Browse the index

Post-tx outcome verification via LLM-as-judge. Zero Core Verify.

Model-tiered content pipeline — cheap models seed, expensive models verify

Agent-payable web data over x402: 18 keyless services an agent pays per call.

Claude reads and writes a real-life RPG character sheet from the eighty self-improvement app.

Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.

MCP relay server for Claude Desktop <-> Claude Code communication

Zendesk MCP server for Claude Code and other MCP clients

AI bookkeeping agent for Japanese accountants — auto-classifies freee/Yayoi/MF/TKC transactions.

Catches when your project drifts from its own decisions. Local-first cross-agent memory MCP.

Run verified read-only code tools: quant diagnostics + agent-ops preflight, no source exposure.

Scan APIs for OWASP Top 10, LLM, and GraphQL security vulnerabilities.

Convert docs to agent-readable specs with criteria and constraints. $0.10/convert.

An MCP server that fuses LLM contextual intelligence with procedural code reliability.

Financial data for AI agents: SEC filings, price history, insider trades, and more.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

Single entry point for the GOSCE portfolio: routes orchestrators to verified agents by capability, w

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t