cuga-project/cuga-agent

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

About the project

CUGA is an enterprise agent harness that turns business requests into actions across applications, APIs, and documents while connecting to tools through MCP, OpenAPI, and Python integrations. Organizations use it to run general-purpose agents in controlled environments, apply approval and execution policies, and configure models and workflows for private or disconnected deployments. The catalogue entries supply instructions and skills for working with the CUGA harness.

Latest release v0.4.4 · 1 Nov 2026

2 files for Codex, OpenCode and Claude Code: cuga-agent AGENTS.md, cuga-agent CLAUDE.md — 2,158 tokens loaded in every session.

1,107Stars on the repository
2Files it configures its agents with
2,158Tokens loaded in every session
3Agents configured

Instructions

These files are cuga-project/cuga-agent's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.