Less searching.
Get more done.

Find the answer in a contract. Prepare for the next customer conversation. Have a recurring summary ready for you. Kivanto brings your knowledge and your work together, with AI that can access your documents.

Your knowledge. Your workflows. On your infrastructure.

Download for free ↓Book a consultation

Kivanto Solo · Free for your computer

Already using Claude or ChatGPT? Explore the import →

Kivanto answers a question and shows the source in the document — Kivanto explained in 1:48 · Images and voice AI-generated

Claude & ChatGPT → Kivanto

Your chat history. Your control.

Bring available conversations and files from ChatGPT or Claude / Cowork into your own Kivanto instance.

Start with Kivanto →

Import scope and data processing

ChatGPT

Import your extracted ChatGPT data export: readable conversations become Kivanto chats, and included files become project documents.

The export becomes one Kivanto project. Each conversation’s active branch becomes a readable chat; other branches stay in the original export. Missing cloud attachments cannot be retrieved. Previous ChatGPT project assignments are not restored.

Claude / Cowork

Bring your locally available Cowork projects with you: linked folders, available attachments, outputs and readable conversations.

The import reads local Claude / Cowork data or a compatible local backup. Cloud-only content and Claude account-export ZIP files are not included. Instructions and skills are preserved as files and are not automatically activated.

The import preview shows available content and missing files before copying.

The import in Kivanto Solo creates a local copy; your OpenAI or Anthropic accounts remain unchanged. With external AI models, content needed for a request is sent to the selected provider. Local processing also requires the models and services you use to be configured locally.

A look inside Kivanto

Your knowledge becomes your workspace.

From the dashboard to your next task: chat, project rules, routines and customers. Open Word and PDF files in your project or right beside the conversation.

Light Kivanto dashboard with activity chart and knowledge distribution in the fictional Nordlicht Digital project. — Your starting point with shortcuts, AI activity and project knowledge.Open full-size image ↗

Apps & automation

Build once. Reuse. Use fewer tokens.

Have apps built for recurring work. Defined calculations and saved workflows need no new AI plan.

Discuss your workflow →

Example mini-app: quote calculator

Kivanto creates mini-apps like this for you: build once with AI, then calculate without further AI calls and save tokens.

Illustrative values — not Kivanto pricing.

Quantity3

Example unit price: €100 net · VAT: 20%

Example total including VAT€360.00

AI calls for this calculation: 0

Where are tokens saved?

1. Prepare with AI
Describe your task. Review the proposed app and its functions.
2. Reuse as a tool
Calculate totals, validate inputs or filter data without a new AI call for these defined steps.
3. Automate selectively
Save suitable workflows and run them manually, on a schedule or in response to an event.

AI helps create and modify the app. Defined calculations and approved app automations then execute saved steps without Kivanto asking a model to plan them again each time.

AI-generated text, app creation and changes can still use tokens. AI routines still call models. Connected services may incur their own costs. Actual savings depend on the workflow.

Creation and additional AI tasks can still use tokens.

Sound familiar?

01The information you need is somewhere between a shared drive, a document store and your CRM.
02Before a customer call, you are missing the last commitment, the right document or the next step.
03Recurring summaries, notes and follow-up tasks start from scratch every time.
04Your AI knows the question but lacks the documents and the context.

Aus vorhandenem Wissen wird your next step.

What did we promise in the proposal? Who is part of the project? And which source supports the answer?

Documents, contacts and connections in one platform.

Kivanto in everyday work

What would you like to get done today?

Start with a question or a task. Your documents, customer information and connected tools provide the context.

Move forward with one question.

“What did we agree — and where does it say so?”

Ask your documents instead of searching folders one by one. Kivanto combines search and chat: get an answer with references and read the original source. Prepare for a conversation or get up to speed on a topic.

Start with a document, a scan or a recording

Drop a PDF, Word document, spreadsheet or presentation into the chat and ask about it. Images and scanned PDFs use a configured vision model; audio recordings use a transcription model. Choose whether an attachment stays in the conversation or becomes reusable project knowledge.

