🚀

Space

ML Intern

by smolagents hf-space--smolagents--ml-intern

Nexus Index

46.3 Top 100%

S: Semantic 50

A: Authority 0

P: Popularity 49

R: Recency 99

Q: Quality 50

Tech Context

Vital Performance

0 DL / 30D

0.0%

Source →

gradio SDK

CPU Hardware

Running Status

- Activity

Space Information Summary
Entity Passport
Registry ID	hf-space--smolagents--ml-intern
Provider	huggingface

📜

Cite this space

Academic & Research Attribution

BibTeX

@misc{hf_space__smolagents__ml_intern,
  author = {smolagents},
  title = {ML Intern Space},
  year = {2026},
  howpublished = {\url{https://huggingface.co/spaces/smolagents/ml-intern}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}

APA Style

smolagents. (2026). ML Intern [Space]. Free2AITools. https://huggingface.co/spaces/smolagents/ml-intern

🔬Technical Deep Dive

Full Specifications [+]

⚖️ Nexus Index V2.0

Methodology Index Protocol

46.3

TOP 100% SYSTEM IMPACT

Semantic (S) 50

Authority (A) 0

Popularity (P) 49

Recency (R) 99

Quality (Q) 50

💬 Index Insight

FNI V2.0 for ML Intern: Semantic (S:50), Authority (A:0), Popularity (P:49), Recency (R:99), Quality (Q:50).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit

Unbiased Data Node Refresh: VFS Live

Environment Profile

smolagents logo

ML Intern

An ML intern that autonomously researches, writes, and ships good quality ML related code using the Hugging Face ecosystem — with deep access to docs, papers, datasets, and cloud compute.

Quick Start

Installation

bash

git clone git@github.com:huggingface/ml-intern.git
cd ml-intern
uv sync
uv tool install -e .

That's it. Now `ml-intern` works from any directory:

bash

ml-intern

Create a .env file in the project root (or export these in your shell):

bash

ANTHROPIC_API_KEY= # if using anthropic models
OPENAI_API_KEY= # if using openai models
HF_TOKEN=
GITHUB_TOKEN=

If no HF_TOKEN is set, the CLI will prompt you to paste one on first launch. To get a GITHUB_TOKEN follow the tutorial here.

Usage

Interactive mode (start a chat session):

bash

ml-intern

Headless mode (single prompt, auto-approve):

bash

ml-intern "fine-tune llama on my dataset"

Options:

bash

ml-intern --model anthropic/claude-opus-4-6 "your prompt"
ml-intern --model openai/gpt-5.5 "your prompt"
ml-intern --max-iterations 100 "your prompt"
ml-intern --no-stream "your prompt"

Architecture

Component Overview

text

┌─────────────────────────────────────────────────────────────┐
│                         User/CLI                            │
└────────────┬─────────────────────────────────────┬──────────┘
             │ Operations                          │ Events
             ↓ (user_input, exec_approval,         ↑
      submission_queue  interrupt, compact, ...)  event_queue
             │                                          │
             ↓                                          │
┌────────────────────────────────────────────────────┐  │
│            submission_loop (agent_loop.py)         │  │
│  ┌──────────────────────────────────────────────┐  │  │
│  │  1. Receive Operation from queue             │  │  │
│  │  2. Route to handler (run_agent/compact/...) │  │  │
│  └──────────────────────────────────────────────┘  │  │
│                      ↓                             │  │
│  ┌──────────────────────────────────────────────┐  │  │
│  │         Handlers.run_agent()                 │  ├──┤
│  │                                              │  │  │
│  │  ┌────────────────────────────────────────┐  │  │  │
│  │  │  Agentic Loop (max 300 iterations)     │  │  │  │
│  │  │                                        │  │  │  │
│  │  │  ┌──────────────────────────────────┐  │  │  │  │
│  │  │  │ Session                          │  │  │  │  │
│  │  │  │  ┌────────────────────────────┐  │  │  │  │  │
│  │  │  │  │ ContextManager             │  │  │  │  │  │
│  │  │  │  │ • Message history          │  │  │  │  │  │
│  │  │  │  │   (litellm.Message[])      │  │  │  │  │  │
│  │  │  │  │ • Auto-compaction (170k)   │  │  │  │  │  │
│  │  │  │  │ • Session upload to HF     │  │  │  │  │  │
│  │  │  │  └────────────────────────────┘  │  │  │  │  │
│  │  │  │                                  │  │  │  │  │
│  │  │  │  ┌────────────────────────────┐  │  │  │  │  │
│  │  │  │  │ ToolRouter                 │  │  │  │  │  │
│  │  │  │  │  ├─ HF docs & research     │  │  │  │  │  │
│  │  │  │  │  ├─ HF repos, datasets,    │  │  │  │  │  │
│  │  │  │  │  │  jobs, papers           │  │  │  │  │  │
│  │  │  │  │  ├─ GitHub code search     │  │  │  │  │  │
│  │  │  │  │  ├─ Sandbox & local tools  │  │  │  │  │  │
│  │  │  │  │  ├─ Planning               │  │  │  │  │  │
│  │  │  │  │  └─ MCP server tools       │  │  │  │  │  │
│  │  │  │  └────────────────────────────┘  │  │  │  │  │
│  │  │  └──────────────────────────────────┘  │  │  │  │
│  │  │                                        │  │  │  │
│  │  │  ┌──────────────────────────────────┐  │  │  │  │
│  │  │  │ Doom Loop Detector               │  │  │  │  │
│  │  │  │ • Detects repeated tool patterns │  │  │  │  │
│  │  │  │ • Injects corrective prompts     │  │  │  │  │
│  │  │  └──────────────────────────────────┘  │  │  │  │
│  │  │                                        │  │  │  │
│  │  │  Loop:                                 │  │  │  │
│  │  │    1. LLM call (litellm.acompletion)   │  │  │  │
│  │  │       ↓                                │  │  │  │
│  │  │    2. Parse tool_calls[]               │  │  │  │
│  │  │       ↓                                │  │  │  │
│  │  │    3. Approval check                   │  │  │  │
│  │  │       (jobs, sandbox, destructive ops) │  │  │  │
│  │  │       ↓                                │  │  │  │
│  │  │    4. Execute via ToolRouter           │  │  │  │
│  │  │       ↓                                │  │  │  │
│  │  │    5. Add results to ContextManager    │  │  │  │
│  │  │       ↓                                │  │  │  │
│  │  │    6. Repeat if tool_calls exist       │  │  │  │
│  │  └────────────────────────────────────────┘  │  │  │
│  └──────────────────────────────────────────────┘  │  │
└────────────────────────────────────────────────────┴──┘

