas as Pro — only the credit allowance is higher Call to action: Available soon. #### Pro ×10 — 10× the credits, per member **420 € net / seat / month. Coming Soon — not available yet.** - Everything in Pro, plus: - Same knowledge base, document, storage and provider quotas as Pro — only the credit allowance is higher Call to action: Available soon. --- ## Download Source: https://pia-ai.de/download.html **Download** # Take control of your intelligence. Install Pia in only two minutes. No account. No tracking. With a local model and sync off, nothing you write leaves your device. Choose a cloud provider like OpenAI or Mistral and your requests go to them; switch on Cloud Sync and your data lives on a server — ours or one you run yourself. [Where your data goes](https://docs.pia-ai.de/wpf/guides/where-your-data-goes/) walks through every setup. - Download for Windows (system-wide installer): https://storage.pia-ai.de/f/wpf/Pia-Setup.msi — installs for everyone on the machine, needs admin rights. - Per-user installer: https://storage.pia-ai.de/f/wpf/Pia-Setup-PerUser.msi — installs for the current user, no admin required. - Current version, release date, size and SHA-256: https://storage.pia-ai.de/f/wpf/latest.json - Release notes for the current version (English): https://storage.pia-ai.de/f/wpf/RELEASE-NOTES.md - Audit the code on GitHub: https://github.com/Pia-Ai-dev/Pia.Wpf ### What happens next, after you install 1. **Install Pia.** Run the installer. No account creation, no sign-up forms. 2. **Pick your AI provider.** A guided wizard walks you through connecting OpenAI, Azure, or any compatible provider. 3. **Press your hotkey.** Pia sits in your system tray. One hotkey and you're ready to go. ### Requirements and terms **Windows 10+.** 64-bit Windows 10 or later. .NET 10 runtime included. **No account required.** A guided setup wizard walks you through provider configuration in minutes. Use Pia locally with your own AI keys — cloud sync is optional. **Open source.** Full source code available on GitHub. Build from source if you prefer. **Trouble installing or using Pia?** piasupport@pia-ai.de --- ## Pia for business Source: https://pia-ai.de/business/ **Pia for business** # Your company already uses AI. Now take control of it. Company data is already flowing into consumer chatbots — invisible, unpoliced, unlogged. Pia replaces shadow AI with a better assistant where you set the rules — from the server down to the individual request. Calls to action: "Talk to us" (vertrieb@pia-ai.de), "See self-hosting" (https://pia-ai.de/business/self-hosting.html). Trust markers: Made in Germany · Open source · No usage data collected · Self-hostable ### The three mechanics (animated hero) 1. **One employee — drafted on their device.** Work starts *on the device* — you decide what leaves it. 2. **Team sync — on your server.** It syncs to *your* server, with optional end-to-end encryption. 3. **Provider boundary — guardrails decide.** Only what policy allows *crosses the line*. ### Deployment: two ways to run Pia Both keep the same promise: control over your data stays with you — either because you run the server yourself, or because, with end-to-end encryption, it receives the content you sync only encrypted. **Self-host it.** Run the Pia server on your own hardware, in your own network. It comes in two editions on the same image: the free Community Edition — open source, local authentication built in, five users — and the licensed Enterprise Edition, which adds SSO, your own groups, knowledge bases and negotiated seats. Both editions are coming soon. See what each edition includes: https://pia-ai.de/business/self-hosting.html#editions - Your hardware, your network, your rules - You choose the AI providers — including local models via Ollama - Free with the Community Edition — coming soon, no payment details **Or use Pia Cloud.** The same server, operated by us, on European providers in Europe (EEA and Switzerland) — no US companies among our providers. With end-to-end encryption, your devices encrypt the content you sync before it leaves them, and our server holds the key only in encrypted form. Prompts sent to a Pia Cloud model are processed on the server rather than stored; with your own provider they bypass it entirely. - No infrastructure to run - End-to-end encryption (optional) - Start free, upgrade when you need to — coming soon Free will be per person; Pro, the paid plan, from five users up. Both are coming soon. ### Control, not a ban Banning AI only takes away your view of it. Pia hands you the controls instead: who uses which model, what gets checked before the answer, and what you can trace afterwards. **Who may do what: the group decides.** Every rule hangs on a group and applies to everyone in it: token budgets per hour, day and week, quotas, permitted plugins, knowledge bases. A new hire gets the right rules with the group — not with a ticket. And a spent budget is a stop with a reset time, not a surprise on the invoice. **Which model answers: you set it.** A default model per group, one per mode — text optimization routed differently from the assistant — and one per type for assistant personas, say a code model for developer personas. In front of the assistant sit the guardrails: you decide which check rules apply, which model classifies the requests, and which protected model answers when a rule hits. **What you see afterwards: the record, not the conversation.