Dictate your question and edit the recognised text before sending it. Completed answers can be read aloud. Suitable speech models must be configured; external providers process the recording or answer text.

For important statements, turn on “Thorough” to request additional checks against original sources. See supporting evidence, contradictions and unresolved points. The agent can use a local calculator for arithmetic. You remain responsible for assessing the answer.

When your own documents are not enough, enabled web research can add external sources. It must be configured for your deployment and sends search queries to external services. Reopen conversations later or share them with authorised colleagues to read or continue.

Understand what a change could affect.

“If this supplier fails, what depends on it?”

See how people, companies, projects and documents connect. Impact analysis follows recorded dependencies and shows potentially affected items with an evidence trail. Know where to take a closer look first.

Follow a connection back to the evidence

Move from a concept to its relationships and the relevant source passage in the knowledge graph. Explore the network in 3D and full screen. Custom concepts, relationship types and industry templates represent your domain knowledge. Reviewed additions and structured exports support further use.

The analysis shows possible dependencies in visible, indexed knowledge. It does not predict actual damage. Check whether stock, alternatives or other agreements change the outcome in your specific situation.

Be ready for the next customer conversation.

“What is still open, what did we promise and who owns the next step?”

Open the customer record to bring contacts, sales opportunities, tasks, notes and related documents together. Keep the next step visible alongside the deal. Personal views and sales summaries help you prioritise today’s work.

Fit customer work to your processes and existing systems

Organise opportunities on a board or in a table. Custom sales stages, fields, filters, lists and dynamic contact groups reflect how you work. Attachments and change history stay with the customer record. Use chat to look up CRM data and prepare changes for your approval.

A configured Microsoft 365 connection brings email subjects, previews and calendar events into your activity history. Brevo campaign reports show available delivery and engagement figures. Import Twenty data with field mapping, review conflicts and preview supported changes before writing them back. Connections and permissions are configured for your actual accounts.

CRM workflows can respond to a change by creating a follow-up task or note, updating a sales stage or preparing an email draft. Conditions and delays control the sequence; a test run previews the steps. Open email drafts in your email application to send them.

Set up recurring questions once.

“Summarise this project’s status every Monday.”

Save a task as a routine. Kivanto starts it on a schedule, through a webhook or when files change in a watched project folder. The result is saved as a conversation you can continue working in.

Use schedules and events that fit your day

Run once, hourly, daily, on weekdays or weekly, in your time zone. Prepare a routine for approval from chat, run it manually or pause it. History shows results and failed runs.

Events from connected systems can trigger a routine through a webhook. The sender must be able to reach the Kivanto instance. For every routine, Kivanto must be running, but the browser can be closed. Required approvals for proposed actions still apply.

Watch for incoming receipts, for example. File patterns and events determine what triggers the routine; a quiet period lets copying finish. Multiple changes are processed together. Saved scripts and enabled skills can be reused in the task.

From a conversation to a usable document.

“Turn this into a report and update the budget spreadsheet.”

Prepare Word documents and Excel spreadsheets, or make targeted changes, directly in chat. Review the content and proposed changes, approve the file and continue working with it. There is no need to copy individual answers into a document.

What you can review before approval

Word supports text, headings and tables; Excel supports edits to cells, formulas and worksheets. Content previews show the draft and proposed changes. HTML drafts can be viewed as a rendered page.

File editing runs locally and does not require an Office installation. Your selected AI model may still be an external service. Previews do not reproduce the printed Office layout; new Excel formulas are calculated when opened in Excel.

Turn an idea into material you can use.

“An image for the post, a voice for the text.”

Use Media Studio to create images, spoken text and audio with configured models. Turn an uploaded recording into a transcript. Preview, listen to and download your results.

Choose models for the result you need

Use suitable enabled models through services such as OpenAI-compatible providers, fal.ai or Higgsfield. Available image, audio and speech functions depend on the configured model. Find your jobs and completed results in your personal history.

Text or files sent to external providers are processed there and may incur charges. Media Studio does not currently generate video; transcription works with uploaded files.

Let AI agents work with your project knowledge.

“Use our documents and prepare the next step.”

