Noodle Skills
Open-source, Go-built skill-based agent orchestration framework with scheduling, optional memory, and adjustable autonomy modes.
At a Glance
Noodle core is released under the MIT License (OSI-approved) and is free to use, copy, modify and distribute.
Engagement
Available On
Listed Nov 2026
About Noodle Skills
Noodle is an open-source agent orchestration tool by Lauren Tan (poteto), written in Go and released under the MIT License. It lets users orchestrate AI agents using composable skills, with scheduling handled by the system. The latest release listed is v0.1.5, published 2026-03-03.
What It Is
Noodle is a skill-based agent orchestration framework. Instead of hard-coding orchestration logic, users define reusable skills and Noodle runs them. The project site describes four core primitives: Skills, Scheduling, Brain, and Modes.
Core Primitives
- Skills: composable, reusable units that let users shape agent orchestration as they want.
- Scheduling: agent-powered task scheduling that routes work to the right model at the right time, with full observability.
- Brain: optional persistent memory across sessions; the site suggests adding brainmaxxing for self-learning agents.
- Modes: auto, supervised, and manual modes to tune how autonomous agents are at each step.
Setup Path
Installation is designed to be agent-driven: users give their coding agent a prompt pointing to the project's INSTALL.md, and the agent installs Noodle and sets up the project. A manual getting-started guide is also provided, along with a cookbook that includes a minimal Noodle loop example. Contributors build with pnpm build and run lint, tests, and vet with pnpm check.
Community Discussions
Be the first to start a conversation about Noodle Skills
Share your experience with Noodle Skills, ask questions, or help others learn from your insights.
Pricing
Open Source
Noodle core is released under the MIT License (OSI-approved) and is free to use, copy, modify and distribute.
- MIT License
- Skill-based agent orchestration built in Go
- Skills, Scheduling, Brain (optional persistent memory) and Modes (auto, supervised, manual)
Capabilities
Key Features
- Composable, reusable skills for agent orchestration
- Agent-powered task scheduling that routes work to the right model
- Full observability of scheduling
- Optional persistent Brain memory across sessions
- Auto, supervised, and manual autonomy modes
- Agent-assisted installation via INSTALL.md
- Cookbook with minimal Noodle loop example
