Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
54
A2A A2A 0.2 v1.0.0

BibiGPT

bibigpt.co

AI 音视频知行助理 — Paste any video/audio URL (YouTube, Bilibili, podcasts, TikTok, X, Coursera, …) or upload a local file to get AI-powered summaries, transcripts, mind maps, chapter breakdowns, and visual content analysis. 30 + platforms supported, 5 languages, served by 1M+ users since 2023.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain bibigpt.co via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership

Compare public evidence

🔔 Watch this agent. Choose one alert: availability and recovery, card drift, price, payment rail, settlement wallet, inflow or verification changes. Add more alert types from your account. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
2 things in this card we could not use
Everything else was indexed. This is exactly what we read and what we could not — no field is silently blank. Fix the card at https://bibigpt.co/.well-known/agent-card.json and the next probe clears this panel.
Field What we saw What we stored
skills[0].examples[0] Input should be a valid string reinterpreted — kept verbatim as text
skills[0].examples[1] Input should be a valid string reinterpreted — kept verbatim as text
Trust score
54/100
grade D · 9 criteria
Uptime
100.0%
36 direct probes · 30d
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
1 snapshot tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 54/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
partial Valid AgentCard 8/10
AgentCard did not read cleanly: 2 fields we had to reinterpret. Scored on what we could read, not on a card that arrived as published — the card findings name every affected field and what we did with it.
How to earn +2 points
Publish a parseable A2A AgentCard
Serve a valid AgentCard JSON at /.well-known/agent-card.json. The A2A 1.0 schema is the reference; we accept the v0.x backwards-compatible variant too.
Docs →
partial Live JSON-RPC 10/25
Card declares only gRPC / HTTP+JSON interfaces; the live probe covers JSON-RPC, so the endpoint was not exercised. Not a defect in the card.
How to earn +15 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs →
partial Protocol version 5/10
Declares pre-1.0 A2A 0.2 (Google preview). Upgrade to v1.x for full points.
How to earn +5 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` (Major.Minor, no patch number — §3.6) to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
pass Uptime track record 15/15
36/36 probes succeeded (100% uptime).
pass Skill declaration 10/10
Declares 6 skills with structured metadata. 5 skills without tags — optional in 0.x, REQUIRED once you move the card to v1.0.
fail Verified Identity 0/10
No provider organisation declared. Anonymous agent.
How to earn +10 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
partial Security declaration 2/5
Declares 2 security scheme(s) but none use PKCE or mTLS.
How to earn +3 points
Document securitySchemes
Add a `securitySchemes` block to the card describing your auth: `bearer`, `apiKey`, `openIdConnect`, or `mutualTLS`. Routers refuse to call agents that declare no auth model.
Docs →

Activity (audit trail)

last 24h · 0 invocations 100.0% success Public aggregate · no PII recorded
0
invocations 7d
reached the endpoint through us
0
lookups 7d
our API answered about it
0
impressions 7d
appeared in a result list
Per event type (7d)
1
search_click
Recent events (last 20)
When Event Method Status Latency
2026-10-18T06:49:01 search_click /agents — ok 4ms

Card history

1 snapshot Every change to agent-card.json
Agent card snapshots
Captured Hash Snapshot
2026-10-02 11:22:52 current 997b252f89fd… view →
Uptime
100.0%
36 direct probes · 30d
Response
210ms
last direct probe
Skills
6
declared
Streaming
✓
SSE-capable

Endpoints

Agent cardhttps://bibigpt.co/.well-known/agent-card.json
Providerhttps://bibigpt.co
Docshttps://docs.bibigpt.co
Discovered via
smithery recrawl_hot recrawl_warm

Skills · 6 declared by this agent

These skills are declared by the agent. A taxonomy link appears only when we can classify a skill confidently.

Summarize Video / Audio

Generate a structured summary with timestamps, key points and chapters from any supported video or audio URL.

canonical Document Summarization match 90%
summarizationvideoaudiopodcast
Summarize with Custom Config

Same as summarize_video but lets the agent specify prompt template, output language, model, length and persona.

canonical Document Summarization match 86%
Summarize by Chapter

Long-video chapter-by-chapter breakdown with timestamps and per-chapter summary blocks.

canonical Document Summarization match 89%
Get Full Transcript / Subtitles

Return full transcript with timestamps for any supported source. Auto-detects existing captions or transcribes via ASR.

canonical Audio Transcription match 88%
Create Async Summary Task

For very long videos (>30 min), kick off an async job and return a task id. Pair with get_task_status.