** An audit log with sign-in anomaly detection, every guardrail verdict, token usage by user, group and model, every device with its status — and one click to revoke a lost one. What the requests contained is in none of them: the token log knows timestamp, model and token count, the guardrail log only a hash of the judged content. And the console itself is divided: admin roles grant view and manage rights per area — the audit log for data protection, the token board for finance, the groups for IT. Only an owner can hand out rights. The admin plane in detail: https://pia-ai.de/business/self-hosting.html ### For the people using it: an assistant that doesn't need a mandate The rules ride along in the background — up front is an assistant that wins on its own merits. Here's what a rollout actually gives your team. **Company knowledge with citations.** Server-side knowledge bases scoped to groups: your documents in, cited answers out. Feed them from your own pipelines over a REST ingestion API. **Meetings & transcription.** Teams meetings transcribed live with speakers told apart, plus on-device transcription of the room — behind a spoken consent gate. Summaries land where your people can keep them. **Agentic work.** Tools are permissions, schedules deliver answers as chats, and every capability can be revoked. Employees can hand bigger jobs to your Pia server to run in the background — behind an explicit consent screen that states exactly what leaves the device, with caps and a job list. **Managed personas.** Author a persona once — its voice, its knowledge bases, its tools — and publish it to a group. Everyone gets the same reviewed assistant, and every answer shows which persona wrote it. ### Where to go next **Security & compliance.** Control before the answer, traceability after it: guardrails, SSO, audit with anomaly detection, encryption at rest — and precisely what an admin cannot see. Security in detail: https://pia-ai.de/business/security.html **Self-hosting & administration.** Where control gets concrete: groups as the unit of policy, model routing per mode and persona type, admin roles per console area, token usage boards, live-editable runtime policies, devices — and a side-by-side of what each edition includes. Self-hosting in detail: https://pia-ai.de/business/self-hosting.html ### Closing **Talk to us about your rollout.** Deployment, licensing, security reviews — email us and a person answers, in German or English. Email vertrieb@pia-ai.de --- ## Security and compliance Source: https://pia-ai.de/business/security.html **Security & compliance** # Security you can verify. Everything on this page is shipped, documented, and open source. Where a protection has limits, we state them — that's what makes the rest believable. **Guardrails that act before the model answers.** A catalog of check rules you configure per group — and three decisions that stay with you: which rules are active, which model classifies every assistant request, and which protected model answers when a rule hits. Verdicts are cached so the check stays fast — and every decision lands in a log you can review. Guardrails and single sign-on need the licensed Enterprise Edition — guardrails because they are a group setting, and the Community Edition cannot reconfigure its one group. - Classified per group - Risky requests rerouted to a protected model - Every verdict logged - When in doubt, the protected model — images included - Request path: Requests → Guardrail → Requested model or Protected model → Decision log **Sign in with what you already run.** Microsoft Entra ID single sign-on with a fully documented OAuth registration and login flow. SSO comes with the Enterprise Edition; the free Community Edition signs people in locally, with MFA and passkeys. **An audit trail that flags anomalies.** Structured events with filtering and retention — including login-anomaly detection that flags unusual sign-in patterns. Guardrail decisions sit alongside, with verdict, model and a hash of the judged content instead of the text: one place answers what happened and what the AI layer did about it — without reading along. **Encryption at rest, with stated limits.** A master key, an AES-GCM wire format, layered disk protection — and documentation that states the threat model, including what it does not protect against. We'd rather you know. **Pia Cloud runs on European providers.** We select the providers behind Pia Cloud to be European companies processing in Europe (EEA and Switzerland), with a data-processing agreement in place for each. No US companies among our providers; the service providers they use in turn are listed on our sub-processor page. That is our procurement policy for Pia Cloud — self-hosting or your own provider key keeps the question in your hands entirely. **What an admin cannot see.** With end-to-end encryption on, the admin console shows what exists — devices, item counts, sync state — while synced content reaches the server, and its operator, only encrypted. Our server processes prompts to a Pia Cloud model the moment they arrive and does not store them; one of our model providers keeps them for 30 days to detect abuse. If you run the server yourself or use your own AI provider, those prompts never reach our server at all. That separation is documented and demonstrable: exactly what a works council or data-protection officer asks for. Data that arises on the server or runs it — accounts and sign-ins, logs, reports on AI answers, managed personas, policies, extensions, device details, trusted certificates — is not end-to-end encrypted, and neither is what sync itself needs, such as IDs, timestamps and order. **Losing a device need not mean losing data.