Let LLMs control embedded devices via the Model Context Protocol.

Mantis Hack

My personal directory of skills.

Public results and task definitions for FrontierHarness Eval

An MCP server that lets LLM agents play Civilization VI.

Deterministic safety solutions for probabilistic AI agents

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Turn Pi into el Gentleman: a senior-architect development harness with SDD/OpenSpec, subagents, strict TDD evidence, review guardrails, and skill discovery.

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-tiered permissions, event-sourced replayable sessions, and a fail-closed OS-level sandbox.

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.