MIT bridge
Free
Open-source code; external services and model costs excluded
- Advertised scope
- Specialist prompts bridged to meeting voice participants
Specialist AI participants for meetings · Official-source review 2026-10-09
This open-source project adapts gstack specialist prompts into voice participants for Google Meet, Zoom and Teams through AgentCall. Users can select individual specialists or preset teams to discuss plans in a meeting.
For developers experimenting with specialist prompts in live discussions while retaining control of their agent environment.
Nineteen specialist personas and six team presets advertised. A YC-office-hours persona is not a real partner, official interview or endorsement. Shared demo pool can be busy; bring-your-agent path uses the existing Claude Code/Codex/Cursor account. Zero LLM cost on the page means no vendor token charge, not free provider access. Local agent context does not prove all meeting data stays local: voice and avatar plumbing uses AgentCall and the meeting provider. Latency and availability claims not independently tested. No installation, meeting joined, audio transmitted or interview exercise performed.
Obtain meeting participants’ agreement, scope the agent’s context and permissions, and treat its feedback as suggestions to verify.
Nineteen specialist personas and six team presets advertised. A YC-office-hours persona is not a real partner, official interview or endorsement. Shared demo pool can be busy; bring-your-agent path uses the existing Claude Code/Codex/Cursor account. Zero LLM cost on the page means no vendor token charge, not free provider access. Local agent context does not prove all meeting data stays local: voice and avatar plumbing uses AgentCall and the meeting provider. Latency and availability claims not independently tested. No installation, meeting joined, audio transmitted or interview exercise performed.
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | This open-source project adapts gstack specialist prompts into voice participants for Google Meet, Zoom and Teams through AgentCall. Users can select individual specialists or preset teams to discuss plans in a meeting. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Nineteen specialist personas and six team presets advertised. A YC-office-hours persona is not a real partner, official interview or endorsement. Shared demo pool can be busy; bring-your-agent path uses the existing Claude Code/Codex/Cursor account. Zero LLM cost on the page means no vendor token charge, not free provider access. Local agent context does not prove all meeting data stays local: voice and avatar plumbing uses AgentCall and the meeting provider. Latency and availability claims not independently tested. No installation, meeting joined, audio transmitted or interview exercise performed. | Facts sourced | 2026-10-09 |
Understand the total cost
MIT bridge
Free
Open-source code; external services and model costs excluded
Meetily is a privacy-first AI meeting assistant that records, transcribes, and summarizes calls locally on your device. It targets Zoom, Teams, and Google Meet users who want offline-ready workflows, open-source community edition software, and optional Pro licenses for diarization and exports.
Explore toolOtter is an AI meeting agent that transcribes conversations in real time, generates summaries, and supports chat across meetings for sales, education, and media teams. It integrates with Zoom, Microsoft Teams, and Google Meet plus CRM and automation tools on higher tiers.
Explore toolTactiq is a Chrome-based AI note taker that transcribes Google Meet, Zoom, and Microsoft Teams calls without a bot joining the room. It delivers live transcripts, one-click AI summaries, action items, Ask AI prompts, and workflow exports to Slack, Notion, Linear, and HubSpot.
Explore toolThe practical questions
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
This open-source project adapts gstack specialist prompts into voice participants for Google Meet, Zoom and Teams through AgentCall. Users can select individual specialists or preset teams to discuss plans in a meeting.
MIT bridge code available for self-use. Coding-agent subscriptions, inference, AgentCall service and infrastructure terms are separate and unconfirmed.. This record lists ongoing free access; check the plan limits before starting.
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
AgentCall bridge and local coding-agent sessions documented. Separate public API pricing and stable endpoints not verified on this page.. API access and subscription access may have different terms; consult the linked sources.
Nineteen specialist personas and six team presets advertised. A YC-office-hours persona is not a real partner, official interview or endorsement. Shared demo pool can be busy; bring-your-agent path uses the existing Claude Code/Codex/Cursor account. Zero LLM cost on the page means no vendor token charge, not free provider access. Local agent context does not prove all meeting data stays local: voice and avatar plumbing uses AgentCall and the meeting provider. Latency and availability claims not independently tested. No installation, meeting joined, audio transmitted or interview exercise performed.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Current official product source read individually; product artwork inspected visually.
Read original source ↗Official product page reviewed for disclosed costs; unverified prices and allowances are identified in the listing.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.