Agentic Loop Flow

text

User Message
     ↓
[Add to ContextManager]
     ↓
     ╔═══════════════════════════════════════════╗
     ║      Iteration Loop (max 300)             ║
     ║                                           ║
     ║  Get messages + tool specs                ║
     ║         ↓                                 ║
     ║  litellm.acompletion()                    ║
     ║         ↓                                 ║
     ║  Has tool_calls? ──No──> Done             ║
     ║         │                                 ║
     ║        Yes                                ║
     ║         ↓                                 ║
     ║  Add assistant msg (with tool_calls)      ║
     ║         ↓                                 ║
     ║  Doom loop check                          ║
     ║         ↓                                 ║
     ║  For each tool_call:                      ║
     ║    • Needs approval? ──Yes──> Wait for    ║
     ║    │                         user confirm ║
     ║    No                                     ║
     ║    ↓                                      ║
     ║    • ToolRouter.execute_tool()            ║
     ║    • Add result to ContextManager         ║
     ║         ↓                                 ║
     ║  Continue loop ─────────────────┐         ║
     ║         ↑                       │         ║
     ║         └───────────────────────┘         ║
     ╚═══════════════════════════════════════════╝

Events

The agent emits the following events via event_queue:

processing - Starting to process user input
ready - Agent is ready for input
assistant_chunk - Streaming token chunk
assistant_message - Complete LLM response text
assistant_stream_end - Token stream finished
tool_call - Tool being called with arguments
tool_output - Tool execution result
tool_log - Informational tool log message
tool_state_change - Tool execution state transition
approval_required - Requesting user approval for sensitive operations
turn_complete - Agent finished processing
error - Error occurred during processing
interrupted - Agent was interrupted
compacted - Context was compacted
undo_complete - Undo operation completed
shutdown - Agent shutting down

Development

Adding Built-in Tools

Edit agent/core/tools.py:

python

def create_builtin_tools() -> list[ToolSpec]:
    return [
        ToolSpec(
            name="your_tool",
            description="What your tool does",
            parameters={
                "type": "object",
                "properties": {
                    "param": {"type": "string", "description": "Parameter description"}
                },
                "required": ["param"]
            },
            handler=your_async_handler
        ),
        # ... existing tools
    ]

Adding MCP Servers

Edit configs/cli_agent_config.json for CLI defaults, or configs/frontend_agent_config.json for web-session defaults:

json

{
  "model_name": "anthropic/claude-sonnet-4-5-20250929",
  "mcpServers": {
    "your-server-name": {
      "transport": "http",
      "url": "https://example.com/mcp",
      "headers": {
        "Authorization": "Bearer ${YOUR_TOKEN}"
      }
    }
  }
}

Note: Environment variables like ${YOUR_TOKEN} are auto-substituted from .env.

🤗 Data Source: Hugging Face ↗

🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Space Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-space--smolagents--ml-intern
slug: smolagents--ml-intern
source: huggingface
author: smolagents
license
tags: docker, region:us

⚙️ Technical Specs

architecture: null
params billions: null
context length: null
pipeline tag: docker

📊 Engagement & Metrics

downloads: 0
stars: 208
forks: 0

Data indexed from public sources. Updated daily.

Welcome to Free2AI Tools!

Smart Search

FNI Score

You're All Set!

Cite this space

🔬Technical Deep Dive

⚖️ Nexus Index V2.0

💬 Index Insight

Verification Authority

Environment Profile

ML Intern

Quick Start

Installation

That's it. Now `ml-intern` works from any directory:

Usage

Architecture

Component Overview

Agentic Loop Flow

Events

Development

Adding Built-in Tools

Adding MCP Servers

🛡️ Space Transparency Report

🆔 Identity & Source

⚙️ Technical Specs

📊 Engagement & Metrics