Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.

SOUL.md governance framework for Hermes Agent — structured memory, skill management, and operational rules

Free OpenAI-compatible LLM endpoint. Zero API keys, zero signup, zero user compute. Aggregates keyless public endpoints (Pollinations, ApiAirforce) with auto-failover, client-side queueing, and ad/notice filtering.

Instant web hosting for AI agents. One curl, one CLI, *.wooven.dev URL in <1s.

A decision engine for Claude Code. MIT licensed.

Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes

Public Plugin Marketplace

Package manager and registry for Claude skill packages - install, validate, score, and publish .skill packages with Claude Code integration via MCP

Schema-validated JSON blocks for AI-generated reports — Markdown source, safe runtime, zero AI-generated HTML/CSS/JS. Works with Claude Code, Codex, any agent.

Graph-driven reasoning over verified evidence. A formal workflow protocol for AI coding agents: deterministic Definition of Ready, falsifiable assumption gates, atomic done-transitions, and a single auditable lock file as source of truth.

Route OpenAI API requests through a free, keyless endpoint with multi-provider failover and edge compatibility for existing AI tools.

Task-class-aware multiplexer for local LLM configurations on Apple Silicon. Profiles, swap, lab.

Playwright-native CLI for inspecting live React apps without opening the DevTools UI.

Node.js TypeScript CLI for discovering, staging, activating, and wiring reusable AI-agent assets across VS Code/Copilot, OpenCode, Cursor, Zed, Claude Code, and Pi.

A Codex skill that reports which skills influenced each reply and gives evidence-based suggestions on which skills to keep, observe, use on demand, or disable.

A local-first multi-repo workspace system with shared runtime control, memory, docs, and agent tooling.

A Claude Code plugin that gives Claude a self-introspection tool for its own subscription quota — so it can warn you before a long task runs out of budget.

Structural code recon cli tool built for agents