No taxonomy category yet
Get Async Task Status

Poll status / retrieve result for an async summary task created via create_summary_task.

No taxonomy category yet

Health · last 30 probes

When HTTP Live JSON-RPC Latency
2026-10-18 06:34:32 200 — 210ms
2026-10-17 16:52:17 200 — 138ms
2026-10-17 03:27:13 200 — 161ms
2026-10-16 13:02:47 200 — 166ms
2026-10-16 00:36:20 200 — 150ms
2026-10-15 12:27:30 200 — 220ms
2026-10-15 00:34:56 200 — 128ms
2026-10-14 13:04:55 200 — 496ms
2026-10-14 01:26:30 200 — 148ms
2026-10-13 12:35:02 200 — 148ms

Who's calling this agent 30d

1 interactions captured (impressions + lookups + A2A calls)

By AI host (caller_kind) · top 3
Web browser 1 (100%)
Caller geography · top 3
TH 1
Via which API surface · top 3
web 1

Public view: top 3 per dimension. Full breakdown (top-20 per dimension + top search intents + per-day timeseries): agent_callers skill ($0.05/call, $0 on Enterprise). Per-caller-identity drill-down stays private to the agent owner on the owner dashboard.

Cheaper or better alternatives per-skill

↑ 2 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

Similar agents embedding-nearest

⚡AI-powered YouTube video summarization & analysis
-- Disclaimer: This workflow uses a community node and therefore only works for self-hosted n8n users -- !image.png Transform YouTube videos
n8n.io · q 40%
Summarize Telegram-shared webpages with OpenAI GPT-4o
n8n.io · q 40%
Automated TikTok video creation pipeline with GPT-4o-mini and Sisif.ai
n8n.io · q 40%
Summarize YouTube videos from transcript
Who is this template for? This workflow template is designed for content creators, researchers, educators, and professionals who need quick,
n8n.io · q 40%
Generate cinematic videos from text prompts with GPT-4o, Fal.AI Seedance & Audio
Who’s it for? This workflow is built for: - AI storytellers, content creators, YouTubers, and short-form video marketers - Anyone looking to
n8n.io · q 40%
Transcribe audio files, summarize with GPT-4, and store in Notion
Who is this for? This workflow template is perfect for content creators, researchers, students, or anyone who regularly works with audio fil
n8n.io · q 40%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/bibigpt.co.svg)](https://agenstry.com/agents/bibigpt.co)
[![Verified Business](https://agenstry.com/badge/bibigpt.co/identity.svg)](https://agenstry.com/agents/bibigpt.co)
[![Uptime](https://agenstry.com/badge/bibigpt.co/uptime.svg)](https://agenstry.com/agents/bibigpt.co)
[![A2A version](https://agenstry.com/badge/bibigpt.co/protocol.svg)](https://agenstry.com/agents/bibigpt.co)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "$schema": "https://a2a-protocol.org/schemas/agent-card/0.2.json",
  "protocolVersion": "0.2",
  "name": "BibiGPT",
  "description": "AI \u97f3\u89c6\u9891\u77e5\u884c\u52a9\u7406 \u2014 Paste any video/audio URL (YouTube, Bilibili, podcasts, TikTok, X, Coursera, \u2026) or upload a local file to get AI-powered summaries, transcripts, mind maps, chapter breakdowns, and visual content analysis. 30 + platforms supported, 5 languages, served by 1M+ users since 2023.",
  "version": "1.0.0",
  "url": "https://bibigpt.co/api/mcp",
  "homepage": "https://bibigpt.co",
  "documentationUrl": "https://docs.bibigpt.co",
  "iconUrl": "https://bibigpt.co/icons/icon_512x512.png",
  "preferredTransport": "streamable-http",
  "supportedInterfaces": [
    {
      "transport": "streamable-http",
      "url": "https://bibigpt.co/api/mcp",
      "protocol": "mcp",
      "description": "Hosted MCP endpoint with OAuth2 + Bearer token auth"
    },
    {
      "transport": "https",
      "url": "https://bibigpt.co/api/openapi.json",
      "protocol": "openapi",
      "description": "tRPC-derived OpenAPI 3 spec for direct REST integration"
    },
    {
      "transport": "https",
      "url": "https://bibigpt.co/api/ask",
      "protocol": "nlweb",
      "description": "Natural-language Q&A endpoint (NLWeb spec) with optional SSE streaming"
    }
  ],
  "additionalInterfaces": [
    {
      "transport": "streamable-http",
      "url": "https://bibigpt.co/api/mcp",
      "protocol": "mcp",
