rio
Rio is a fully autonomous, one-shot coding agent. It has no built-in interactive TUI, no conversation history, no human steer in the middle and no follow-up turns. Start a task and Rio runs until the task completes or aborts.
Getting Started
Install via uv:
uv tool install rio
Usage
Login to your preferred providers:
rio login anthropicrio login github-copilotrio login codex- ...
Run an ad hoc task:
rio run "Fix gh issue 123."
Rio keeps its State in SQLite and executes independent Python scripts through uv.
Committed work survives restart; interrupted scripts return UnknownExecution for
inspection. See Architecture.
Run a predefined workflow:
rio run task.md
The workflow is to write the task in a Markdown file, then run Rio against it.
You can add a short instruction when invoking it:
uv run rio run "Follow feature.md, run the tests, and finish the implementation"
Use --provider NAME --model MODEL to choose a provider and a model.
Rio prints a compact human transcript by default. Use --output json for one JSON
event per line. Each human-mode run prints a session id; continue it with
rio run --resume SESSION_ID. Start a new run for a new task.
Documentation
See the documentation for tutorials, guides, command-line reference, and an explanation of Rio's architecture.
Development
uv run pytest
uv run ruff check .
To run the Lean 4 verification, install elan and build the pinned toolchain from the repository root:
cd tests/lean && lake build
See the Lean behavior models for their scope and limits.
- rio.ai streams model responses from multiple providers.
- rio.agent owns SQLite state, immutable cells, notes, controls, workers, and recovery. Callers add runnable cell kinds.
- rio.coding supplies code and cmd cells, provider configuration and credentials.
- rio.cli runs coding tasks.
Metadata
Release files for rio 0.9.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| rio-0.9.1.tar.gz | 296.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| rio-0.9.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 492.2 kB
Release files / rio-0.9.1.tar.gz
| Download URL | rio-0.9.1.tar.gz |
|---|---|
| Size | 296.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fb11960d3bcf677c1166f99c57de7e1b8b3e6bec03385d7357af9b2875717009
|
|
BLAKE2b-256 checksum How to use checksums |
0e15c1e27f751301c7a4378fa3521927b9b49369f4b861ab88477e4db6451330
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 15, 2026.
Transparency logRelease files / rio-0.9.1-py3-none-any.whl
| Download URL | rio-0.9.1-py3-none-any.whl |
|---|---|
| Size | 195.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e733778482dbed769632b38ede53dc87346e982c6d2b1adb1d8ad368e03d1b62
|
|
BLAKE2b-256 checksum How to use checksums |
ab8c5b700b792a2ae22de11c1b4f8ed866c4cce12bf958893a16fb9ab36814e7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 15, 2026.
Transparency log