AI & research · One purpose, multiple implementations
Airtop Web Agent
Adapt the published “Airtop Web Agent” workflow to other implementations while preserving its documented behavior.
The source contains 17 executable nodes and 15 connections. This draft is derived from the n8n export; it needs a human-reviewed purpose, input/output contract, and behavioral tests before a port can claim equivalence.
Open agent files on GitHub ↗Shared workflow
This initial Mermaid diagram shows observed connections from the n8n source, including model and tool dependencies. Unresolved connections are listed under Evidence. It is a starting point for the shared design; it does not execute the agent or establish correctness.
Rendering the workflow diagram…
Read the Mermaid source
flowchart LR n0["AI Agent"] n1["Click"] n2["Query"] n3["Load URL"] n4["End session"] n5["Type"] n6["Start browser"] n7["Claude 3.5 Haiku"] n8["On form submission"] n9["Slack"] n10["Structured Output Parser"] n11["Output"] n12["Session"] n13["Window"] n14["Return IDs"] n15["When Executed by Another Workflow"] n16["Slack1"] n5 -->|"ai_tool out 0 to in 0"| n0 n1 -->|"ai_tool out 0 to in 0"| n0 n2 -->|"ai_tool out 0 to in 0"| n0 n9 -->|"main out 0 to in 0"| n14 n11 -->|"main out 0 to in 0"| n16 n13 -->|"main out 0 to in 0"| n9 n12 -->|"main out 0 to in 0"| n13 n0 -->|"main out 0 to in 0"| n11 n3 -->|"ai_tool out 0 to in 0"| n0 n4 -->|"ai_tool out 0 to in 0"| n0 n6 -->|"ai_tool out 0 to in 0"| n0 n7 -->|"ai_languageModel out 0 to in 0"| n0 n8 -->|"main out 0 to in 0"| n0 n10 -->|"ai_outputParser out 0 to in 0"| n0 n15 -->|"main out 0 to in 0"| n12
Implementations
Each implementation shares the agent’s purpose. Available source, planned ports, and verified results are labeled separately.
n8n
Source available · not runtime-tested
Read setup and source ↗Inspect the n8n canvas and download JSON →Build or operate with an assistant
Each prompt includes separate build and operating instructions tailored to this agent. They are untested instructions, not working implementations. Check the chosen product’s actual capabilities before using it.
Evidence and remaining work
The bulk collection has publication checks, not live-service testing. Diagrams and prompts are documentation. A port needs reviewed schemas, fixtures, actual execution results, and explicit limits before claiming equivalent behavior.
- Define input/output schemas and expected outputs.
- Review source expressions, external actions, and failure behavior.
- Determine whether model judgment is required or deterministic rules suffice.
Curated by Nik Bear Brown. Preserve each implementation’s original attribution and license. These source templates are separate from the audited Claude directory.