Midscene.js
Framework (OSS)LIVEby ByteDance
ByteDance's open-source UI automation framework with natural-language APIs covering web and Android. Pairs with UI-TARS or any vision-language model, and caches execution plans for repeatable low-cost re-runs. Ships a strong visual report UI for debugging runs.
- Provider
- ByteDance
- Type
- Framework (OSS)
- Added
- Dec 2024
- Interface
- Task + session
- Trust tier
- restricted
- Egress
- Banana Peel egress guard
- Evidence
- partial
- Max session
- 90 min
- Regions
- US
- Pricing
- license free (MIT)compute + LLM operator-paid
- Compliance
- ZDRSOC 2HIPAAPCI-DSS ROC
0.3%
Traffic share
18.6%
Success
6s
Median duration
Free · OSS
List price
—
p95 first action
Success rate over time
Traffic share over time
Pricing
| Model | Native price | Normalized $/run | Notes |
|---|---|---|---|
| oss | Free (self-hosted) | $0.00 | — |
| license | free (MIT) | — | — |
| compute + LLM | operator-paid | — | — |
Capability matrix
Capabilities for this runner — extra/gap badges compare against the most common capability set for Framework (OSS) runners in the catalog.
Login flowsextra
MFA/2FA interactions
CAPTCHA handling
File download
File upload
Form filling
Structured extraction
Vision-based
DOM-based
Stealth/anti-bot
Residential proxies
Persistent sessions
Parallel sessions
Human-in-the-loop
Full evidence
Storage capture
Code sample
Pin this runner via routing: "midscene"
curl -X POST "$BANANA_PEEL_BASE/api/v1/responses" \
-H "Authorization: Bearer $BANANA_PEEL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "banana-peel",
"input": "Extract the title from https://example.com",
"routing": "midscene"
}'