TikTok videos that outperform, for your agent or your app
Open-source AI agent orchestration platform for incident response and automation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Open source
Pricing
Pay as you go: $0.005 per call ($5 for 1,000 calls), $1.00 free credit when you sign up. Top up with $5, $10, $25, $50 (+10% credit) or $100 (+10% credit). Pro plan: $69/month with 1,000 searches per day included. Agency plan: $299/month with 5,000 searches per day included. All paid plans include a
Not given
Key features
Search TikTok videos by keyword, creator, or hashtag
Measure videos against creator's usual performance (vsUsual metric)
View history showing performance over time
Shares per 1,000 views metric
Sort by trending, outlier, views, recent, engagement or shares
Track your own accounts with followers and video analytics
Daily video ideas and AI video checks
MCP integration with Claude and Cursor
REST API and command-line interface
Rate limit of 60 calls per minute, up to 50 videos per call
Incident response with agent investigation and pull request generation
Automated workflows triggered on schedules or webhooks
Agent summoning from GitHub, GitLab and Radicle with /ryph command
Semantic memory system for shared and persistent agent learning
Credentials kept behind gateways with no access in sandbox
Customized environments per repository with cached dependencies
Browser use for agent interactions with live watching
Artifacts and pages for reports and overviews
Deployment options from laptop to Kubernetes
Tool proxy with allowlisted MCP server integrations
What makes it different
Data refreshed daily with view history tracking, not a live scraper
Measures performance relative to creator's baseline, not absolute views
Three public MCP tools work without an API key as preview
Includes trending hashtags and sounds in search results
Agents work without holding real credentials or keys
Changes ship as patches that require review before merge
Runs on your own infrastructure from laptop to cloud
Semantic memory learns across runs with deduplication and contradiction handling
Built-in safety assuming agents can be manipulated or exploited
Viewlify
Ryph