GreatCTO

GreatCTO is an open-source AI agent orchestration harness and engineering pipeline framework created by Anatoly Velikiy (avelikiy). It coordinates multi-role software delivery workflows by automating handoffs between distinct engineering personas, including Product Managers, Architects, Senior Developers, QA Engineers, Security Officers, Performance Engineers, DevOps, and L3 Support. In daily use, GreatCTO manages structured tasks across different pipeline phases. Tasks are tracked via the Beads lifecycle protocol or local task manifests (.great_cto/tasks.md). The harness interacts with LLMs through integrations such as Claude plugins (.claude-plugin) and standardized skill protocols, guiding autonomous execution through phase boundaries and formal task decomposition. GreatCTO distinguishes itself by enforcing strict verification and artifact governance rather than trusting self-reported agent success. It integrates structural linting (artifact-lint), local CI execution (ci-local), and workflow parity validators (guard-parity.mjs) to ensure that agent-generated deliverables, tests, and security assertions are systematically validated before pipeline progression. The project is open-source under public GitHub distribution, designed for local-first execution with built-in dashboard metrics and task cost-tracking utilities.

Tags: AI, ai agent, cli, developer tools, OpenSource, productivity

Visit GreatCTO

Key features

  • Multi-Role Agent Pipeline — Coordinates specialized personas including PM, Architect, Senior Developer, QA, Security, Performance, DevOps, and Support across development lifecycles. - Phase Task Protocol — Enforces structured task decomposition, state tracking, and closure criteria across Beads and local markdown task registries. - Artifact Linting & Verification — Validates agent-generated outputs against structural schema and quality checks with artifact-lint. - Guard Parity & Local CI — Audits workflow commands and runs verification locally via ci-local to avoid silent CI configuration failures. - Claude Plugin Compatibility — Provides first-class integration manifests (.claude-plugin) and skill definitions for agent tool execution. - Cost & Task Metrics Dashboard — Includes lightweight local server packages to track stage progression and token cost history across development tasks.

Use cases

Use Case: End-to-End Feature Development Pipeline Developers use GreatCTO to orchestrate multi-agent handoffs from initial requirements and architecture design down to code implementation and automated test coverage across staged phase tasks.

Use Case: Automated Security & Architecture Governance Teams run GreatCTO to enforce pre-merge gates using dedicated security officer and performance engineer agent roles, ensuring pull requests satisfy linting and policy constraints.

Use Case: Local CI and Guard Verification Engineers run GreatCTO's local verification tooling to test and validate workflows locally, confirming all gate scripts and linting steps pass before pushing upstream.

Who it is for

GreatCTO is designed for engineering leads, autonomous agent developers, and teams building structured, multi-agent software engineering pipelines with strict verification gates. It is less suited for developers seeking a lightweight, single-file interactive chat agent or simple code autocomplete tool.

Install guide

Installation Clone the repository and install dependencies using Node.js: bash git clone https://github.com/avelikiy/great_cto.git cd great_cto npm install

First Run Ensure your agent environment (such as Claude plugin configuration or LLM API keys) is set up, and initialize the task registry: bash # Check workflow and guard parity node guard-parity.mjs # Run local CI and artifact verification ./ci-local

Example Session Execute a phase task lifecycle command using the phase helper: bash # Open and track a pipeline phase task for an architecture pass ./scripts/phase-task.sh start architect "Design authentication subsystem" # Validate generated artifacts npm run artifact-lint -- --enforce # Close the phase task upon completion ./scripts/phase-task.sh close architect "Design authentication subsystem"

Part of CLI Coding Agents

Categories: AI Coding Agents, Assistant, Developer Tools, Productivity

Related CLI agents

  • PicoClaw — PicoClaw is an open-source command-line coding agent developed by Sipeed and community contributors. Written in Go, it is engineered for…
  • Agent Island — Agent Island is an open-source agent orchestration harness created by developer tristan666666 on GitHub. Designed as a framework for running…
  • Playwright Praman — Playwright Praman is an open-source test harness and agent orchestrator developed by Maheshwar Kanitkar. It is designed to bridge terminal…
  • Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
  • Skillreaper — Skillreaper is an open-source skill lifecycle management and auditing tool for AI agent ecosystems, developed by thousandflowers. It analyzes agent…
  • Zosma QA — Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories