Generate human-readable ids from lists of easy-to-spell nouns and adjectives

Private-repository MCP connector for bounded Stewie Agent Farm delegation

Let AI agents query and update Postgres/MySQL safely without giving the model raw SQL, unrestricted schema access, or database credentials.

Interactive AI coding assistant CLI powered by Nuvin core

React email surfaces for AppKit chat and admin workflows.

Human-in-the-loop approval middleware for OpenClaw. Intercepts tool execution via before_tool_call and routes destructive calls through the built-in approval flow (TUI / Control UI / chat).

Pi extension for resource-aware security policy engine and tool authorization

Open-source AI agent governance for TypeScript: policy, exact one-use approvals, controlled tool execution, and verifiable receipts.

SignedApproval n8n node — cryptographic human approval with Ed25519 proof

Format numbers for human consumption.

Converts a number to/from a human readable string: `1337` ↔ `1.34kB`

Official n8n community node for Tracira AI output monitoring and approval workflows.

RIVO local MCP — holds the agent's own (non-custodial) wallet, signs each payment, and relays it to the hosted RIVO app for policy + human approval + audit before broadcast. RIVO never holds the key or custodies funds. Zero code: add it to your harness an

Otorga - a consent layer for credentials. A local-first, self-hostable secrets broker that gates every secret access behind hardware-backed human approval, with full process-tree visibility and a tamper-evident audit trail. Under construction.

Multi-agent workflows with full observability and time travel: watch every step live, rewind, fork, and replay any run. Claude Code, Codex, Gemini, any model or harness.

Parse a human name string into salutation, first name, middle name, last name, suffix. Parse an address into address, city, state, zip

Scaffold a new Cloudflare Think agent — npm create think

MCP server for governed AI workflows — invoice OCR, AML triage, credit review, and custom contracts with human approval gates and audit trails

Action ledger schema, append-only write helpers, and idempotency primitives for Voyant control surfaces.

Human readable time measurements