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

Libraries

How to use driaforall/mem-agent with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("driaforall/mem-agent")
model = AutoModelForCausalLM.from_pretrained("driaforall/mem-agent")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use driaforall/mem-agent with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/driaforall/mem-agent

SGLang

How to use driaforall/mem-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 "driaforall/mem-agent" \
    --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": "driaforall/mem-agent",
		"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 "driaforall/mem-agent" \
        --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": "driaforall/mem-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use driaforall/mem-agent with Docker Model Runner:
```
docker model run hf.co/driaforall/mem-agent
```

AtakanTekparmak commited on Sep 9, 2025

Commit

9416a84

verified ·

1 Parent(s): 681ae06

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ get_size(file_or_dir_path: str) -> int  # Bytes; empty = total memory size
 go_to_link(link_string: str) -> bool
 ```
-The model uses <think>, <python> and <reply> tags to structure its response. Using <reply> only when it's done interacting with the memory. The <python> block is executed in a sandbox with the tools and the results of the code block are returned in a <result> tag to the model, forming the agentic loop.
 The model is also trained to be able to handle optional filters given by the user in between <filter> tags after the user query. These filters are used to filter the retrieved information and/or obfuscate it completely.

 go_to_link(link_string: str) -> bool
 ```
+In the scaffold, the model uses `<think>`, `<python>` and `<reply>` tags to structure its response. Using `<reply>` only when it's done interacting with the memory. The `<python>` block is executed in a sandbox with the tools and the results of the code block are returned in a `<result>` tag to the model, forming the agentic loop.
 The model is also trained to be able to handle optional filters given by the user in between <filter> tags after the user query. These filters are used to filter the retrieved information and/or obfuscate it completely.