USC-FORTIS / AD-AGENT
A multi-agent framework to fully automate anomaly detection in different modalities, tabular, graph, time series, and more (work in progress)!
Why this job: says: agent framework, multi agent; topics: multi-agent
What it does
- Natural-language workflow generation. Go from a sentence to a runnable anomaly detection script.
- Multi-agent orchestration. Decoupled agents handle model selection, documentation lookup, code generation, review, and evaluation.
- Cross-library support. Works across pyod (tabular), pygod (graph), and tsb_ad (time-series).
- Pipeline API. Call api.pipeline stages directly from Python to embed AD-AGENT in notebooks, scripts, or larger workflows.
- Automatic model suggestion. When no algorithm is specified, the selector agent recommends competitive candidates based on the data and task.
Get started
pip install -r requirements.txt- Maintenance
- Inactive
- Last commit 6 months ago
- Stars
- 104
- On GitHub
- Licence
- BSD-2-Clause
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 3 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 100%
Topics
- anomaly-detection
- llm
- multi-agent
- outlier
- outlier-detection
Project record
- JobAgent frameworks
- StatusListed
- Commits139
- Forks34
- Watching8
- Stars in 28 days0
- CreatedMar 23, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026