Start OpenCode tasks directly in Kivanto chat. The agent receives your request, conversation context and suitable attachments. Follow its steps, answer questions and respond to approval requests without switching windows to coordinate the work.

From research to drafts and reviewed code changes

Direct execution requires Kivanto Solo, a local project folder and a configured OpenCode installation. OpenCode uses its own models, tools and permissions; changes are made directly in the project folder. Stopping a task keeps changes already made. External agent tasks cannot yet be scheduled as routines.

If you prefer working in your existing assistant, guided setup connects OpenCode and Pi Agent to Kivanto. Cline has a manual connection option; Claude and Codex remain supported. Access to project knowledge is separate from running OpenCode directly in chat. Each connection can be revoked individually.

Prepare a note, a structured analysis or a new text file as a draft. For development work, the project agent can search code, inspect Git changes and propose specific file edits. With a configured runner, approved tests and builds run in an isolated project copy.

Turn recurring work into your own tool.

“Build me a quote calculator I can reuse.”

Have an app built with its own interface. Calculations, form validation and data filters run as defined functions, so the same work does not need to be sent to an AI model again on every use.

Combine apps, automation and AI deliberately

Alongside AI forms, Kivanto supports executable apps with their own inputs and saved data. Quote calculators, form checks and list analyses are typical examples. In the Server edition, apps can be shared with suitable projects and roles.

Approved app automations connect defined calculations, data processing and supported read access. They can run manually or through routines. Required approvals and access permissions still apply.

AI-generated text, app creation and changes can still use tokens. AI routines still call models. Connected services may incur their own costs. Actual savings depend on the workflow.

Save your working instructions as skills.

“Use our template and follow our process.”

Give your agent reusable instructions, references and templates. Create, import, edit and activate your own skills for the next suitable task.

Manage personal skills

Describe your process in chat and have a skill prepared with instructions and relevant scripts. Review the proposal and save it with Create. Manage templates and reference files in the skill editor afterwards.

The built-in catalogue, Markdown files and skill packages help you get started. Active skills are available to the internal agent and the local OpenCode integration. Skills do not expand access rights; execution follows the applicable approval rules.

Take the next step in connected systems.

“Prepare the record and show me the details.”

The agent can use write tools from suitable MCP connections. By default, you review the destination, purpose and exact details in chat before the tool runs.

Set approvals for each tool

Administrators can explicitly allow individual tools on a project connection to run without asking. Personal connections always ask. Data imports and background synchronisation remain read-only. Composio has separate tool checks; this extension does not enable its write tools.

Turn data into an analysis you can review.

“Compare these lists and create a chart.”

The agent writes and runs small programs to clean up lists, compare data or perform calculations. Outputs, images and generated files appear directly in chat.

Reuse scripts and results

A private workspace stores files and scripts per person and project across conversations. Resume an analysis later, download results and reuse proven scripts in skills or routines.

Execution requires the appropriate permissions and a supported runtime. Additional Python packages are available in the macOS package where compatible packages are supported. Programs run in an isolated environment; review the results for accuracy.

Keep agreements for the next task.

“Remember: our reports need an executive summary.”

Store knowledge, working rules and follow-up questions in project memory. The agent uses relevant active entries for the next task. Search, create, edit or deactivate rules directly in chat.

Review changes and resolve open decisions

Before saving, you see the proposed rule text and, for edits, the previous version. Version checks protect against overwriting concurrent changes. Stored questions appear in chat with their defined answer options.

Preview: meetings

The next step for your working day.

Turn a recording into a transcript and structured notes. Meeting features are available as a limited preview. We agree on the version and setup for your use.

Turn recordings into meeting notes.

“What was decided, and who is responsible for each task?”

Upload a recording to receive a transcript and structured notes referencing the relevant passages. Follow-up tasks can be prepared as a CRM proposal for approval.

Current preview scope

A transcription model and a language model must be configured. External models process the recording or its text at the provider. The preview uses file uploads, without a live meeting bot. Long recordings are not yet split automatically; participant matching and retention rules are not fully implemented.

Connect knowledge. Understand relationships.

Start with your documents. Keep working together.

