Turn tracker tickets into autonomous agent sessions

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

DeFi toolkit for AI agents and coding assistants — deposit funds, execute trades, and manage crypto wallets. Works with Claude Code, Cursor, Windsurf, OpenClaw, CrewAI, AutoGPT, and other AI agent frameworks.

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.