Agents

Wudao MCP

68 read-only China A-share MCP tools for AI Agents: K-line, limit-up ladder, capital flow, Dragon Tiger List and post-market review.

Hitl Protocol

Human-in-the-Loop Protocol for Autonomous Agent Services — Open Standard (v0.8)

Open Visualization Protocol

OVP: the open visualization protocol for describing, validating, and rendering information design identically, for humans, software, and AI...

Mozart Router

Local orchestration and routing for AI agents — gateway-first, agent-first, integration-first

Ensemble

Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.

K8S MCP Go

Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.

Clicks Protocol

Autonomous yield for AI agents on Base. 80% liquid, 20% earning. No lockup. One SDK call.

Guard

Runtime guardrails for TypeScript AI agents. Prevents duplicate tool calls, enforces per-user cost budgets, and gates irreversible actions....

Cortex

Persistent shared memory and context compression for AI coding agents. Local-first Rust daemon with HTTP, MCP, and a desktop control center.

Seshat

The operating manual for your codebase — written for AI agents. Shift-left intelligence layer that gives AI coding agents deep understanding...

Controlkeel

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

Vatt Ghern

Daily tech-news zine for engineers — Claude-authored prose, bespoke HTML, CJK typography. Deployed on Cloudflare Pages.