What makes modellix notable?

2.3K downloads. Trust evidence available

How should modellix be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

modellix

Integrate Modellix's unified API for AI image, video, and audio workflows. Use this skill whenever the user wants to generate or edit images, create or transform videos, synthesize speech, transcribe audio, clone a voice, do virtual try-on, or call any Modellix model API. Also trigger when the user mentions Modellix, model-as-a-service for media generation, or providers such as Qwen, Wan, Seedream, Seedance, Kling, Hailuo, MiniMax, Whisper, or CosyVoice through a unified API, or when they ask for a Modellix model's request schema, OpenAPI contract, or required input fields. Prefer modellix-cli (model get-schema, model run --wait, task download, doctor, model list) over hand-rolled REST polling whenever the CLI is available.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.3k

Updated

Oct 9, 2026

Version

1.0.24

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.3K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.3K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.24release · observed Sep 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170k1t1777mbfpt9j5hkb7fzx847td6:modellix

Install using `clawhub skill install s170k1t1777mbfpt9j5hkb7fzx847td6:modellix` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/modellix/modellix before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-modellix-modellix/snapshot"

Documentation

CLAWHUB

159,760 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: modellix
description: Integrate Modellix's unified API for AI image, video, and audio workflows. Use this skill whenever the user wants to generate or edit images, create or transform videos, synthesize speech, transcribe audio, clone a voice, do virtual try-on, or call any Modellix model API. Also trigger when the user mentions Modellix, model-as-a-service for media generation, or providers such as Qwen, Wan, Seedream, Seedance, Kling, Hailuo, MiniMax, Whisper, or CosyVoice through a unified API, or when they ask for a Modellix model's request schema, OpenAPI contract, or required input fields. Prefer modellix-cli (model get-schema, model run --wait, task download, doctor, model list) over hand-rolled REST polling whenever the CLI is available.
license: MIT
compatibility: Requires network access and Node.js 18.17+; Python 3.10+ enables automatic CLI updates and bundled helpers.
metadata:
author: Modellix
version: "3.10.0"
modellix-primary-credential: MODELLIX_API_KEY
modellix-hermes-tags: creative,image-generation,video-generation,audio-generation,speech-to-text,modellix,cli,api
---

# Modellix Skill

Modellix is a Model-as-a-Service (MaaS) platform for asynchronous image, video, and audio workflows. Prefer the official CLI (`modellix-cli`) so submit, wait, and download stay one coherent workflow. Host-specific persistent session guardrails also ship under `rules/*.mdc`.

## Official Docs

- AI Onboarding: https://docs.modellix.ai/get-started.md
- REST API: https://docs.modellix.ai/ways-to-use/api.md
- Full Models Index: https://docs.modellix.ai/llms.txt
- Docs MCP (search / read docs): https://docs.modellix.ai/mcp
- CLI package (source of truth for CLI behavior): https://www.npmjs.com/package/modellix-cli

### Documentation lookup policy

This plugin may expose the **Modellix Docs MCP** (`.mcp.json` → `https://docs.modellix.ai/mcp`). It is a **read-only documentation** server (`search_modellix`, docs filesystem query, optional feedback). It does **not** submit generation tasks, poll, download, or handle API keys.

When looking up product/API/install docs vs request-body schema:

1. For **request/response schema**, use `modellix-cli model get-schema <slug>` (JSON is the default; the endpoint is public and needs no API key). If CLI is unavailable, use Docs MCP, then `docs_url` from `model describe` or https://docs.modellix.ai/llms.txt.
2. For **product/install narrative**, prefer Docs MCP when the host has it connected (search, then read the matching page). Else use `model describe <slug> --json` → `docs_url`, or browse `llms.txt` and fetch the model `.md`.
3. For **CLI command syntax and flags**, prefer this skill, `references/cli-playbook.md`, the npm README, or `modellix-cli --help` — do **not** trust website CLI pages over the CLI package (docs can lag).

If the Docs MCP exposes a skill resource, treat **this** `SKILL.md` as the execution policy source of truth (CLI-first, defaults, paid-submit safety).

Do not rely on the w

scripts/README.md

# Scripts

These stdlib-only scripts provide deterministic CLI update and execution handling. The default execution path remains:

`modellix-cli model run --wait` → `modellix-cli task download`

## preflight.py

Environment check for CLI-first routing. Before doctor or any paid submit, it queries the public npm `latest` tag and installs the exact release only when the CLI is missing or older. It never downgrades a newer installed CLI.

