Instructions to use Hoodx/mira-agent-instinct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hoodx/mira-agent-instinct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Hoodx/mira-agent-instinct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hoodx/mira-agent-instinct")
model = AutoModelForCausalLM.from_pretrained("Hoodx/mira-agent-instinct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hoodx/mira-agent-instinct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hoodx/mira-agent-instinct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hoodx/mira-agent-instinct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hoodx/mira-agent-instinct

SGLang

How to use Hoodx/mira-agent-instinct 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 "Hoodx/mira-agent-instinct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hoodx/mira-agent-instinct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Hoodx/mira-agent-instinct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hoodx/mira-agent-instinct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Hoodx/mira-agent-instinct with Docker Model Runner:
```
docker model run hf.co/Hoodx/mira-agent-instinct
```

Mira AI Agent Model – Instinctive AGI / RSI

Mira is an agent-oriented LLM with instinctive reasoning compression and safe recursive self-improvement loops. Designed for long-horizon tasks, tool use, and self-play fine-tuning with eval gating.

Overview

Instinct mode: fast heuristic policy that reduces reasoning tokens while preserving first-attempt accuracy.
Agent layer: smolagents / Transformers Agent Toolkit compatible.
RSI: offline self-play fine-tuning with DPO, frozen improvement operator, lineage tracking.
Safety: gated repo, guardrails, audit log, explicit limitations.

Model Details

Base model: Qwen/Qwen3-8B
Architecture: decoder-only transformer
Context length: 32k
Training: supervised fine-tune on agent trajectories + self-play synthetic data
Quantized variants: Q4_K_M, Q8_0

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Hoodx/mira-agent-instinct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "user", "content": "Plan a 3-step research workflow and execute step 1"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
outputs = model.generate(**inputs)

smolagents

from smolagents import CodeAgent, HfApiModel

model = HfApiModel(model_id="Hoodx/mira-agent-instinct")
agent = CodeAgent(model=model, tools=[...])
agent.run("...")

Demo

See the HuggingFace Space: Hoodx/mira-agent-instinct-demo

Evaluation

Results in .eval_results/:

Terminal-Bench 2.1
SWE-Bench Verified
AgentBench

Limitations

Not AGI. Agent-oriented LLM with heuristic compression.
Recursive self-improvement is offline and eval-gated.
Tool use requires guardrails.

Citation

@misc{mira-agent-instinct,
  title={Mira AI Agent Model – Instinctive AGI / RSI},
  author={Hoodx},
  year={2026}
}

License

Apache-2.0

Downloads last month: 298

Model tree for Hoodx/mira-agent-instinct

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B