Text Generation
Transformers
Grok
GGUF
English
Indonesian
agent
autonomous-agent
chameleon-agent
universal-agent
omni-modal
multimodal
voice-notes
audio-processing
computer-vision
image-to-code
openai
claude
gemini
deepseek
permission-gated
full-access
senior-dev
code-generation
cybersecurity
debugging
architecture
ollama
prompt-engineering
Instructions to use Kicaulah/chameleon-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kicaulah/chameleon-agent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kicaulah/chameleon-agent")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kicaulah/chameleon-agent", device_map="auto") - Grok
How to use Kicaulah/chameleon-agent with Grok:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kicaulah/chameleon-agent with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kicaulah/chameleon-agent" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kicaulah/chameleon-agent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Kicaulah/chameleon-agent
- SGLang
How to use Kicaulah/chameleon-agent with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Kicaulah/chameleon-agent" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kicaulah/chameleon-agent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Kicaulah/chameleon-agent" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kicaulah/chameleon-agent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Kicaulah/chameleon-agent with Docker Model Runner:
docker model run hf.co/Kicaulah/chameleon-agent
Download quickstart.py from Kicaulah/chameleon-agent: direct link, hf CLI and curl.
- Browser
- Download file 4.7 kB
-
https://huggingface.co/Kicaulah/chameleon-agent/resolve/main/quickstart.py
- Command line
-
hf download hf://Kicaulah/chameleon-agent/quickstart.py
-
curl -L -o quickstart.py https://huggingface.co/Kicaulah/chameleon-agent/resolve/main/quickstart.py
4.7 kB
| """ | |
| Chameleon Agent: Universal Omni-Modal Multi-Platform Quickstart | |
| ============================================================== | |
| Run Chameleon Agent across ANY frontier provider or local engine with: | |
| - ποΈ Voice Notes & Audio Recordings (.mp3, .wav, .m4a, .ogg) | |
| - πΌοΈ Visuals & Screenshots (.png, .jpg, diagrams, UI bug captures) | |
| - π Documents, Log Dumps & Archives (.pdf, .csv, .log, .pcap, .zip) | |
| - π» Code Generation & System Engineering | |
| Supported Providers: OpenAI, Anthropic Claude, Google Gemini, DeepSeek, xAI Grok, Ollama. | |
| Protocol: Full Technical Access with Strict User-Permission Gate. | |
| """ | |
| import os | |
| import base64 | |
| from pathlib import Path | |
| SYSTEM_PROMPT_FILE = Path(__file__).parent / "system_prompt.txt" | |
| def load_system_prompt() -> str: | |
| if SYSTEM_PROMPT_FILE.exists(): | |
| return SYSTEM_PROMPT_FILE.read_text(encoding="utf-8") | |
| return "You are Chameleon Agent, the universal adaptive autonomous AI engineering entity with Omni-Modal ingestion." | |
| # ========================================================================= | |
| # 1. Processing Images & Visual Diagrams (OpenAI / Claude / Gemini / Grok) | |
| # ========================================================================= | |
| def analyze_image_with_openai(image_path: str, user_instruction: str): | |
| """Analyze architecture diagram or error screenshot using OpenAI GPT-4o.""" | |
| from openai import OpenAI | |
| client = OpenAI() | |
| with open(image_path, "rb") as f: | |
| base64_image = base64.b64encode(f.read()).decode("utf-8") | |
| response = client.chat.completions.create( | |
| model="gpt-4o", | |
| messages=[ | |
| {"role": "system", "content": load_system_prompt()}, | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "text", "text": user_instruction}, | |
| { | |
| "type": "image_url", | |
| "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"} | |
| } | |
| ] | |
| } | |
| ], | |
| temperature=0.2 | |
| ) | |
| return response.choices[0].message.content | |
| # ========================================================================= | |
| # 2. Processing Voice Notes & Audio Recordings (Google Gemini Native Audio) | |
| # ========================================================================= | |
| def process_voice_note_with_gemini(audio_path: str, instruction: str = "Transcribe, extract technical requirements, and plan the solution."): | |
| """Analyze audio memo or WhatsApp/Telegram voice note using Gemini 2.0 Flash.""" | |
| import google.generativeai as genai | |
| genai.configure(api_key=os.environ.get("GEMINI_API_KEY")) | |
| model = genai.GenerativeModel( | |
| model_name="gemini-2.0-flash", | |
| system_instruction=load_system_prompt() | |
| ) | |
| # Upload audio file directly | |
| audio_file = genai.upload_file(path=audio_path) | |
| response = model.generate_content([audio_file, instruction]) | |
| return response.text | |
| # ========================================================================= | |
| # 3. Processing Documents & Log Dumps (Anthropic Claude 3.7 Sonnet) | |
| # ========================================================================= | |
| def analyze_log_file_with_claude(log_path: str, prompt: str): | |
| """Ingest massive stack traces or core dumps with Claude 3.7 Sonnet.""" | |
| import anthropic | |
| client = anthropic.Anthropic() | |
| with open(log_path, "r", encoding="utf-8", errors="ignore") as f: | |
| log_content = f.read() | |
| message = client.messages.create( | |
| model="claude-3-7-sonnet-20250219", | |
| max_tokens=4096, | |
| system=load_system_prompt(), | |
| messages=[ | |
| { | |
| "role": "user", | |
| "content": f"Log Dump Content:\n```\n{log_content[:50000]}\n```\n\nTask: {prompt}\nRemember to ask for permission before modifying files." | |
| } | |
| ] | |
| ) | |
| return message.content[0].text | |
| def main(): | |
| print("=" * 80) | |
| print("π¦ Chameleon Agent: Universal Omni-Modal AI Engineering Engine") | |
| print("=" * 80) | |
| print("Omni-Modal Capabilities Active:") | |
| print(" [β] ποΈ Audio & Voice Notes : WhatsApp/Telegram memos, meeting audio (.mp3, .wav, .m4a)") | |
| print(" [β] πΌοΈ Visuals & Screenshots: Architecture diagrams, UI bugs, terminal errors (.png, .jpg)") | |
| print(" [β] π Files & Raw Dumps : Core dumps, stack traces, PDF specs, Wireshark PCAPs (.log, .pdf)") | |
| print(" [β] π Frontier Providers : OpenAI, Claude, Gemini, DeepSeek, Grok, Ollama") | |
| print("\nGovernance: Full Technical Access with Strict User-Permission Gate") | |
| print("=" * 80) | |
| if __name__ == "__main__": | |
| main() | |