# BibiGPT

> Probe-verified (tier 2 of 3). Last checked 2026-08-23. 4 of 5 capability checks passed.

- host: bibigpt.co
- url: https://bibigpt.co/
- category: ai video summarization tool
- type: saas
- language: zh

## Probe-verified · tier 2 of 3

Probed live on 2026-08-23 against rubric v1. 4 of 5 checks passed.

- PASS — Markdown negotiation
- PASS — Markdown twin at a predictable URL
- fail — llms.txt
- PASS — API catalog
- PASS — MCP server answers

MCP tools (from tools/list on 2026-08-23): summarize_video, summarize_video_with_config, summarize_by_chapter, create_summary_task, get_task_status, get_subtitle, get_account_info, get_latest_feed, get_channel_health, mark_feed_seen, list_saved_videos, get_saved_video

## Unverified actions

Read from the page's own content, with the wording each was drawn from. Inference is kept separate from tested facts; an agent completing the action is tier 3.

- **register** — "Start your free trial now!" → `https://bibigpt.co`
- **contact** — "Contact: https://bibigpt.co/contact" → `https://bibigpt.co/contact`
- **query_api** — "Call those capabilities from an agent via MCP (`https://bibigpt.co/api/mcp`)" → `https://bibigpt.co/api/mcp`
- **query_api** — "OpenAPI (`https://bibigpt.co/api/openapi.json`)" → `https://bibigpt.co/api/openapi.json`

## Summary

BibiGPT is an AI tool that summarizes and transcribes audiovisual content from multiple platforms with timestamped structured outputs and API access.

## Context

2 sites in this index share the category "ai video summarization tool"; 2 are transactional.

## How we grade

- tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability.
- tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
- tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked.

## About this record

Known-Good probes sites live and publishes what was tested and when.
Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark