Verbatim turns meeting transcripts into a structured, queryable record of every commitment, decision, open question, and blocker — each one sourced to an exact verbatim quote. Slack, GitHub, Linear, Jira, daemon mode, local LLMs. Free forever.
$ verbatim ingest standup.txt ✓ Saved 4 items from standup.txt VRB-a1b2c3d4 commitment Qat → ship CULA prototype (Friday) VRB-e5f6a7b8 decision use Kafka for replay cache VRB-9c0d1e2f question who owns the m2w domain config? VRB-3a4b5c6d blocker waiting on Cyren tier-3 JWT $ verbatim show a1b2c3d4 VRB-a1b2c3d4 commitment open high-confidence Actor: Qat Deadline: Friday Quote: "I'll have the CULA prototype shipped by Friday." Source: standup.txt · line 47 · 2026-05-18
Every extraction must point at the exact words that produced it. No hallucinated action items. No summarized "the team agreed to…" with no receipt.
Actor, deliverable, deadline. Open → confirmed → resolved status flow.
The choice and the alternative it ruled out. Searchable later.
What was asked and not answered. Auto-promotes to a follow-up.
Item, blocked-by, owner. Visible across surfaces until cleared.
Verbatim runs locally as a CLI, daemon, MCP server, or web UI — and bridges into the tools you already use.
Linear-style three-pane browser, dark / light theme, full-text and entity-type filters.
Confirm, dismiss, edit, reassign — straight from a Block Kit card in the channel.
Watches a folder, ingests new transcripts, posts a digest. Set and forget.
Plug Verbatim's memory into Claude, Claude Code, or any MCP-aware agent.
Sync commitments to GitHub Issues, Jira, or Linear with one command.
Anthropic Claude by default — or any tool-calling model via Ollama. $0, air-gapped.
Per-model spend tracking, daily budget caps, dry-run mode before any paid call.
Slack live API, Slack export ZIP, GitHub PR discussions, plain transcripts.
Python 3.10+. One pip install, then run the init wizard.
# install pip install verbatim-ai # interactive setup — picks model, API keys, default surfaces verbatim init # extract from a transcript verbatim ingest meeting.txt # browse the web UI on localhost:8765 verbatim web # or run fully local on Ollama, no API key required verbatim ingest meeting.txt --model ollama:llama3.1:8b