** A recovery code lets encrypted data survive a lost or reset device. And the honest flip side: if the code is gone too, the data is unrecoverable — by design, because a backdoor for you would be a backdoor for everyone. **One policy file for the whole fleet.** An enterprise policy file enforces defaults across managed installations — including how the assistant itself behaves — with rollout guidance for IT. **Revoke the laptop, not the account.** Every registered device is visible with its pairing status and sync cursors. A lost machine gets revoked — cut off from sync — without touching the account or the other devices. Delete it entirely when it's truly gone. **The pod uplink trust model.** Pods connect over a single inbound route with a narrow contract: what a pod can and cannot see is documented, and the operator plane is unreachable from chat. ### Closing **Send us your security questions.** Security questionnaires, DPO questions, threat-model deep dives — we answer them ourselves. Talk to us about security: vertrieb@pia-ai.de --- ## Self-hosting Source: https://pia-ai.de/business/self-hosting.html **Self-hosting** # Your server. Your rules. No fine print. The whole admin plane on your own hardware — and with it every decision about who uses which model, what gets checked and what gets logged. Here's what running Pia yourself looks like day to day. **The free Community Edition — coming soon.** The Community Edition is the real server, not a demo: open source, local authentication built in, and a documented walkthrough from zero to first login. If you can run a standard .NET service and a database, you can run Pia. Read the walkthrough: https://docs.pia-ai.de/wpf/guides/community-edition Every Pia server runs on a signed licence file, including this one — the Community licence will be free once the edition is out. On first start the server prints a setup token; paste it together with the licence on the setup page and it activates without a restart. ### Two editions, one server Community and Enterprise are the same container image. The signed licence decides what it unlocks, so moving up later means replacing one file — same server, same data. | Capability | Community | Enterprise | |---|---|---| | Local login with MFA and passkeys | Included | Included | | AI proxy with your own provider keys | Included | Included | | Sync and chat history across devices | Included | Included | | Admin dashboard, token board, runtime policies | Included | Included | | Audit log and login-anomaly detection | Included | Included | | Encryption at rest | Included | Included | | End-to-end encryption, recovery, device revocation | Included | Included | | Plugins, MCP and the public REST API | Included | Included | | Groups as the unit of policy | One default group | Groups you define | | Guardrails with a decision log | Not included | Included | | Microsoft Entra ID single sign-on | Not included | Included | | Managed personas and client policies | Not included | Included | | Knowledge bases with cited answers | Not included | Included | | Users / admins | 5 / 1 | Per contract | Guardrails, quotas, provider routing and plugin allowlists are settings on a group — that is why they sit on the Enterprise side, not because the feature itself is switched off. Everything above the group row works on a Community licence. Both editions are coming soon and cannot be ordered yet. The Community licence will be free. **The group is the unit of policy.** (Enterprise Edition.) Whatever you set on a group applies to every member automatically: token budgets per hour, day and week — hard limits, not guidelines — per-user and knowledge-base quotas, guardrail configuration, and the list of permitted plugins. Policy stops being tribal knowledge. Which model answers is yours to set, in layers: a default for the group, one per mode — text optimization routed differently from the assistant — and one per type for assistant personas, say a code model for developer personas or a fast one for everyday questions. Whatever you leave unset falls back to the next layer, down to the server default. (A group carries: Quota, Providers, Plugins, Knowledge.) **Account lifecycle without loose ends.** Roles, identity sources, disabling, session revocation, soft delete with recovery. Offboarding is a checklist the server already knows. **See where the tokens go.** Usage over time, broken down by user, group, and model, plus the heaviest requests and a per-user request log — you see the invoice coming before it arrives. What was in those requests is not there: the log knows the timestamp, model, template and token count — not a single sentence from the conversation. **Not every admin sees everything.** The console is split into areas — accounts, groups, guardrails, audit, tokens, licence and more. Roles (bundles, in the console) grant view or manage rights per area; an Auditor role ships ready-made: audit log, token board, AI feedback. Only an owner can hand out rights. Useful from the second admin on — the Community Edition has one. **Policies you can edit live.