Usage:

```bash
python scripts/preflight.py
python scripts/preflight.py --json
```

Checks:

- `modellix-cli` availability
- Installed and public-latest CLI versions, update source, and any non-fatal update warning
- Safe automatic upgrade before execution; `MODELLIX_CLI_AUTO_UPDATE=0|false|off` disables it
- Doctor result (Node, auth source, connectivity, balance) when CLI exists; a failed doctor check blocks a ready recommendation
- `MODELLIX_API_KEY` / discoverable profile auth
- Recommended mode (`cli`, `rest`, or `none` when readiness is not verified)

Credential handling policy:

- Default to session-only `MODELLIX_API_KEY` usage.
- Persist with explicit user approval via `modellix-cli auth login` / `init` (preferred) or user-level env.
- Do not write system-level env vars or other agent config files.

## invoke_and_poll.py

Optional wrapper: CLI uses `model run --wait`; REST keeps submit + poll fallback.
If this script fails, switch to the direct CLI commands and continue.

Usage:

```bash
python scripts/invoke_and_poll.py \
  --model-slug google/nano-banana-2-lite \
  --body '{"prompt":"A cinematic portrait of a fox in a misty forest at sunrise"}'

python scripts/invoke_and_poll.py \
  --model-slug bytedance/seedance-2.0-mini-t2v \
  --body '{"prompt":"A cat in a garden"}' \
  --timeout 10m \
  --output-dir ./outputs
```

Key behavior:

- Mode `auto` (default): resolve/update CLI before paid submission, pin that executable for submit/wait/download, otherwise use REST
- CLI path: single `modellix-cli model run --wait --json` (no hand-rolled poll loop; no paid-submit auto-retry)
- Optional `--output-dir` triggers `task download` after a successful CLI wait
- REST path: submit a paid POST exactly once, then retry only safe task-status reads on transient `408`/`429`/`5xx` responses or transport failures
- An explicit `--api-key` is passed to child CLI processes through `MODELLIX_API_KEY`, never as a process argument
- `--model-slug` is required in `provider/model` format
- Skill defaults when user omits a model: T2I=`google/nano-banana-2-lite`, T2V=`bytedance/seedance-2.0-mini-t2v`, TTS=`alibaba/qwen-audio-3.0-tts-flash`, STT=`openai/whisper-1`, STS=`alibaba/cosyvoice-clone` (full table in `SKILL.md`)

_meta.json

{
  "ownerId": "kn7dnx6mfjqqqdz8jdsr91fwdx82kha7",
  "slug": "modellix",
  "version": "1.0.24",
  "publishedAt": 1788513007269
}

references/capability-matrix.md

# Capability Matrix

Use this matrix to switch between CLI and REST without changing task semantics.

| Capability | CLI | REST | Notes |
| --- | --- | --- | --- |
| Resolve/update CLI and diagnose env/auth | `scripts/preflight.py --json` → `modellix-cli doctor --json` | N/A (manual key + probe) | Update check runs before paid work; failure keeps a working installed CLI |
| List / describe models | `model list`, `model describe <slug>` | Browse `llms.txt`, then fetch model `.md` | Prefer CLI when installed; `describe` is catalog metadata (`docs_url`, pricing, featured) |
| Get request / response schema | `model get-schema <slug>` (JSON default; public, no API key) | Fetch model `.md` OpenAPI via Docs MCP / `docs_url` / `llms.txt` | Use CLI schema before building `--body` when the slug is non-default or the body is non-trivial |
| Look up product / API / install docs | Docs MCP (`search_modellix` / docs filesystem) when connected via portable `mcp.json` or host adapter `.mcp.json` | Fetch `docs_url` or `llms.txt` → model `.md` | Docs MCP is read-only documentation — not generation. CLI flags still prefer npm / `--help` over website CLI pages |
| Submit async task | `modellix-cli model run --model-slug <provider/model> --body/--body-file ...` | `POST /api/v1/{provider}/{model_id}/async` | `model invoke` is an alias of `model run` |
| Wait for terminal status | `model run --wait` or `task wait <task_id>` | Poll `GET /api/v1/tasks/{task_id}` | Prefer CLI wait; do not hand-roll poll loops when CLI exists |
| Read task once | `task get <task_id>` | `GET /api/v1/tasks/{task_id}` | Same status lifecycle: `pending` / `processing` / `success` / `failed` |
| Download resources | `task download <task_id> --output-dir ...` | Download URLs from `result.resources` | CLI path preferred (safe filenames, limits) |
| Batch submit | `model batch <file.jsonl> --max-tasks N` | Multiple REST POSTs | CLI validates all lines before first paid POST |
| Local task recovery | `task history` | N/A | Never stores API keys or bodies |

