The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
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,…
Install
npx skills add https://github.com/anthropics/skills --skill pptx -a universalclaude mcp add cuga-agent -- npx skills add https://github.com/anthropics/skills --skill pptx -a universal{
"mcpServers": {
"cuga-agent": {
"command": "npx",
"args": [
"skills",
"add",
"https://github.com/anthropics/skills",
"--skill",
"pptx",
"-a",
"universal"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →CUGA: Configurable Generalist Agent — Agent Harness for the Enterprise
Start with a generalist. Customize for your domain. Deploy faster!
Building a domain-specific enterprise agent from scratch is complex and requires significant effort: agent and tool orchestration, planning logic, safety and alignment policies, evaluation for performance/cost tradeoffs and ongoing improvements. CUGA is a state-of-the-art generalist agent designed with enterprise needs in mind, so you can focus on configuring your domain tools, policies and workflow.
Why CUGA? — A generalist agent harness for the enterprise: wire your APIs and MCP servers, tune reasoning and task modes, and govern behavior with policies—without rebuilding orchestration from scratch.
Feature How MCP, OpenAPI & LangChain tools mcp_servers.yaml·CugaAgent(tools=[...])Code generation profiles (fast / balanced / accurate) [features] cuga_modeinsettings.toml·configurations/modes/Hybrid API + browser tasks [advanced_features] mode = 'hybrid'· Playwright + browser extensionMulti-agent (CugaSupervisor) cuga start demo_supervisor·[supervisor]insettings.tomlEvent-driven agents (channels · triggers · standing flows) cuga start demo+python -m cuga.backend.events.service— web chat, Slack/Discord/Telegram, webhooks, cron/poll/push flows armed from natural language with a human confirming each one, one supervisor agent over a YAML roster. Runs as a second service beside CUGA (:7860 + :8100); CUGA is unchanged when it is not deployed. Setup and the per-connector guides live in the events documentation repository.A2A & remote agents External agent entries in supervisor config · CugaSupervisor Policies & HITL Policies SDK — Intent Guard, Playbook, Tool Approval, Tool Guide, Output Formatter Manage & publish cuga start manager· draft tools, MCP, LLM, and policies in the web UI, then publish a versioned config for production chat (details)Reflection [advanced_features] reflection_enabledinsettings.tomlTool-call budgets [advanced_features] max_tool_calls_per_block / _per_run / _per_threadinsettings.tomlLangflow Low-code visual workflows — integrates with CUGA (langflow.org) Knowledge (RAG) enable_knowledge=True(default) · ingest PDFs/Office/HTML/Markdown via Docling · agent-level + session-level scopes ·cuga start demo_knowledge· detailsAgent skills SKILL.mdunder.cuga/skills(default) ·cuga start demo_skills(sandbox_mode = "native"by default, oropensandbox) · ordemo --sandboxwith[skills]on · Agent skillsSelf-host on a cluster Helm chart and deploy scripts in deployment/· Kubernetes guide (local kind/minikube, or registry push for cloud clusters)
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io