** Rate limits, quotas, identity and lockout policy, AI payload caps, provider retry behaviour — all editable from the admin UI while the server runs. No config-file archaeology, no restart window. One click in settings tells you whether the provider connection is up. Better you find out than your users. **Every client, accounted for.** Registered devices with pairing status and sync cursors. Revoke a lost machine to cut it off from sync, or delete it outright — the difference is deliberate, and documented. **Licence status at a glance.** Edition, expiry and seat counts at a glance; licence events on a timeline; install or replace a licence from the UI, with an automatic rollback if the new file fails to validate. Expiry is a hard stop, not a slow fade: the server returns to setup mode and waits for a valid licence. Your data stays fully intact — the server simply stops accepting requests until a licence is in place. So it does not catch you out, the console starts warning 30 days ahead. **Extend it your way.** (Enterprise Edition for the per-group allowlist.) Plugins come in three kinds — server-delivered tool packs, MCP servers you bring, and REST APIs wired in as tools. Which of them a group may use is an Enterprise setting; the catalogue itself works on every edition. Third-party plugins are covered by signing certificates, with the trust list managed by you. **Pia Mesh — included, and off until you switch it on.** Connectors put pods on the tool plane: register a pod, issue its token, pick a transport, grant it to a group, and watch its presence. Operators put them on the task plane: serve skills, supervise running assignments, control retention. Nothing participates until an admin turns it on. **A public API, documented.** Auth, sync, AI proxy, assignments, and the E2EE endpoints are a documented contract — build your own integrations against the same API the client uses. ### Closing **Start on your own server — soon.** The free Community licence is coming soon; read the walkthrough (https://docs.pia-ai.de/wpf/guides/community-edition). --- ## About Source: https://pia-ai.de/about.html **About Us** # Built by a team that uses AI every day. We're Team Pia, a small product team inside neo42 GmbH in Wiehl, Germany, building the AI assistant we use ourselves every day. **Our Story.** We got tired of AI assistants that use your data as their business model — and leave you no say in it. So we built one where control stays with you: over your data, your models and your rules. Pia started as an internal tool at neo42 that we still use every day — and it is open source now. We believe the best products come from teams that use what they sell. **Backed by neo42 GmbH.** For over 15 years, neo42 has helped IT teams package, deploy and manage software on thousands of endpoints — for more than 1,000 customers. So Pia ships the way IT departments expect: signed installers, a self-hostable server, and an admin who stays in control. More: https://neo42.de/ueber-neo42 ### Philosophy: AI-first. In everything we do. We don't just build AI — we work alongside it. Every task starts with one question: can AI do this? **AI evaluates first.** Before assigning a task to a human, we ask: can AI do this? Not to replace people, but to amplify what the team can achieve. **AI as teammates.** Every feature in Pia gets tested in our own daily workflows first. From code review to content creation, AI colleagues are part of our daily routine. **Humans set direction.** People define the vision, values, and strategy. AI handles execution, research, and scaling. Together, we move faster. ### Values: what we stand for **Privacy by default.** Privacy isn't a feature — it's a principle. Control over your data stays with you: it lives on your device, on a server you run, or on ours — which, with end-to-end encryption, receives the content you sync only encrypted. **Transparency.** Open source, honest pricing, no hidden agendas. **Lean & fast.** Small team, solid footing. We ship fast because AI lets a small team do more — and because neo42 already runs the infrastructure, signs every release and answers the phone. We get to focus on the product. Closing: **Try Pia or contribute on GitHub.** --- ## Site-wide ### Navigation Features (/features.html) · Business (/business/) · Pricing (/pricing.html) · About (/about.html) · Download (/download.html) Business sub-navigation: Overview (/business/) · Security & compliance (/business/security.html) · Self-hosting (/business/self-hosting.html) Footer: Business · GitHub (https://github.com/Pia-Ai-dev/Pia.Wpf) · Docs (https://docs.pia-ai.de) · Imprint (/impressum.html, German) · Privacy (/datenschutz.html, German) · Legal (/legal/, German) © 2026 Pia — a product by neo42 GmbH. All rights reserved. ### Privacy of this website This website sets no cookies. Fonts, styles, and analytics are self-hosted — no third-party CDNs. Our analytics (analytics.pia-ai.de) processes your IP address on our own infrastructure. The download page fetches the latest release version from GitHub. ### Languages The site is published in English, German and French, selectable in the header. This Markdown file and https://pia-ai.de/llms.txt are English only.