Rolecraft

Rolecraft is an open-source CLI agent harness and orchestrator maintained by Samet Celikbicak and the rolecraft-sh organization. Designed to coordinate and structure AI coding agents, it provides a command-line foundation for managing agent personas, modular skill sets, and execution boundaries. In day-to-day use, Rolecraft operates as a terminal-based orchestration harness. Developers execute tasks by invoking agent runtimes—such as Oh-My-Pi (omp) or OpenCode agents—while attaching specific functional skills using command-line flags. The tool controls agent workspace directories, enforces skill separation, and captures run execution logs. Rolecraft distinguishes itself through its modular skill-injection model, integrated benchmarking suites, and automated security reporting. Rather than serving as a monolithic coding chatbot, it acts as a configurable orchestration layer that standardizes skill attribution and audits agent actions across varied agent backends. Rolecraft is open-source software distributed via GitHub. The repository includes automated testing, CodeQL security scanning, and pre-commit linting to maintain harness reliability.

Tags: agent harness, ai agent, cli, developer tools, OpenSource

Visit Rolecraft

Key features

• Skill-based orchestration — Assign granular, task-specific capabilities using multiple --skill flags at runtime. - Multi-agent runtime support — Coordinate different agent backends, including Oh-My-Pi (omp) and OpenCode agents. - Security auditing and reports — Automatically include active skill metadata within generated execution security reports. - Built-in benchmarking harness — Evaluate and compare agent performance and execution efficiency across standardized benchmarks. - Isolated agent workspaces — Maintain clean runtime environments by managing recorded agent execution directories. - CLI-first architecture — Execute and script agent workflows directly from terminal environments and CI pipelines.

Use cases

Use Case: Modular Agent Skill Assignment Developers can pass discrete --skill parameters to configure an agent specifically for refactoring, testing, or API design without polluting the context window with unnecessary instructions. This isolates operational roles to only the tools needed for the task.

Use Case: Comparative Agent Benchmarking Teams evaluating different coding agent engines can use the built-in benchmark utilities to run tasks across supported agents like Oh-My-Pi, measuring accuracy and output consistency.

Use Case: Audited Code Generation Engineers operating in sensitive repositories can run tasks under Rolecraft to generate explicit security reports tied to each assigned skill, tracking how the harness executes file changes.

Who it is for

Rolecraft is designed for AI engineers, DevOps teams, and developers building structured multi-agent workflows who need command-line skill management and benchmarking. It is not intended for non-technical users or developers looking for a graphical IDE chat plugin.

Install guide

Installation Clone the repository and install dependencies locally (Node.js/npm standard setup): bash git clone https://github.com/rolecraft-sh/rolecraft.git cd rolecraft npm install npm link

First Run Verify that the CLI is accessible and inspect the available flags and agent configurations: bash rolecraft --help

Example Session Execute a coding task using the Oh-My-Pi backend while attaching specific skills: bash rolecraft run --agent omp --skill refactoring --skill testing "Refactor error handling in src/api/client.ts"

Part of CLI Coding Agents

Categories: AI Coding Agents, Developer Tools

Related CLI agents

• SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
• Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
• Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
• Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
• Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
• Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…