uio-ai 0.1.8

Provider-agnostic AI agent/skill/prompt runner

uio

uio is a lightweight, provider-agnostic framework for building the Agentic Stack — agents, skills, prompts, and tools — as plain markdown files with YAML frontmatter. The uio CLI discovers and executes them against any supported LLM provider. The origin story covers how and why.

Concepts

Concept	What it is
Agent	A multi-turn tool-use loop that can execute shell commands and call MCP tools; defined in *.agent.md
Skill	A focused, composable subtask — same loop as an agent, but user-directed via uio skill run; defined in *.skill.md
Prompt	A single-shot LLM instruction with no tool loop; defined in *.prompt.md
Tool	An external capability the model invokes mid-loop (MCP tools, run_command) — agent-directed, not user-directed

See the Glossary for precise definitions of all terms, including the skill vs tool distinction.

Documentation

Full documentation lives in docs/ — covering installation, core concepts, a quickstart, CLI reference, configuration, providers, MCP integration, the chat REPL, cost ledger, registry, writing definitions, etc.

See Use Cases for end-to-end worked examples.

Quickstart

pip install uio-ai

# Scaffold .uio/ and install bundled examples
uio init --examples

# Run one of the bundled examples
uio skill run summarise "Your text here"
uio agent run repo-health

# Interactive streaming chat
uio chat

# View token spend
uio cost

Definitions live in .uio/:

my-project/
└── .uio/
    ├── agents/     my-agent.agent.md
    ├── skills/     my-skill.skill.md
    ├── prompts/    my-prompt.prompt.md
    ├── workflows/  my-workflow.workflow.md
    └── memory/

See Writing Definitions for the full file format and authoring guide.

License

GNU Affero General Public License v3.0