# video-db/call.md

Turn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls.

Repository: https://github.com/video-db/call.md
Canonical: https://ross.abutalabs.com/products/callmd
Homepage: https://docs.videodb.io/examples-and-tutorials/ai-copilots/call-md
Language: TypeScript
License Family: other
Topics: agentic-ai, agentic-workflow, ai, mcp, meeting, meeting-notes, note-taking, notes-app, skills
Last push: 2026-08-19T06:24:36+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 13
- inputs: {"age_days": 189, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1132, forks 131 (observed 2026-08-28T04:03:42.784561+00:00)

## What it is
Call.md is an open-source Electron desktop app that records meetings locally, transcribes them in real time with speaker separation, and provides live AI intelligence during calls. After the meeting it generates summaries with action items and can trigger MCP tools and workflow automations via webhooks.

## Use cases
- transcribe meetings in real time with speaker separation
- get live AI suggestions and coaching during calls
- generate meeting summaries with action items automatically
- trigger MCP tools and automations from conversation context
- track conversation metrics like talk ratio and pace
- push meeting notes to CRM or project management tools
- take AI-assisted meeting notes without a bot joining the call

## When to choose
- you want real-time meeting intelligence rather than post-call transcription only
- you want an open-source alternative to Otter.ai or Fireflies.ai with agent automation
- you want meetings to trigger MCP tools and workflow webhooks automatically
- you are on macOS and want local recording with dual-channel transcription

## When to avoid
- you need recording on Linux or Windows ARM64, which are not supported
- you need a fully self-contained tool without a VideoDB API key dependency
- you need a polished Windows installer, which is not yet published
- you only need simple passive transcription without AI features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, agent-framework, mcp, audio-processing, workflow-automation, chatbot
- domain: developer-tools, artificial-intelligence, speech-processing
- platform: windows
- tags: meeting-notes, meeting-transcription, real-time-ai, ai-copilot, mcp-tools, video-meetings, action-items, videodb, ai-agents, automation, macos, linux, electron, desktop, typescript, nodejs

## Member repositories
- video-db/call.md (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:42.784561+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:37:59.945621+00:00, confidence not recorded.
  - readme: https://github.com/video-db/call.md (fetched 2026-08-28T04:03:42.784561+00:00, sha 25b30fcc61a9)
  - homepage: https://docs.videodb.io/examples-and-tutorials/ai-copilots/call-md (fetched 2026-08-29T12:42:35.521483+00:00, sha 37702952fcb1)
  - site_page: https://docs.videodb.io/ (fetched 2026-08-29T12:42:35.530741+00:00, sha 869205365e8d)
  - site_page: https://docs.videodb.io/pages/community/about-us (fetched 2026-08-29T12:42:35.532935+00:00, sha 200c37609263)
  - site_page: https://docs.videodb.io/examples-and-tutorials/live-intelligence/multicam-quickstart (fetched 2026-08-29T12:42:35.534343+00:00, sha 2345f13806d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.