UKGovernmentBEIS/inspect_ai
Inspect: A framework for large language model evaluations
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 4 days ago, with 354 contributors on GitHub.
Use Cases & Benefits
- Provides a Python framework for evaluating large language models with built-in components for prompt engineering, tool usage, and model-graded assessments.
- Offers a comprehensive, extensible evaluation system with over 100 pre-built tests, enabling consistent and scalable LLM performance analysis.
- Use for benchmarking and comparing different large language models on standardized evaluation tasks.
- Use for developing and testing new prompt engineering techniques and multi-turn dialog strategies in LLMs.
- Use for integrating custom elicitation and scoring methods into LLM evaluation workflows via Python extensions.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Welcome to Inspect, a framework for large language model evaluations created by the UK AI Security Institute.
Inspect provides many built-in components, including facilities for prompt engineering, tool usage, multi-turn dialog, and model graded evaluations. Extensions to Inspect (e.g. to support new elicitation and scoring techniques) can be provided by other Python packages.
To get started with Inspect, please see the documentation at https://inspect.aisi.org.uk/.
Inspect also includes a collection of over 100 pre-built evaluations ready to run on any model (learn more at Inspect Evals)
To work on development of Inspect, clone the repository and install with the
-eflag and[dev]optional dependencies:Optionally install pre-commit hooks via
Run linting, formatting, and tests via
If you use VS Code, you should be sure to have installed the recommended extensions (Python, Ruff, and MyPy). Note that you'll be prompted to install these when you open the project in VS Code.
To work on the Inspect documentation, install the optional
[doc]dependencies with the-eflag and build the docs:If you intend to work on the docs iteratively, you'll want to install the Quarto extension in VS Code.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
894+262
Open issues
487+221
Compared with peers in LLM
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| thedotmack/claude-mem | 113.6K | +8.8K | 35 | today |
| NVIDIA/auto-ontology | 7.5K | +5.6K | 37 | — |
| HKUDS/DeepTutor | 55.5K | +5.5K | 65 | 5 days ago |
| affaan-m/ECC | 297.9K | +5.2K | 63 | 35 days ago |
| DietrichGebert/ponytail | 185.3K | +5.1K | 60 | 7 days ago |
| UKGovernmentBEIS/inspect_ai | 3.2K | — | 60 | 4 days ago |
| Category median | 113.6K | +5.5K | 60 | — |
Discover Repositories
Search across tracked repositories by name or description