Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.

A compiler, optimizer and executor for financial expressions and factors

A cross-host prompt library and agent skill for managing long-horizon multi-task workflows in coding agents like Claude Code, Cursor, Codex, and Grok Build.

A Codex Skill for coordinating four specialized subagents to handle development, research, analysis, and review tasks.

Automated MT5 Trading Bot with AI Alerts & Webhook Bridge 2026

A Python framework for managing positions and trades in DeFi

Claude Code skills: codex-sprint, review-loop (iterative simplify-review-fix), rust-dev (FAIL FAST standards)

A skill collection that separates planning from execution via verifiable goals and fresh-session handoffs for AI coding agents.

A Claude Code skill that structures long coding tasks as a graph with executor and supervisor nodes to prevent drift.

Curated library of battle-tested prompts for long-horizon agent tasks adapted to multiple AI agent hosts like Claude Code, Cursor, and Codex.

Design, implement, and review Kotlin and Android APIs. Use when working on .kt files, Kotlin nullability, sealed classes/interfaces, coroutines, Android threading, Java interop, or Kotlin-backed React Native Nitro Module implementations.