| What it does | TikTok videos that outperform, for your agent or your app
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| 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
| Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
|
|---|
| 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
| - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
|
|---|
| 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
| - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 0 |
|---|
| Citation Flow (Majestic) | 13 | 9 |
|---|
| Referring domains (Majestic) | 5 | 4 |
|---|
Viewlify
Argentic