CLI command policy:

- Canonical single-task flow: `model run --wait` → `task download`.
- Resolve the CLI once through `preflight.py` before the first command; do not update it after a paid submit begins.
- Split flow when needed: `model run --output task-id` → `task wait` → `task download`.
- Do not use deprecated guessed flags (for example `--model-type`).
- Use `--help` only when behavior is unclear.
- `preflight.py` owns automatic CLI refresh; `invoke_and_poll.py` pins the resolved executable for its complete workflow.
- Paid POST submissions must not be blindly retried on unknown outcomes.

## Slug Mapping

- `model-slug` uses `provider/model` format for both CLI and REST.
- REST path transformation:
  - Input: `google/nano-banana-2-lite`
  - Derived path parts: `provider=google`, `model_id=nano-banana-2-lite`

## Default Models (when user omits model)

| Task Type | Default slug |
| --- | --- |
| T2I | `google/nano-banana-2-lite` |
| T2V

references/cli-playbook.md

# CLI Playbook

Use this reference when `modellix-cli` is available. Command behavior source of truth: npm package `modellix-cli` and `modellix-cli --help` (not the website CLI guide page).

## Automatic version preflight

```bash
python3 scripts/preflight.py --json
```

Run preflight before the first CLI command in each workflow. It compares the installed CLI with the public npm `latest` tag, installs the exact newer version before execution, never downgrades, and falls back to the working installed CLI if the registry or install is unavailable. Set `MODELLIX_CLI_AUTO_UPDATE=0` only to pin the installed version. If Python is unavailable, inspect/install `modellix-cli@latest` manually before `doctor`.

## Authentication and profiles

Key resolution order (independent of profile selection):

1. `--api-key`
2. `MODELLIX_API_KEY`
3. Selected saved profile

Profile selection order: `--profile` → `MODELLIX_PROFILE` → saved `currentProfile` → `default`.

Session-first policy:

- Default to session env for one-off agent runs.
- When the user asks to persist: prefer `modellix-cli auth login` or `modellix-cli init`.
- Do not write system-level env or other agent config files.

```bash
# Interactive / validated save
modellix-cli init
modellix-cli auth login
modellix-cli auth login --profile work

# Non-interactive
modellix-cli init --api-key "$MODELLIX_API_KEY" --yes --json
modellix-cli auth status --json
modellix-cli auth whoami --json
```

Session-only:

```bash
export MODELLIX_API_KEY="your_api_key"
```

```powershell
$env:MODELLIX_API_KEY = "your_api_key"
```

Avoid putting keys on the command line when possible (shell history). Status/config JSON never prints the credential value.

## Diagnose

```bash
modellix-cli doctor
modellix-cli doctor --json
```

Checks Node.js, key source (without printing the key), API connectivity, and balance when authenticated. Failed required checks exit non-zero.

## Discover models

```bash
modellix-cli model list
modellix-cli model list --type text-to-image --output slugs
modellix-cli model list --provider google --limit 20
modellix-cli model list --search banana
modellix-cli model describe google/nano-banana-2-lite --json
```

When the user did not specify a model, use skill defaults instead of listing first:

- T2I: `google/nano-banana-2-lite`
- T2V: `bytedance/seedance-2.0-mini-t2v`
- I2I: `google/nano-banana-2-lite-edit`
- I2V: `bytedance/seedance-2.0-fast-i2v`
- V2V: `bytedance/seedance-2.0-fast-v2v`
- TTS: `alibaba/qwen-audio-3.0-tts-flash`
- STT: `openai/whisper-1`
- STS: `alibaba/cosyvoice-clone`

`--model-slug` must be exact `provider/model` as returned by the catalog.

`model describe` is catalog metadata (pricing, `docs_url`, featured). For the request/response contract, use the public schema command (no API key):

```bash
modellix-cli model get-schema alibaba/qwen-image-3.0-pro
modellix-cli model get-schema alibaba/qwen-image-3.0-pro --output human
modellix-cli model get-schema alibaba/qwen-image-3.0-pro --

Github ReposUpdated 2h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.