Launching today

Kassinão

Launching today

The Discord bot that turns calls into searchable memory

3 followers

The Discord bot that turns calls into searchable memory

3 followers

Visit website

Kassinão turns Discord calls into searchable team memory. It records one track per speaker, then creates named transcripts, meeting notes, decisions, action items, and answers with source links. Ask inside Discord or from an MCP-capable AI assistant. It is free, AGPL open source, and self-hosted, with access rechecked against Discord membership and meeting permissions.

Free

Launch tags:Productivity•Open Source•Artificial Intelligence

Launch Team / Built With

Blocks.aiThe Control Plane & Network Layer For AI Agents

Promoted

Maker

📌

Hey Product Hunt 👋 I built Kassinão around a Discord-specific advantage: the platform already exposes a separate voice stream for each participant. Instead of mixing everyone together and trying to infer speakers afterward, Kassinão keeps that identity from capture to transcript. Start with /record. When the call ends, you get a named transcript, meeting notes, decisions, action items, timestamped notes, downloads, and /ask answers with links back to their sources. The same authorized meeting memory can be queried through a read-only MCP connector from Claude Desktop, Cursor, and other MCP clients. Kassinão is free and AGPL open source. You self-host it, control retention, and choose local transcription or supported cloud providers. Recording stays visible inside Discord, and access to each meeting is rechecked against Discord membership and meeting permissions. The public demo uses fictional data but the real product interface, so you can explore a finished meeting without signing in. I’d especially value feedback on three things: the Discord workflow, the self-hosting experience, and which meeting-memory query should become the next MCP tool.

Report

2d ago

The per-speaker track separation that flows into named transcripts is a thoughtful detail. Most tools give you a blob of text, but tying each line back to its actual voice makes the search and source links genuinely trustworthy instead of just a nice idea.

Report

5h ago

Forum Threads

p/kassinao

•

2d ago

Why Kassinão preserves speaker identity before transcription

Most meeting tools receive one mixed audio stream and try to reconstruct who said what afterward. Discord gives us a better starting point: a separate voice stream for each participant.

Kassin o keeps that identity from capture to transcript, then turns the call into searchable notes, decisions, tasks, and answers with source links. The same authorized meeting memory can be queried from Discord or through a read-only MCP connector.

It is free, AGPL open source, and self-hosted. The public demo uses fictional data, so anyone can explore a finished meeting without signing in.

We launch July 16. I m curious: if your team could ask one reliable question across all its past calls, what would it be?

View all