Agent & Infrastructure

Start a deep research job on any longevity or aging topic. Aubrai orchestrates sub-agents for literature synthesis, data analysis, and hypothesis generation — returns a conversation ID to poll for the full report.

Property bill and ordinance analysis for agents. Accepts address, ZIP, city, or county, then resolves governing jurisdictions for bills, agendas, ordinances, zoning, tax, fee, bond, housing, and permit-change artifacts. Never legal advice, political advice, or forecasts. Install agent skill: npx @velinussage/locus-agent-skill add.

Returns a list of GitHub repositories, likely filtered or analyzed based on specified criteria.

Generate an advanced AI-powered similarity key for US street address matching with enhanced algorithm accuracy. Uses deeper AI models for more precise matching of complex address variations including unit numbers, directionals, and abbreviations.

Independent multi-agent security audit (OWASP ASI01-ASI10 coverage) of a counterparty agent or MCP server before you grant it tool access or spend authority. Findings are Merkle-committed and the audit report is signed.

5-11 agent panel debate playing CFO + CIO + CISO + Procurement Lead. Forced vote on any vendor decision. Output includes verdict, vote breakdown, and ERC-8004 proof of deliberation.

5-11 agent panel debate with 11 LLM models, structured voting, forced decision-making

Invoice field verification for AI agents: arithmetic consistency of invoice fields, line-item totals, and accounting JSON. 0.001/call.

Cheapest endpoint: liveness plus x402 payment pipeline check — Returns ok with the server time and whether this call was paid. Use it to verify your x402 client end to end before spending on data endpoints.

Paid liveness probe for the MimirAPI counter. Returns pong, the SKU id, and a server timestamp. One tenth of a cent buys a complete challenge, sign, settle, serve round trip — the cheapest possible proof that your x402 client wiring works before you spend real money on real SKUs.

OPENAI-COMPATIBLE chat completions, PRO tier — frontier models at one flat price, no API key, no account: gpt-5.2 (default), gpt-5.5, claude-sonnet-5, gemini-3.1-pro, gemini-3.5-flash. Same dialect as OpenAI — base_url https://api.webbersites.com/v1/pro works with any OpenAI SDK. Caps: 24,000 input chars, 1,024 output tokens, text-only, no streaming. The x402 payment IS the auth.

Generate a realistic mock API response with proper headers, status codes, and schema-matching body data.

Classify your AI system's risk level under the EU AI Act before the August 2026 deadline. Risk classification, obligations, and supervisory authority.

Look up known vulnerabilities for a package+version via OSV API. Supports npm, PyPI, Maven, Go, Cargo, NuGet. Returns CVEs with severity and fix versions.

Test an API endpoint: send request, validate response status and schema. Integration testing as a service.

Verify any paid API endpoint before your agent spends money. Checks reachability, SSL, response time, and validates the payment protocol handshake (L402, x402, MPP). Returns a proceed/caution/avoid recommendation with parsed payment details. Use this befo…

Should your agent execute this transaction? Single-call go/no-go middleware for DeFi agents. Checks wallet risk, token safety, approval security, current gas costs, and sanctions status. Returns a risk verdict.

Analyze AI agent execution traces (LangChain/CrewAI/AutoGen). Identifies failure points, root causes, token waste, and suggests fixes.

Everything your sales agent needs from one email address — validation, domain intel, reputation, registrar, and tech stack detection.

End-to-end invoice verification: extract structured data from the invoice, validate the vendor's VAT number, verify the payment IBAN, and convert currency if needed. Returns everything an AP automation agent needs.

[3-LEG] AI tool and MCP chain, one tool (?entity=mammoth-ai): leading decay warnings, release cadence stalling and docs going dark -> current live or dead status from real DNS and GitHub checks -> realized lifecycle from launch to death with days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: DNS, GitHub, package registries. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

[3-LEG] AI dependency chain, one dependency (?entity=openai-text-davinci-003): leading deprecation notices INCLUDING the sunset date the publisher itself scheduled -> current current availability -> realized lifecycle to deprecation, days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: vendor notices, source URL per record. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

[3-LEG] Regulatory filing chain, one issuer (?entity=AMC): leading NT late-filing notices, a distress leading indicator -> current 8-K material events graded by item severity -> realized Form 4 insider transactions (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: SEC EDGAR. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

Generates or retrieves universally unique identifiers.