Start on your own with Kivanto Solo or set up a shared instance for your team. You decide which knowledge to include and who can work with it.

Start your day in the dashboard.

The light interface gives your work more room. Jump from the dashboard to chat, documents and customers. Charts show AI requests and the distribution of your project knowledge.

Keep track of activity and usage

Switch between 24 hours, 7 days and 30 days, and open usage details when needed. New agent replies are marked in the conversation list. Kivari helps you find your way and explains features for your edition and permissions.

Keep using the knowledge you already have.

Start with a folder, your project files or a connected document store. Upload multiple files, organise them in the file browser and open search results directly in the preview.

Which sources can I use?

Configure local folders, mounted network drives, Paperless archives, Calibre libraries and ZIM reference works as sources. Local source folders are imported read-only; synchronise to pick up changes. MCP connections add services such as HubSpot, Pipedrive, Monday.com and Brevo. An Odoo provider profile and dedicated Odoo 17 add-on are available; installation, credentials and business model permissions are configured separately.

Share knowledge with the right people.

Organise collaboration by project. Give a colleague access to the documents they need or share a conversation to read and continue. Personal spaces stay separate.

How do teams get started?

The Server edition supports shared use with roles and read/write permissions. MCP connections can be shared with specific roles and people; personal credentials are stored encrypted. Existing Microsoft or LDAP accounts can be connected through central sign-in. Solo remains the free edition for one person. Both interfaces are available in German and English.

Use an AI model that fits the task.

Manage providers and models together under AI models. Assign suitable models to chat and document processing, and choose models for images, transcription and speech output. Combine local and external providers.

What does this mean for data and costs?

With external models, the content needed for a request leaves your instance. Your personal usage dashboard shows available chat token counts and cost estimates based on configured model prices, down to individual calls. Media generation and other external services are not fully included. Missing measurements are shown as unavailable.

Start with a manageable task.

Install Kivanto Solo for Windows, Mac or Linux and follow the setup wizard. Choose an AI provider and add your first documents. For team use, we help with setup, data connections and onboarding.

How do you keep control of your setup?

Desktop packages include the required runtime and a local database. Use the status icon to start or stop Kivanto and reopen model settings. For teams, the shared instance runs on your infrastructure; data transfer, backups and operational procedures are agreed during setup.

Use your own examples to prepare recurring decisions.

Use examples reviewed by your team to distinguish document types and surface signals about sales opportunities, customer risks or possible project delays. Local specialist models help with the initial selection. Your team reviews the signals and decides what to do next.

Learn from your own data and check the results

Unter „Lernen & Modelle“ sammelst Du bestätigte Beispiele, trainierst Modelle und vergleichst ihre Ergebnisse. Eine Aktivierung setzt getrennte Trainings- und Prüfdaten sowie bestandene Qualitätsprüfungen voraus. Ohne passende Beispiele gibt es kein trainiertes Modell für Deine Aufgabe. Training und Ausführung dieser Spezialmodelle erfolgen lokal. Sie können auch Dokumentinhalte, Beziehungen und eng begrenzte Quellenprüfungen unterstützen. Geeignete einfache Rechen- und Wissensabfragen kommen ohne generativen Modellaufruf aus; andere Fragen nutzen weiterhin das eingerichtete Sprachmodell. Hinweise sind keine zugesicherten Vorhersagen oder tatsächlichen Abschlusswahrscheinlichkeiten. Vorgeschlagene Beziehungen werden nicht ungeprüft als Fakten übernommen. Bestätigte Trainingsbeispiele werden separat gespeichert und müssen bei einer späteren Datenlöschung berücksichtigt werden.

Choose a model for the task and your budget.

Compare local models and configured providers in one place. Where providers supply the data, model information and token prices are visible during selection. This helps you weigh suitability against expected costs.

