HumlaHumla
AI chat

Ask your meetings anything.
It stays on your Mac.

Humla's chat searches your meeting history, reads the notes that matter, and answers with citations. Fully offline with local models, or with your own OpenAI key. Free either way.

Download for macOSHow it works
  • Open source
  • Works offline
  • No quotas
What it's like

It actually looks for the answer

Most chat with your notes tools run one search and hope. Humla searches, reads and tries again before it answers, and shows you where every answer came from.

Works the question

It searches, opens the notes that look promising, tries a different angle if the first search misses, and only then answers. You watch it happen, so you know where the answer came from.

Answers you can check

Every answer comes with citation chips. Click one and you land in the source note, on the day it happened.

Finds it by meaning

Notes are indexed in small pieces, by keyword and by meaning. So “the pricing discussion from spring” finds the right stretch of a call from May, even if nobody said the word pricing. We test it daily in Norwegian and English, and the models underneath handle most languages.

Ask wide or narrow

Point a question at this note, its folder, or everything you've ever recorded, right from the composer. Every note keeps its threads, so you can pick one back up next week.

Under the hood

Agentic RAG, on your Mac

Agentic retrieval

The model gets three tools, search, read a note and browse, and loops up to six steps before it answers. If retrieval comes up empty, it says so instead of guessing.

Hybrid search

SQLite FTS5 (BM25) plus embedding similarity, fused with reciprocal rank fusion, over paragraph aware chunks of about 750 tokens from the body, transcript and summary.

Local models

Chat via Ollama, where Gemma and Qwen run well on Apple Silicon. Embeddings via EmbeddingGemma, on device. The cloud path is your own OpenAI key, nothing else.

Your data, your disk

Notes, search index and chat history live in local SQLite. And it's open source, so you can read the code.

Private

Fully private, if you want

Point Humla at a local model in Ollama and everything, the chat model and the search index, runs on your Mac. Nothing leaves your machine, and the local experience is the whole product, not a demo tier. Prefer cloud? Bring your own OpenAI key. Either way, personal chat is free forever, with no quotas and no meters.

Teams

The same chat, for your whole team

On Humla Cloud, chat works across your team's shared workspace. Ask about any meeting, whoever took it, and get cited answers. Conversations are visible to the workspace, so teammates build on each other's threads.

Humla for teams

FAQ

Questions and answers

Does chat send my notes to the cloud?

Only if you choose a cloud chat provider: OpenAI, Anthropic or GitHub Copilot. With a local model in Ollama, the chat model and the search index both run on your Mac — nothing leaves your machine.

What does chat cost?

Nothing. The app is free and open source, and personal chat has no quotas or meters. If you use OpenAI you pay them for your own usage; with local models there's nothing to pay at all.

What do I need to run it offline?

Ollama, plus two downloads: a chat model (Gemma or Qwen) and EmbeddingGemma for search by meaning. Humla's settings walk you through both.

Which languages does it work in?

Norwegian and English are what we test daily, including notes that mix both. The models underneath are multilingual — a hundred-plus languages — so most languages work fine. If it handles Norwegian, it can probably handle yours.

Which AI models does it use?

Your choice: local models through Ollama, or OpenAI with your own key. The local experience is the full product — same search, same citations, same everything.

Every answer you need is already in your notes.

Free and open source. Apple Silicon, macOS 13 or later.

Download for macOSView the source