Browse the index

Human intelligence API — AI agents verify facts with human domain experts via MCP

LLMs can't draw. This MCP can. 81 arts + 100 kaomoji + diagrams + charts.

MCP server for fixing static analysis issues from SARIF reports with AI agents

Equilibrium-aware primitives for AI agents — negotiation, auctions, mechanism design.

Math-optimal negotiation moves for AI agents, in plain dollars (single + multi-issue).

No-auth discovery endpoint for Apex by LeadShark — governed LinkedIn hands for AI agents.

x402station.io: independent risk-signal layer for x402 endpoints before agents pay.

Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.

Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.

Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

12 tools that let AI agents check trust scores and reviews before recommending any software tool.

Protect your AI agents and IDEs from malicious open-source packages.

Scores your prompts against your real codebase — context-aware prompt intelligence

Local-first memory for AI agents that reaches backward to find a failure's root cause.

Negotiate prices at any negotiate.v1 store. AI shopper tools for Claude.

Inspect, operate, and author Microsoft Power Automate cloud flows from an agent context.

Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.

Read-only MCP access to presence: living project model and outcome telemetry.