Skip to main content

A minimal, file-driven CLI agent harness built on coreouto.

Project description

miniouto

miniouto logo

A minimal, file-driven CLI agent harness built on coreouto.

Three principles:

  1. Minimalism — No bloat. Extend with styles.
  2. Automation-friendly — Full CLI; TUI is optional.
  3. Fluidity — Adapts to any environment.

Preview

miniouto preview

Install

uv tool install miniouto
# or
pip install miniouto

License

Apache License 2.0

Quick start

# Either add a custom provider by hand:
miniouto provider custom add \
  --name openai \
  --api-key sk-... \
  --base-url https://api.openai.com/v1 \
  --default-model gpt-5.5            # optional; used when chat --model is not given

# Or browse the lma (llm-model-api) catalog and add from there:
miniouto provider providers          # see all 144 catalog providers
miniouto provider add Anthropic --api-key sk-ant-...   # adds it with the first catalog model

miniouto provider default openai
miniouto style set default
miniouto chat "hello"
miniouto                              # TUI mode

Model resolution

The active model is chosen by the first match in:

  1. miniouto chat --model <name> (per-call override)
  2. settings.model (legacy per-session override; cleared whenever the TUI model picker saves)
  3. provider.default_model (set by provider add --default-model, provider custom add --default-model, or the TUI model chip)
  4. error — no model can be inferred

Commands

Command Purpose
miniouto chat "prompt" One-shot chat turn
miniouto TUI mode
miniouto status Show current configuration
miniouto provider providers/models/add Browse the lma catalog and add providers from it
miniouto provider custom add Add a custom provider by hand (api_format, base_url, api_key, default_model)
miniouto provider list/remove/default Manage saved providers
miniouto style list/set/add/update/show Manage style documents (update re-seeds bundled + re-fetches all repo styles)
miniouto skill list/show List/show skills from ~/.agents/skills/

chat flags

Flag Effect
--name Session name (persists to ~/.miniouto/settings.toml)
--provider Override the active provider for this call
--model Override the resolved model for this call
--style Override the active style for this call
--max-tokens Cap output tokens
--temperature Sampling temperature
--continue / -c Prepend the session's previous history
--answer-only / -a Print only the final answer (no session marker, no loop events, no finish marker)
--with-session Print only the session marker + final answer (no loop events, no finish marker)

Storage

Everything lives under ~/.miniouto/:

  • providers.toml — provider configs (one top-level TOML table per provider: api_format, base_url, api_key, default_model, source)
  • settings.toml — active provider, model (legacy), style, session, theme
  • style/<name>.md — style documents
  • sessions/<name>.json — conversation history
  • logs/ — reserved (currently unused)

Skills live outside this tree, at ~/.agents/skills/<name>/SKILL.md (the Anthropic convention).

Override the root with the MINIOUTO_HOME environment variable.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

miniouto-0.1.0.tar.gz (5.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

miniouto-0.1.0-py3-none-any.whl (93.6 kB view details)

Uploaded Python 3

File details

Details for the file miniouto-0.1.0.tar.gz.

File metadata

  • Download URL: miniouto-0.1.0.tar.gz
  • Upload date:
  • Size: 5.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for miniouto-0.1.0.tar.gz
Algorithm Hash digest
SHA256 c331f2d556375af5f9bd5547a617ab38e94e40618c928bc51e95937f849e1d5f
MD5 e6c1f1e717d2c5f9f8d81670bc5e5d07
BLAKE2b-256 995e0605bcb5a44ff62241ef862091286e2c380339360b9a11bd2e2a316a156e

See more details on using hashes here.

Provenance

The following attestation bundles were made for miniouto-0.1.0.tar.gz:

Publisher: release.yml on llaa33219/miniouto

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file miniouto-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: miniouto-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 93.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for miniouto-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e7a8111b744d44015c312b405d9ff7b24f7c18596aaee8152a35d618c08bd3cb
MD5 1ed5bb61f8d81a458bd1d6e190f9c27e
BLAKE2b-256 72ee3ff486e5a7329367b44f5283824180cf7dd145593e81ff6208a1a0d2a2cd

See more details on using hashes here.

Provenance

The following attestation bundles were made for miniouto-0.1.0-py3-none-any.whl:

Publisher: release.yml on llaa33219/miniouto

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page