Understand provider choices and cost estimates

Einrichtungsvorlagen unterstützen europäische und internationale Anbieter sowie lokale Modellserver. Verfügbare Kontextgrößen und Preise lassen sich bei unterstützten Anbietern abrufen. Bei anderen Angeboten trägst Du Modell und Preise selbst ein. Die benötigten Fähigkeiten werden für jedes Modell festgelegt. Der Unternehmenssitz eines Anbieters sagt noch nichts über den Verarbeitungsort Deiner Anfrage aus; maßgeblich sind der gewählte Dienst und Dein Vertrag. Preisangaben und das Verbrauchs-Dashboard helfen bei der Einschätzung, ersetzen aber keine Abrechnung. Fehlende Preise werden nicht als kostenlose Nutzung gewertet.

Discuss your workflow

Make everyday responsibilities traceable.

When you need to review access or handle a privacy request, you need traceable records. Kivanto helps you review events and prepare decisions.

Trace what happened when questions arise.

Review who requested project access, when it happened and whether it was allowed. Recorded response, research and settings events add context. Filters and CSV/JSON exports help you assemble relevant entries for a review.

Prepare privacy requests in an organised way.

Record responsibility, deadlines, identity checks and relevant data references in a case. Document your assessment and export the review package. Actual data discovery, disclosure or deletion is carried out separately.

Grant access deliberately.

Projects, roles and sharing settings control access to your knowledge. Personal spaces remain separate. Connected AI assistants also use assigned permissions and revocable keys.

Choose how processing is configured.

Run Kivanto on your infrastructure and choose your data sources and AI models. Local models can keep AI processing within your own environment. External providers are connected deliberately.

GDPR in practice.

For your deployment, you define processing purposes, legal bases, retention and deletion periods, and the required agreements with service providers. Kivanto provides technical access-control and traceability features; GDPR compliance depends on your configuration and organisational processes.

Read the GDPR ↗

Four steps to Kivanto

Define your use case

Initial consultation

We discuss the knowledge your team needs, where it is stored today and the tasks Kivanto should help with.

Choose your setup

Infrastructure & models

Together we choose the installation environment, AI models and team access. We then prepare your proposal.

Connect your knowledge

Sources & projects

We configure the agreed data sources, projects and permissions, then check the results using your documents.

Get your team started

Training & handover

Your team learns to use search, chat and the knowledge graph. If needed, we connect your AI assistants and provide ongoing support.

Daniel Schlager, software developer and specialist in digitalisation and AI

Daniel Schlager · Developer of Kivanto

Daniel Schlager.
The developer behind Kivanto.

Software developer and specialist in digitalisation and AI.

Daniel Schlager has many years of experience in software development. He builds applications, connects existing systems and helps businesses bring digital processes and artificial intelligence into their daily work.

From software architecture to everyday business use.

With Kivanto, he brings this experience together in his own platform for company knowledge and AI. As its developer, he is your direct contact for implementation, data integration and use within your team.

Development and rollout from the same person.

Daniel Schlager develops Kivanto in Salzburg and supports you from the first use case through setup to team adoption. He combines technical experience with an understanding of your business processes.

More about Daniel Schlager ↗

Frequently asked questions

01How does Kivanto help with everyday work?+

Kivanto connects your knowledge to the tasks you want to accomplish: ask about documents, check claims against sources, explore dependencies, prepare customer conversations, organise follow-up tasks and schedule recurring summaries. Media Studio and AI assistants support further work. The instance runs on your infrastructure, with models and connections configured for your needs.

02Can I bring my chats from Claude or ChatGPT?+

Yes, with the local import in Kivanto Solo. The ChatGPT import brings available conversations and files from an extracted data export into one Kivanto project. The Claude / Cowork import covers locally available projects, files and readable chats. Cloud-only content is not retrieved; Claude account-export ZIP files are not supported. A preview shows the scope and missing content before copying. Original files and provider accounts remain unchanged.

03How does Kivanto Solo differ from team use?+

Kivanto Solo is free for one person on their own computer, including professional use. A shared instance for multiple people requires the Kivanto Server edition under a separate agreement. Setup, data integration and support are offered individually.

04Where does Kivanto run, and where is our data processed?+

Kivanto runs on your own infrastructure, either locally on a computer or on a company server. You can configure local models or an external model provider for AI processing. With an external provider, the content needed for each request is sent to that provider. Models and data sources are selected during setup.

