AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Project Management › AD-AGENT
✦ Free & open sourceProject Management

AD-AGENT

An LLM-driven multi-agent framework that automates anomaly detection across tabular, graph, and time-series data.

Automate anomaly detection with natural language multi-agents

Generate, execute, review, and evaluate anomaly detection pipelines using conversational prompts.

Free forever · open source · BSD-2-Clause
✓ Light setup✓ Browser-based✓ Real-time collaboration
6
ZEKAI
Promising LLM anomaly agent
Free & open source · Project Management
Ease of setup5
Usefulness7
Maintenance7
Community5
★ 104
GITHUB
Apr 2026
UPDATED
BSD-2-Clause
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

AD-AGENT is an open-source framework that converts natural language requests into executable anomaly detection code. It coordinates specialized LLM agents to select algorithms, fetch documentation, generate scripts, and evaluate performance. You should use it if you analyze operational data and want to automate detection workflows across tabular, graph, or time-series datasets.

Runs on
Cross-platform
Hosting
Self-host
Languages
Python
License
BSD-2-Clause

What it is

The system accepts natural language instructions to run detection algorithms like Isolation Forest or DOMINANT on your raw datasets. It orchestrates separate agents for task planning, model selection, code generation, code review, and evaluation. Execution happens inside isolated Modal or Docker sandboxes to prevent unverified LLM code from running directly on your host machine.

Who it's for

It suits data analysts, technical project leaders, and operational engineers looking to prototype anomaly detection routines without manual script wiring. It is less suitable for non-technical teams needing a finished GUI or production-grade stability, as the project is still under active refactoring. It also requires an OpenAI API key and container infrastructure to run.

Key features

Natural Language Pipeline Generation

Converts text prompts into runnable Python scripts for anomaly detection algorithms.

Multi-Agent Orchestration Architecture

Coordinates specialized agents to manage model selection, doc retrieval, code writing, code review, and evaluation.

Cross-Library Detection Support

Integrates with PyOD for tabular data, PyGOD for graph structures, and TSB-AD for time-series datasets.

Isolated Sandbox Execution Backend

Executes LLM-generated code inside local Docker containers or remote Modal environments for security.

Direct Python Pipeline API

Exposes individual orchestration stages as Python functions to embed directly into custom Jupyter notebooks or scripts.

How to start

Up and running in 3 steps

1
Clone the repository and set up a Python virtual environment with dependencies installed from requirements.txt.
2
Set your OPENAI_API_KEY environment variable and configure your sandbox environment to Docker or Modal.
3
Run main.py via CLI or import api.pipeline into your Python scripts to start generating detection workflows.
Real talk

Our honest verdict

What's great

  • Automates algorithm selection and script writing across tabular, graph, and time-series modalities.
  • Runs generated code inside Docker or Modal sandboxes to protect host environments.
  • Supports popular underlying libraries including PyOD, PyGOD, and TSB-AD out of the box.
  • Provides a Python Pipeline API for direct integration into custom analytical workflows.

Where it falls short

  • Requires an active OpenAI API key, introducing recurring LLM API execution costs.
  • Under active refactoring with an un-packaged repository and unstable public API surface.
  • Requires local Docker setup or a Modal account to execute generated code securely.
Cost

Pricing & license

AD-AGENT is free under the BSD-2-Clause license. Running it requires an active OpenAI API key, which incurs usage costs per token, alongside optional infrastructure costs if you use Modal remote sandboxes.

Paid work

Open remote AI-training roles

877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives
Get more

Use it, or have us set it up

📄 Free PDF: AD-AGENT for Project Management
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure AD-AGENT for you — and train your team.
Get it done for you ↗
Questions

FAQ

What data formats and modalities does AD-AGENT support?

AD-AGENT handles tabular, graph, and time-series data using integrations with PyOD, PyGOD, and TSB-AD libraries.

Is generated code safe to run locally?

Yes, generated scripts run inside an isolated sandbox environment using either local Docker containers or remote Modal backends.

Do I need an LLM API key to use AD-AGENT?

Yes, AD-AGENT relies on OpenAI models for agent reasoning and code generation, so an active OpenAI API key is required.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Project Management — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google