Equip Agents · Updated April 20, 2026
Close the capability gap in Gemini CLI
Gemini CLI is Google's open-source AI agent CLI, it reasons with Gemini models, runs code, searches the web, and reads files. What it can't do natively: generate images, generate video, or understand visual inputs at the capability-call level. UseTrawsn fills that gap. Install it once, add it as a skill to Gemini CLI, and the agent gains access to image generation, video generation, and image understanding through a single runtime with no additional provider integrations.
What Gemini CLI can't do without UseTrawsn
Gemini CLI handles reasoning and code-centric tasks well. The gap is in production multimodal capabilities, the kind an agent needs to complete real-world tasks that involve creating or understanding visual content.
| Capability | Gemini CLI alone | With UseTrawsn |
|---|---|---|
| Image generation | No. Gemini CLI can't generate images natively. | Yes. Seedream 5, Nano Banana Pro, Nano Banana 2, routed through one command. |
| Video generation | No. Video generation isn't available in Gemini CLI. | Yes. Veo 3.1, Kling 3.0, Seedance 2.5, async with predictable polling. |
| Image understanding | Limited. Text-based description only via chat. | Yes. Read any image file or URL and get structured output for the agent to act on. |
| Video analysis | Limited. Not built into CLI capability calls. | Yes. Analyze video files or URLs and extract structured insights. |
| Multi-provider routing | N/A. No generative media routing. | Yes. One credential, one CLI, routes across all supported models by task. |
Add UseTrawsn to Gemini CLI in three steps
Installing UseTrawsn and connecting it to Gemini CLI takes about two minutes. Once the skill is active, Gemini CLI can discover and call any UseTrawsn capability as part of an agentic workflow.
1. Install the UseTrawsn CLI
curl -fsSL https://usetrawsn.ai/install.sh | shInstalls the usetrawsn binary. Verify with: usetrawsn --version
2. Authenticate
usetrawsn loginOpens a browser auth flow. Free tier available.
3. Add the UseTrawsn skill to Gemini CLI
npx -y skills add usetrawsn-ai/usetrawsn -a gemini-cli -yRegisters the UseTrawsn skill in Gemini CLI's skill context. Gemini CLI will discover it on next run.
What Gemini CLI can do with UseTrawsn
Once the UseTrawsn skill is active, Gemini CLI can invoke any of these capability commands as part of an agentic workflow, directly or as part of a multi-step task.
Generate images
Routes to Seedream 5, Nano Banana Pro, or Nano Banana 2. Returns a URL.
usetrawsn image generate --prompt "a product photo on a clean white surface"Generate video
Async job with polling. Returns video URL when complete.
usetrawsn video generate --model kling-3.0 --prompt "a product rotating slowly"Read and analyze images
Returns structured description the agent can act on.
usetrawsn actions image-read --url https://example.com/screenshot.pngAnalyze video
Extracts structured insights from a video file or URL.
usetrawsn actions video-read --url https://example.com/recording.mp4
How Gemini CLI decides what to call
- Need text reasoning? → Gemini CLI handles it natively
- Need to generate an image? → usetrawsn image generate
- Need to generate a video? → usetrawsn video generate
- Need to analyze a screenshot? → usetrawsn actions image-read
- Need to review a recording? → usetrawsn actions video-read
Why a capability runtime, not a direct API
Each generative media provider has its own SDK, credential path, rate-limit surface, and error vocabulary. Adding Veo 3.1, Kling 3.0, and Seedream 5 directly to a Gemini CLI workflow means five separate integrations that each need maintenance. When one provider changes its response schema, the workflow breaks.
UseTrawsn normalizes all of this. The agent authenticates once. The CLI interface is identical across all models. Async job handling, retry logic, and credential resolution happen inside the runtime, not in the agent's prompt or tool code. When a new model is added to UseTrawsn, Gemini CLI gets access to it without any changes to the workflow.
Frequently asked questions
Can Gemini CLI generate images?
Not natively. Gemini CLI is built for reasoning, code generation, and web search. Adding UseTrawsn as a skill gives Gemini CLI access to image generation through Seedream 5, Nano Banana Pro, and Nano Banana 2.
How do I add image generation to Gemini CLI?
Install UseTrawsn (curl -fsSL https://usetrawsn.ai/install.sh | sh), authenticate with usetrawsn login, then add the skill with npx -y skills add usetrawsn-ai/usetrawsn -a gemini-cli -y. Gemini CLI will discover the capability on its next run.
Which video models are available for Gemini CLI through UseTrawsn?
Veo 3.1 (Google DeepMind), Kling 3.0 (Kuaishou), and Seedance 2.5 (ByteDance) are all available through UseTrawsn. The agent selects the model with a --model flag or lets UseTrawsn route based on the task.
Does UseTrawsn replace Gemini's built-in capabilities?
No. UseTrawsn adds generative media capabilities that Gemini CLI doesn't have natively. Gemini CLI still uses its own Gemini models for reasoning, coding, and text tasks. UseTrawsn handles the visual and media layer.
CLI version and updating · 0.6.5
Current release checked October 21, 2026: 0.6.5. Use the update command for your installation method, then verify the version and login in the same environment that runs your agent.
Direct binary installation
usetrawsn updatenpm installation
npm install -g @usetrawsn/cli@latestusetrawsn --version
usetrawsn statusVersion 0.6.5 retries transient downloads, recovers an expired video link by querying the same task, and saves multiple image outputs to numbered files. After a video download failure, resume the existing task instead of generating again.
usetrawsn video tasks wait <task-id> -o result.mp4Dated examples retain the CLI version, output and charge from the original run. Updating the CLI does not revalidate an old result. Check the live model schema and current pricing before a new billed task.