AceKit - One-click integration of AceData AI capabilities for coding agents

You may have encountered a situation like this: while using Claude Code, Cursor, or Codex, you are writing code smoothly, and suddenly you need an image, a piece of background music, a short video, or you want it to conveniently look up the latest information. The result is that the agent itself cannot do these things. You have to find the API, read the documentation, configure the key, write the calling code, handle asynchronous polling, and after all that hassle, your inspiration has already cooled down.

AceKit is here to save you from all that hassle. With a single command, it integrates capabilities such as generating images, videos, music, web searches, and LLM conversations from AceData Cloud into your coding agent. After installation, you can simply speak in plain language, and the agent will load the corresponding skills, authenticate itself, and poll automatically to get the job done.

Understand what it does in 30 seconds

Before installation vs After installation:

What you say Before installation After installation (agent does it itself)
"Give this README a cover image" agent cannot do it, asks you to find the image API yourself Calls NanoBanana / Flux / Midjourney to generate the image
"Make a 30-second video from this script" cannot do it Calls Sora / Veo / Kling / Seedance to produce the video
"Add background music to this demo" cannot do it Calls Suno to generate a song
"Search for the latest X and summarize" cannot connect to the internet Calls Google SERP to get real-time results
"Shorten this long link" cannot do it Calls a URL shortening service to return the surl.id link

In one sentence: Your coding agent has transformed from "only able to write code" to "also capable of generating images, videos, music, and searching the internet."

Three steps to get started

The entire process takes just a few minutes and requires Node.js 18+.

Step 1 · Get an API Token. Go to the console and copy the Token—this single token is shared across all capabilities, and you get a free quota for your first application, so you can try it out for free.

Copy API Token in the console

Step 2 · Install. One command:

npx acekit

It will automatically detect the coding agent on your machine and install the complete set of skills. A real run looks like this (this machine only has Claude Code installed):

🃏  AceKit — wiring AI into your coding agent
✓  Detected: Claude Code
📦  Installing the AceData skill toolkit via @acedatacloud/skills …
Installed 19 skills to ~/.claude/skills
✅  Done. Try it now — ask your agent:
      "generate a hero image for this README"
      "turn this script into a 30-second video"

If the Token is not set, the first run will prompt you interactively to paste it; you can also pre-set export ACEDATACLOUD_API_TOKEN=your_token for a completely unattended installation. The number of skills will change as platform capabilities increase, based on the current list displayed by npx acekit list.

Step 3 · Speak in plain language. Reload the agent, then directly issue commands, such as:

Use the short-url skill to shorten https://platform.acedata.cloud/services

The agent will load the skills, initiate the call, and provide you with a real clickable result.

Run a real example (with output)

The following four examples are all real calls, with immediate returned results, not illustrations. The $KEY in the commands is your API Token.

① Shorten URL (synchronous, instant response)

curl -X POST https://api.acedata.cloud/shorturl \
  -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"content":"https://platform.acedata.cloud/services"}'

Returns https://surl.id/r/1uKp2kilXQ—clicking it will 302 redirect back to the original services page.

② Internet search (synchronous)

curl -X POST https://api.acedata.cloud/serp/google \
  -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"query":"OpenAI Sora release date","type":"search","number":3}'

Gets real-time Google results (excerpt):

- Sora is here — OpenAI                       https://openai.com/index/sora-is-here/
- Sora (text-to-video model) — Wikipedia
- What to know about the Sora discontinuation — OpenAI Help

③ LLM conversation (synchronous, one interface connects to 50+ models)

curl -X POST https://api.acedata.cloud/v1/chat/completions \
  -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-4.1-mini","messages":[{"role":"user","content":"Explain MCP in one sentence"}]}'

MCP is a protocol for unified management and exchange of model context information.
（39 tokens, this time about 0.00007 credit）

④ Generate image (asynchronous, about 20 seconds, agent automatically polls for the image)

curl -X POST https://api.acedata.cloud/nano-banana/images \
  -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"action":"generate","model":"nano-banana",
       "prompt":"a cute cartoon banana mascot waving hello, flat vector logo, white background"}'

About 22 seconds later, it returns a real image (HTTP 200 · image/png · 317 KB · this time about 0.13 credit):

Image generated by AceKit

You actually don’t need to remember these interfaces—after installing the skills, the agent will automatically construct the correct requests, handle authentication, and polling according to each SKILL.md. The above just lays out "what it does behind the scenes" for you.

What exactly has it installed

AceKit is the "front door" to the entire developer toolset of AceData, and currently, it installs a skill toolkit:

  • A set of Agent skills: Each skill comes with a written SKILL.md manual—detailing authentication, asynchronous polling, error retries, and how to fill in parameters, so the agent can just follow it. Run npx acekit list to see the current list (19 at the time of writing, and continuously increasing):
acedatacloud-api   ai-chat            face-transform     fish-audio
flux-image         google-search      hailuo-video       kling-video
luma-video         midjourney-image   nano-banana-image  producer-music
seedance-video     seedream-image     short-url          sora-video
suno-music         veo-video          wan-video
  • Unify a Token: One ACEDATACLOUD_API_TOKEN unlocks all capabilities, billed according to actual usage.

Classified by capability (based on npx acekit list):

Type Provider
🖼️ Raw Image Midjourney · Flux · Seedream · NanoBanana
🎬 Raw Video Sora · Veo · Kling · Luma · Hailuo · Seedance · Wan
🎵 Raw Music / Audio Suno · Producer · Fish Audio (TTS)
💬 LLM Dialogue 50+ models unified interface (GPT · Claude · Gemini · DeepSeek · Grok…)
🔎 Search Google SERP (Web · Images · News · Maps · Videos)
🔗 Tools Short links · Face processing

Similarly, AceData also provides independent MCP servers (Suno, Midjourney, Sora, SERP… published to PyPI / VS Code / Smithery / Docker), command line CLI, and Python / TypeScript SDK, which can be used separately as needed. AceKit v0.2 plans to support acekit add <name> for single capability installation, as well as automatic writing of MCP configurations for each agent.

Supported Agents

Agent Skill Installation Location
Claude Code ~/.claude/skills
Codex CLI ~/.agents/skills
Cursor / Gemini / OpenCode etc. ~/.agents/skills (point your agent here)

During installation, AceKit automatically detects the agents installed on the machine and only installs into the detected ones.

Easter Egg: Use the same Token to drive Claude Code itself

AceData's interface is also compatible with Anthropic's /v1/messages format, so you do not need an official Anthropic subscription, and can drive Claude Code with the same AceData Token. Create .claude/settings.local.json in the project root:

{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "your token",
    "ANTHROPIC_BASE_URL": "https://api.acedata.cloud"
  }
}

Restart Claude Code — it will utilize all Claude models and gain "hands" for raw images, raw videos, and raw music through AceKit. For more details, see the Claude Code Integration Guide.

Start for Free

AceKit is open source (MIT), and the repository is at github.com/AceDataCloud/AceKit. If you find it useful, please give it a ⭐.