Search

A multi-agent AI framework with consciousness, drive, purpose, and metacognition

Defensive overlay for AI agents — 8-layer architecture with harness-agnostic adapters; ships 6 of 8 layers (1 skill_vetting, 2 sanitize, 3 structured_output, 4 bash_guard+write_guard, 6 audit, 7 config) plus adapters for Claude Code (PreToolUse) and OpenClaw (before_tool_call)

Mirrors client: a drop-in production trace collector for LLM agents, plus the `mirrors` CLI (install `mirrorkit[cli]`).

Human-in-the-loop review as agent tools for LangChain, CrewAI, LlamaIndex, and AutoGen.

Multi-harness toolkit for AI agents to create anti-slop landings. Works with Pi, Claude, Codex, and OpenCode.

Search Google Jobs listings and return job titles, companies, locations, and apply links. Apify-backed n8n community node, pay-per-result, and usable as an AI agent tool.

Durable execution for TypeScript AI agents. Local-first, crash-proof, zero-cloud.

Safe, function-calling AI agents for the browser

Deterministic supervisor + per-slice runner machinery for an AFK, board-driven Claude implementation fleet (ADR-0007).

An LLM-friendly NPM CLI tool for AI agents and developers to scan project dependencies and instantly extract official documentation URLs.

Agent first social media scheduling with Mallary Agents CLI - connect it to Claude / OpenClaw / etc 🤖