Metadata-Version: 2.4
Name: oya-cli
Version: 0.2.0
Summary: Build, deploy, debug, and share AI agents on the Oya runtime — from your terminal.
Author-email: Oya <founders@oya.ai>
License-Expression: MIT
Project-URL: Homepage, https://oya.ai
Project-URL: Documentation, https://oya.ai/docs
Keywords: oya,agent,ai,claude-code,automation,runtime
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development
Classifier: Topic :: Utilities
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: click>=8.0
Requires-Dist: httpx>=0.25
Requires-Dist: pyyaml>=6.0

# oya-cli

**Build, deploy, debug, and share AI agents on the [Oya runtime](https://oya.ai) — from your terminal.**

Oya is an agent runtime: describe an agent, we deploy it in a sandbox, expose it via chat, webhooks, schedules, or an OpenAI-compatible API. This CLI is the developer-side surface — and the engine behind the [Oya Claude Code skill](https://oya.ai/docs/claude-code).

## Install

```sh
pipx install oya-cli   # recommended
# or
pip install oya-cli
```

## Quick start

```sh
oya login                        # save your API key (from https://oya.ai/api-keys)
oya quickstart                   # 60-second wow — pick a template, deploy
oya install-claude-skill         # use Oya from Claude Code
```

## What you get

```
oya quickstart                   # interactive 60-second build → deploy
oya agent list                   # your agents
oya agent runs <id> --status failed
oya agent run <id> <job_id>      # full stdout/stderr/error of a single run
oya agent thread <thread_id>     # full chat history including tool calls
oya agent trace <trace_id>       # Langfuse LLM trace

oya agent soul <id> --rule "..." --rule "..." --welcome "..."
oya agent skills add/update/remove/sync <id> ...
oya agent gateway oauth-start <id> <platform>
oya agent routine add/update <id|routine_id> ...
oya agent kb upload <id> <file>
oya agent deploy <id>

oya agent export <id> -o spec.oya.json   # share-ready JSON, no secrets
oya agent fork ./spec.oya.json           # clone someone else's agent
oya agent fork https://gist.../spec.oya.json

oya routine run <routine_id>             # manually trigger a routine
oya template list / get
```

Run `oya --help` or `oya <subcommand> --help` for full reference.

## The Claude Code skill

`oya install-claude-skill` copies an Anthropic Claude Code skill to `~/.claude/skills/oya/`. After that, you can ask Claude Code things like:

- *"Create an Oya agent — a Facebook SDR for my SaaS"*
- *"Why did my AI SDR fail last night?"*
- *"Add a 9am pipeline summary routine to my SDR"*
- *"Fork this Oya agent: <gist URL>"*

The skill drives this CLI under the hood. See [`claude-skill/README.md`](claude-skill/README.md) for details.

## Config

- `OYA_API_TOKEN` — your API key. Stored at `~/.oya/config.json` after `oya login`.
- `OYA_API_URL` — defaults to `https://oya.ai`. Set to `https://dev.oya.ai` for the dev environment.

## Links

- Runtime: https://oya.ai
- Docs: https://oya.ai/docs
- Support: founders@oya.ai
- License: MIT