      "description": "Hosted MCP endpoint with OAuth2 + Bearer token auth"
    },
    {
      "transport": "https",
      "url": "https://bibigpt.co/api/openapi.json",
      "protocol": "openapi",
      "description": "tRPC-derived OpenAPI 3 spec for direct REST integration"
    },
    {
      "transport": "https",
      "url": "https://bibigpt.co/api/ask",
      "protocol": "nlweb",
      "description": "Natural-language Q&A endpoint (NLWeb spec) with optional SSE streaming"
    }
  ],
  "provider": {
    "name": "JimmyLv (\u5415\u7acb\u9752)",
    "url": "https://bibigpt.co",
    "contact": {
      "email": "support@bibigpt.co",
      "twitter": "https://x.com/Jimmy_JingLv",
      "github": "https://github.com/JimmyLv"
    }
  },
  "capabilities": {
    "streaming": true,
    "pushNotifications": false,
    "stateTransitionHistory": true
  },
  "defaultInputModes": [
    "text",
    "url"
  ],
  "defaultOutputModes": [
    "text",
    "markdown",
    "json"
  ],
  "securitySchemes": {
    "oauth2": {
      "type": "oauth2",
      "flows": {
        "authorizationCode": {
          "authorizationUrl": "https://bibigpt.co/api/auth/authorize",
          "tokenUrl": "https://bibigpt.co/api/auth/token",
          "scopes": {
            "read": "Read user library, summaries, and content"
          }
        }
      }
    },
    "bearerToken": {
      "type": "http",
      "scheme": "bearer",
      "description": "Long-lived API token from https://bibigpt.co/dashboard/api"
    }
  },
  "security": [
    {
      "oauth2": [
        "read"
      ]
    },
    {
      "bearerToken": []
    }
  ],
  "skills": [
    {
      "id": "summarize_video",
      "name": "Summarize Video / Audio",
      "description": "Generate a structured summary with timestamps, key points and chapters from any supported video or audio URL.",
      "inputModes": [
        "url"
      ],
      "outputModes": [
        "markdown",
        "json"
      ],
      "tags": [
        "summarization",
        "video",
        "audio",
        "podcast"
      ],
      "examples": [
        {
          "input": "https://www.bilibili.com/video/BV1xx411c7mD",
          "output": "Markdown summary with timestamps"
        },
        {
          "input": "https://youtu.be/dQw4w9WgXcQ",
          "output": "Bullet-point key takeaways"
        }
      ]
    },
    {
      "id": "summarize_video_with_config",
      "name": "Summarize with Custom Config",
      "description": "Same as summarize_video but lets the agent specify prompt template, output language, model, length and persona.",
      "inputModes": [
        "url",
        "text"
      ],
      "outputModes": [
        "markdown",
        "json"
      ]
    },
    {
      "id": "summarize_by_chapter",
      "name": "Summarize by Chapter",
      "description": "Long-video chapter-by-chapter breakdown with timestamps and per-chapter summary blocks.",
      "inputModes": [
        "url"
      ],
      "outputModes": [
        "markdown",
        "json"
      ]
    },
    {
      "id": "get_subtitle",
      "name": "Get Full Transcript / Subtitles",
      "description": "Return full transcript with timestamps for any supported source. Auto-detects existing captions or transcribes via ASR.",
      "inputModes": [
        "url"
      ],
      "outputModes": [
        "text",
        "json"
      ]
    },
    {
      "id": "create_summary_task",
      "name": "Create Async Summary Task",
      "description": "For very long videos (>30 min), kick off an async job and return a task id. Pair with get_task_status.",
      "inputModes": [
        "url"
      ],
      "outputModes": [
        "json"
      ]
    },
    {
      "id": "get_task_status",
      "name": "Get Async Task Status",
      "description": "Poll status / retrieve result for an async summary task created via create_summary_task.",
      "inputModes": [
        "text"
      ],
      "outputModes": [
        "json"
      ]
    }
  ],
  "supportsAuthenticatedExtendedCard": true,
  "tags": [
    "video-summarization",
    "audio-transcription",
    "podcast",
    "knowledge-graph",
    "agent-native",
    "mcp",
    "oauth2"
  ]
}