05Do we need to replace our files and existing systems?+

Start with existing folders, network drives and supported document repositories. Local source folders are imported read-only and synchronised on request. MCP connections add access to other services and supported actions with approval rules. Odoo 17 can be connected through the Kivanto add-on; Twenty, Microsoft 365 and Brevo have dedicated CRM integrations. Credentials, permissions and data mappings are configured for your accounts.

06Does the AI change or send anything without my approval?+

File, document, CRM and rule changes in Kivanto chat are prepared for human approval. Enabled CRM workflows run their configured actions automatically; you send email drafts in your mail application. Writable MCP tools ask by default. Administrators can explicitly allow individual project tools without asking. Authorised code execution in the private workspace can run directly. External agents use their own approval rules.

07Can I keep using my existing AI assistants?+

Yes. OpenCode, Pi Agent, Cline, Claude Desktop, Claude Code and Codex can access shared project knowledge through MCP. Each client receives its own revocable access. In Solo, you can also start OpenCode tasks directly from chat, using a local project folder and a configured OpenCode installation. External agents use their own models and permissions.

08Can Kivanto edit Word and Excel files for me?+

Yes. The built-in agent can create and selectively edit DOCX and XLSX files. You review a content preview and the changes before approving the file. Editing does not require Office to be installed. New Excel formulas are calculated when opened in Excel. The preview is not a print-accurate Office layout.

09Which new features are available?+

The current version includes the light dashboard with activity charts, dictation and read-aloud, personal skills, folder triggers for routines, code execution with a private workspace, and project rules in chat. Writable MCP tools and the Odoo integration are also available. Required models, permissions and connections are configured for your use. Meeting notes from recordings remain a limited preview.

10Does Kivanto automatically learn from all my data?+

Local specialist models are trained on confirmed examples. You compare results and activate a model only after the required quality checks. There is no automatic training on all your documents. Without suitable data of your own, there is no trained model for your task. Risk and opportunity indicators require professional review.

11Who can see which content?+

Kivanto organises knowledge into projects with members and roles. Personal spaces are separate from shared content. Access by AI assistants is also tied to user permissions. Data sources and sharing settings are configured to suit your teams.

12Do routines run when the browser is closed?+

Yes, as long as the Kivanto instance is running. Routines start on a schedule, through a webhook or when matching changes occur in a watched project folder. Results are saved as conversations. A powered-off or sleeping computer is not woken up. Webhooks require a reachable instance. Actions requiring approval are not automatically approved in routines.

13What records are available for internal reviews?+

The audit log records allowed and denied project access, along with other captured response, research and settings events. Authorised users can filter and export entries. Permission to access does not prove that an action was completed; the log is not a complete, tamper-proof archive. Privacy cases support manual preparation for a decision but do not automatically disclose or erase data.

14How does Kivanto support GDPR implementation?+

Self-hosting, role and project permissions, and traceable access decisions support your technical and organisational privacy measures. GDPR compliance also depends on processing purposes, legal bases, configuration, provider agreements, and retention and deletion policies. Automated access and deletion workflows across all data stores are not yet fully available. Audit logs themselves can contain personal data and must be included in your privacy policies and procedures.

15How do we get started, and what does Kivanto cost?+

You can download Kivanto Solo for free and use it as an individual on your own computer. Central company setup, data integration and support are offered through an individual proposal. Infrastructure and external AI models may incur additional costs.

16Do apps and automation save AI tokens?+

Defined app functions such as totals, form validation and data filters need no model call. Approved app automations execute saved steps without Kivanto planning them again with AI. Creating and modifying an app and adding AI-generated text can still use tokens. Conventional AI routines still use a model. External services may incur their own costs. Your overall savings depend on your workflow and how you use it.

Who would you like to speak with?

Thirty minutes, free and without obligation.

Discuss your use case, your data sources and setting up Kivanto.

Open calendar in a new tab · Alexander Brandstetter

Let's put your knowledge to work.

Start for free with Kivanto Solo on your computer. For team setup and connecting your data sources, we provide personal support.

Download for free ↓office@danielschlager.ai

Less searching.Get more done.