Humata
ProductivitySearch, summarize and compare uploaded documents with source-linked answers. Humata adds team-oriented document access and page-based plans for ongoing knowledge work.
Questions across filesCited passages
VANE / THE PROJECT FORMERLY KNOWN AS PERPLEXICA
Vane (formerly Perplexica)
The project formerly known as Perplexica is now Vane: a free self-hosted AI answering engine combining web search, source-linked responses and local or cloud model choices.
Official Vane product screenshot from the current repository; illustrative answer, not independently verified researchExplore the image ↓
What you can do with it
What this tool is for
Vane is the current name of the project previously linked as Perplexica. The old repository address redirects to Vane, whose documentation describes an AI answering engine with web search, model configuration and source-linked responses. This listing preserves the previous name to help existing users find the same project without counting it twice.
The software is useful for people who want control over their search application and inference provider. It is still a retrieval-and-generation workflow: search coverage, source quality and the chosen model affect the result. A response containing citation markers needs the same source checking as any other AI-assisted research draft.
01
Research a technical option
02
Compare public claims
03
Explore an uploaded reference file
04
Prototype an internal search interface
A closer look at the product
Official product image. Click to inspect the details.
Product interface and examples
Key features, practical tasks
Capabilities in practice
- Configurable model providers: The project supports local models through documented paths and several cloud providers. Set the model actually available in your environment rather than copying an example name that may no longer be supported.
- Search-source choices: The API documents web, academic and discussion source choices. Select the type that fits the question and inspect the resulting pages; an academic mode does not certify every returned claim.
- Search modes: Speed, balanced and quality modes expose different search behavior. Treat them as workflow settings, not guarantees of a particular latency or correctness level on your hardware.
- SearxNG integration: The documented default container bundles a metasearch backend, with an option to use a separate instance. The backend still queries external search sources and depends on their availability.
- File-based questions: The project describes uploaded-document questions and semantic retrieval over files. Check extraction and relevant passages before assuming an uploaded file has been understood completely.
- Source-linked answers and history: The interface displays sources and retains conversations on the configured storage. Preserve the original links and dates when turning a search session into a durable research note.
- Programmatic search: The API returns answer text and source information, with streaming options. Applications should validate returned fields and handle incomplete or failed requests instead of assuming every call yields a finished answer.
Get started, step by step
- 01
Install the current project
- 02
Configure models and storage
- 03
Run a bounded research question
- 04
Verify and save findings
A practical first workflow
A practical first workflow
- Install the current project. Follow Vane’s current installation documentation rather than an old Perplexica command copied from a third-party article. Choose the bundled or separate search-backend route.
- Configure models and storage. Set the supported chat and embedding roles as required, confirm the data location and protect credentials. A successful UI load does not prove inference or search is configured.
- Run a bounded research question. Start with a topic whose evidence you can inspect. Check that the returned sources are relevant and accessible before judging the generated prose.
- Verify and save findings. Open the important source pages, confirm dates and preserve supported conclusions. Keep uncertain or conflicting statements labeled rather than smoothing them into one confident answer.
Example prompt or task: Research this narrowly defined technical question using relevant primary documentation. Return source links, identify version assumptions and distinguish what the sources state from your interpretation.
This is an editorial research prompt. FindGoodAI has reviewed project materials, not run a controlled accuracy or speed comparison of Vane.
Find the right plan for you
Free open-source software
Explore official plans ↗Free software Compute and external services are separate
Local-model support provides a route without a required paid language-model API. Web searches still contact external services, and self-hosting does not make browsing offline.
What is free and what can cost extra
Vane is MIT-licensed and can be self-hosted without an application subscription. A compatible local-model setup can avoid commercial per-request inference billing, while using your own hardware, storage and electricity.
Cloud models, hosted infrastructure and optional external services have separate terms and potential costs. The open-source project does not include unlimited paid API credits. Because online search contacts outside sources, the free local software route should not be confused with fully offline research.
A few things worth knowing
Frequently asked questions
Is Vane the same project as Perplexica?
The previous repository URL redirects to the current Vane project; this listing keeps both names for continuity.
Is it free?
The MIT software is free to self-host. Compute and connected services are separate.
Can it use local models?
The project documents local-model support, including Ollama-related setup.
Does local hosting make web search offline?
No. Searching the web still requires external requests.
Are citations proof that an answer is correct?
No. Open the cited pages and check whether they support the associated claim.
Does quality mode guarantee the best result?
No. It is a configuration choice whose outcome depends on sources, model and task.
Can I expose a fresh installation publicly?
Review access controls first. The reviewed roadmap still lists built-in authentication as upcoming, so do not assume it is already provided.
The details behind your decision
Explore platforms, inputs and outputs, licensing, and access requirements.
Four useful starting projects
Four useful starting projects
- Research a technical option: Ask a concrete implementation question and inspect official documentation among the sources. Record which version the answer applies to before using it in a project.
- Compare public claims: Collect the original pages behind competing statements and separate direct evidence from commentary. Use the generated comparison as a draft rather than as the final authority.
- Explore an uploaded reference file: Ask a narrow question about a permitted document. Check the relevant passage and note when the result relies on general model knowledge instead of the file.
- Prototype an internal search interface: Call the documented search API with explicit model and source settings. Display source links and failure states so users can assess where an answer came from.
Platforms, inputs, outputs and setup
Platforms, inputs, outputs and setup
The current project recommends a container route and also documents source installation. Model-server networking and persistent storage need to match the deployment environment; keep a record of the working versions and configuration.
Typical inputs are questions, conversation history and supported uploaded files. Outputs are generated answers with source metadata. API clients must use the actual provider and model identifiers returned by their instance, not illustrative identifiers copied from documentation.
Data, permissions and licensing
Data, permissions and licensing
Local storage and local inference can reduce external processing, but web queries, page retrieval and configured cloud models have their own data paths. Avoid including private details in queries that will be sent to public search services.
The reviewed repository lists authentication among upcoming features. Keep the instance appropriately restricted or provide reviewed access controls before remote exposure, and protect uploaded files and stored search history as working research data.
Sources, documentation and help
Official sources and review date
Official sources and review date
Reviewed October 3, 2026. Product facts come from the official sources below. Suggested projects, prompts and review methods are FindGoodAI editorial guidance, not measured performance results.
Your experience can help someone choose
COMMUNITY
Sign in to rate and comment
Tried it? Share your experience
Loading experiences…
Manage my comments
Community and moderation
Saved tools are private. Approved comments are public; edits return to moderation. Comment counts include approved comments and replies. Each person has one rating. New ratings are automatically approved; withdrawn, unapproved or invalid ratings do not count. Share real experiences and avoid spam, private information or personal attacks.
For moderation appeals or data requests: support@findgoodai.com
NEXT STEP
Explore Vane (formerly Perplexica) ↗Build a search workflow whose sources you can inspect
Bring a real task and see how it fits the way you work.
Jump to a section
User experiences