Executor

Executor is an initiative-scoped workflow system that guides coding agents through structured development phases.

Executor is an initiative-scoped workflow system designed for coding agents. It takes a major idea through intake, discovery, architecture, design, specification, planning, plan regression, execution, review, and verification. The engine uses a strict per-initiative ID namespace, separated thinking and execution stores, and schema-enforced contracts at every state transition. It works with any agent that can read skill files from a directory, including Claude Code, Codex, omp, Cursor, Copilot, Gemini CLI, OpenCode, Amp, and Goose. The engine is written in Python 3.11+, is dependency-free using only the standard library, and runs on macOS, Linux, and Windows.

Executor at a glance

Best for: Software engineer
Runs on: macOS, Linux, Windows
Pricing: Free
Released: September 2026
Category: AI coding tool
Website: github.com/atri10/executor

Key features

Initiative-scoped workflow system for coding agents
Schema-enforced contracts at every state transition
Separated thinking and execution stores
Strict per-initiative ID namespace
Hash-chained append-only journal of events
Python 3.11+ dependency-free standard library engine

Use it for

Manage structured coding workflows with AI agents
Enforce verification and review gates on agent tasks
Track initiative changes with computed blast radius

Alternatives to Executor

Anti Slop — Filters out generic AI-generated UI designs, text, and code.
pstack — Improves AI coding agent outcomes with rigorous workflows.
AI Slop Detector — Avoid AI writing patterns in drafts or train an AI assistant.
SlopGuesser.dev — Test your ability to distinguish between human-written and AI-generated code snippets daily.
Cursor — Autocomplete, inline edits and parallel agents in one editor
Loop Engineering — Design agent loops to discover work and verify results automatically.
ReplySlip — Sends tasks between AI agents and validates answers against a JSON Schema.
Agent Skills — Encodes senior-engineer workflows and quality gates into 24 skills.
Stop That Shit — Enforces task boundaries to stop unnecessary AI agent actions.
slopsidy — Compare AI models and coding agents by capability, speed, and cost.
Agentic CleanSlop — Runs entirely inside AI agents with one pasted line.
SlopIt — Your AI agent creates and manages your blog autonomously via API.

All Executor alternatives