Whistle Enterprise
Otter.ai
Meetly.ai
Hacker News Search
Fireflies.ai
Briefly AI
SecurityBot.dev
SkaldMaps
GitHub
GitLab
BitBucket
VS Code
Git
Treehouse
Pantheon
CodePen
Whistle Enterprise is an offline AI meeting assistant for Windows. It records the audio on the computer running the meeting, transcribes it locally with speaker labels, and writes a structured meeting document using a custom fine tuned AI model from BlazingBanana Ltd. Both models run on the user's own computer, designed for a normal laptop CPU with no internet required.
There is no bot in the meeting. No audio leaves the device. No account is required. Disconnect from the network and the same recording can still be processed.
Every line in the generated document traces back to the transcript line it came from. Export to PDF, Word, Markdown or plain text.
Built for law firms, advisory teams, compliance leads, HR and anyone else whose meetings cannot be sent to a cloud service.
Whistle Enterprise GitHubWhistle Enterprise's answer
Recording, transcription and AI writing all run on the user's own computer. No bot joins the call. No audio leaves the device. A custom fine tuned AI model from BlazingBanana writes the structured meeting document on a normal laptop CPU. Every line in the document traces back to the transcript line it came from, so the record is checkable.
Whistle Enterprise's answer
Because the conversation does not leave the user's computer. There is no bot to disclose in a client meeting, no account to create, no external internet connection at any point. Whistle Enterprise is bought once per seat with a year of updates included. After the update year ends, the licensed software keeps working forever. Only new releases stop being available.
Whistle Enterprise's answer
There are conversations Tobias did not want sending to a cloud provider, and every other tool required it. So he built Whistle Enterprise. The custom AI model from BlazingBanana was built specifically for meeting document generation, and the whole pipeline runs on the user's own machine because the people who most need this kind of record are the ones who cannot lawfully send the audio anywhere else.
Whistle Enterprise's answer
Law firms, advisory teams, compliance leads, HR, public sector teams and anyone else whose meetings cannot be sent to a cloud service. The audience is defined by the kind of work, not the size of the company. Client conversations, witness statements, board discussions and investigations all need a proper written record but cannot lawfully be sent to a third party processor.
Whistle Enterprise's answer
Closed source commercial software. The installer bundles a published speech recognition model for transcription and a custom AI model from BlazingBanana for document generation. Both run on the user's CPU on a normal work laptop, with no GPU required and no external model fetch at runtime.
Based on our record, GitHub seems to be a lot more popular than Whistle Enterprise. While we know about 2473 links to GitHub, we've tracked only 3 mentions of Whistle Enterprise. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
Still working away at https://whistle-enterprise.com. Have spent the last month giving the UI a bit of a modernisation refresh and simplifying/improving some elements based on early user feedback. There's also been a boat load of performance improvements in the dirarisation and document generation pipeline. Feel free to download the prerelease version (its unsigned) here -... - Source: Hacker News / 19 days ago
I fell down the rabbit hole of voice transcription about a year ago, always had a love for utilising small language models so have put two and two together and built https://whistle-enterprise.com. The biggest challenge being it all running on CPU with the target device being your low to mid spec office laptop that's a few years old (I5, 8gb RAM). All nicely packaged together in a single selfcontained app that you... - Source: Hacker News / about 2 months ago
I used LLMs to develop Whistle Enterprise (https://whistle-enterprise.com) from the ground up, from scratch. It's taken _a lot_ of time and effort, but this is an example of what can be developed using LLMs alone. You have to have dedication and a goal to reach, but you can absolutely build anything if you're building with the right foundations in mind. - Source: Hacker News / about 2 months ago
Is published at https://github.com/.keys so an SSH server to which you connect could do a reverse lookup. This is the reason why my ~/.ssh/config has those 2 lines at the end:- Source: Hacker News / 2 days agoHost *.
All of this assumes you can actually inspect what the agent did โ the real inputs after resolution, the real tool outputs, the real intermediate steps. That is the other half of the workflow. AgentLens captures the trace: every model and tool step, resolved inputs, raw outputs. agent-eval scores and gates the output; AgentLens gives you the unforgeable, agent-didn't-author trace data for Tier 1+2 to score against... - Source: dev.to / 3 days ago
# git: the API token, plus the credential used for the push Kubectl create secret generic foreman-github \ --from-literal=GITHUB_TOKEN="$GITHUB_TOKEN" -n foreman-system Kubectl create secret generic foreman-git-credentials \ --from-literal=token="$GITHUB_TOKEN" -n foreman-system Helm upgrade foreman llmkube/foreman -n foreman-system --reuse-values \ --set agent.githubToken.secretName=foreman-github \ ... - Source: dev.to / 3 days ago
This is why eval and observability ship as a unit, not as separate purchases. agent-eval scores and gates the output โ the tiers above, drift, hallucination. AgentLens captures the trace of how the agent got there: every model step and tool call, the resolved inputs, the raw outputs, the trajectory. Two things fall out of that:. - Source: dev.to / 13 days ago
The real fragility is in trying to constrain arguments. The docs are explicit that a pattern like Bash(curl http://github.com/ *) fails to do what it looks like it does. It won't match curl -X GET http://github.com/... (option before the URL), curl https://github.com/... (different protocol), curl -L http://bit.ly/xyz (redirects to GitHub), URL=http://github.com && curl $URL (variable), or curl http://github.com... - Source: dev.to / 14 days ago
Otter.ai - Your AI meeting assistant that takes live notes and generates summaries and other insights using Meeting GenAI.
GitLab - Create, review and deploy code together with GitLab open source git repo management software | GitLab
Meetly.ai - If Google Calendar & Trello had an AI scheduling assistant
BitBucket - Bitbucket is a free code hosting site for Mercurial and Git. Manage your development with a hosted wiki, issue tracker and source code.
Hacker News Search - a faster hnsearch
VS Code - Build and debug modern web and cloud applications, by Microsoft