Koji and joinly are both AI meeting assistants for recording, transcription, and summaries, compared here on pricing, features, and workflow fit. Koji: AI-native customer research platform whose AI interviewer runs voice and text discovery conversations at scale, then synthesizes themes automatically. joinly: Open-source, self-hostable connector that lets AI agents join Google Meet, Zoom, and Microsoft Teams calls to transcribe, listen, and act in real time via MCP. They overlap on ai-meeting-assistants, so the right pick depends on team size, budget, and which meeting workflows you automate.
How Hosiqo compares and tests toolsFinal recommendation
For ai-meeting-assistants workflows, shortlist Koji when running exploratory discovery interviews without scheduling live calls matters most, and joinly when building custom ai meeting agents that answer questions and run tasks during live calls matters most. Both record across Zoom, Google Meet, and Microsoft Teams; trial each on real meetings before committing.
AI-native customer research platform whose AI interviewer runs voice and text discovery conversations at scale, then synthesizes themes automatically.
Open-source, self-hostable connector that lets AI agents join Google Meet, Zoom, and Microsoft Teams calls to transcribe, listen, and act in real time via MCP.
Koji is a free tier with paid upgrades (freemium); joinly is a free tier with paid upgrades (freemium). Always confirm current pricing on each vendor's site before buying.
| Feature | Koji | joinly |
|---|---|---|
| Core capability | AI interviewer that runs asynchronous voice and text discovery conversations at scale | MCP server that exposes meeting tools (join/leave, transcript, chat, audio control, snapshots) to AI agents |
| Standout feature | AI research agent that drafts research goals and interview guides from a brief | Real-time transcription with timestamps and speaker information, subscribable for live updates |
| Team usage | Automatic per-interview analysis with key moments and sentiment | Cross-platform support for Google Meet, Zoom, Microsoft Teams, and browser-based calls |
| Integrations | Cross-interview synthesis into study-wide themes, patterns, and recommendations | Modular speech-to-text and text-to-speech backends (Whisper, Deepgram, Kokoro, ElevenLabs) |
| Languages & capture | Insights traceable back to specific participant quotes | Model-agnostic: works with OpenAI, Anthropic, and local LLMs via Ollama |
| Best-fit workflow | MCP integrations with Claude, ChatGPT, Cursor, and Notion | Docker-based self-hosting with optional CUDA GPU image |
Koji
Choose Koji if you need running exploratory discovery interviews without scheduling live calls — strengths include removes scheduling overhead by running many interviews in parallel and asynchronously.
joinly
Choose joinly if you need building custom ai meeting agents that answer questions and run tasks during live calls — strengths include fully open source (mit) and self-hostable for complete data control.
Koji
joinly
It depends on your workflow. Koji is strong for running exploratory discovery interviews without scheduling live calls, while joinly is strong for building custom ai meeting agents that answer questions and run tasks during live calls. Both transcribe and summarize meetings.
Koji is a free tier with paid upgrades and joinly is a free tier with paid upgrades. Check each vendor's pricing page for the latest plans and free-tier limits.
Yes. Many teams run more than one meeting assistant when the workflows are complementary and the budget is justified.