<p align="center">
<img src="docs/logo.png" alt="Inspect-Hawk" width="320">
</p>
<h1 align="center">Inspect-Hawk</h1>
<p align="center">
<em>Run evals at scale in AWS</em>
</p>
<p align="center">
<a href="https://hawk.metr.org/">Documentation</a> ·
<a href="https://inspect.aisi.org.uk">Inspect AI</a> ·
<a href="https://inspectcommunity.slack.com/signup#/domain-signup">Community Slack</a> (support in <code>#inspect-hawk</code>)
</p>
---
## Start Here
**Run evals against an existing Hawk deployment:** install the CLI, authenticate, and submit your first eval. See the [CLI installation guide](https://hawk.metr.org/getting-started/installation/) and [running evaluations guide](https://hawk.metr.org/user-guide/running-evaluations/).
**Deploy your own Hawk instance:** follow the [Quick Start](https://hawk.metr.org/getting-started/) and [configuration reference](https://hawk.metr.org/getting-started/configuration/).
## Contents
- [Install the Hawk CLI](#install-the-hawk-cli)
- [Deploy Your Own Hawk Instance](#deploy-your-own-hawk-instance)
- [What You Can Do](#what-you-can-do)
- [What Hawk Deploys](#what-hawk-deploys)
- [Architecture](#architecture)
- [Documentation](#documentation)
- [Repository Structure](#repository-structure)
- [Contributing](#contributing)
Inspect-Hawk is a platform for running [Inspect AI](https://inspect.aisi.org.uk) evaluations on cloud infrastructure. You define tasks, agents, and models in a YAML config, and Hawk handles everything else: provisioning isolated Kubernetes pods, managing LLM API credentials, streaming logs, storing results in a PostgreSQL warehouse, and serving a web UI to browse them.
Inspect-Hawk is built on Inspect AI, the open-source evaluation framework created by the UK AI Security Institute. Inspect provides the evaluation primitives (tasks, solvers, scorers, sandboxes). Hawk provides the infrastructure to run those evaluations reliably at scale across multiple models and tasks, without manually provisioning machines or managing API keys.
The system is designed for teams that need to run evaluations regularly and at volume. It supports row-level security and access control per model, a managed LLM proxy, and a data warehouse for querying results across runs. It also supports [Inspect Scout](https://github.com/meridianlabs-ai/inspect_scout) scans over previous evaluation transcripts — Scout runs automated scanners (e.g. for reward hacking, safety-relevant behavior) across transcripts from completed evaluations, producing structured per-sample scan results.
### Demo Video
[](https://youtu.be/jJsapLt4CSk)
## Install the Hawk CLI
If you already have access to a Hawk deployment, you do not need to read the AWS/Pulumi deployment docs. Install the CLI from PyPI with uv:
```bash
uv tool install "hawk[cli]"
```
Or with pip: `pip install "hawk[cli]"`.
> **Keep the CLI in sync with your deployment.** To match a specific deployment,
> pin the release (run `hawk version` to see both sides, or check
> `<API_URL>/version`): `uv tool install "hawk[cli]==2.0.0"`. The CLI also checks
> for drift before each command: by default it warns and asks for confirmation
> (`HAWK_VERSION_CHECK=prompt`). Set `HAWK_VERSION_CHECK=warn` to warn without
> prompting, `block` to abort, or `off` to disable.
> **Bleeding edge (dev).** To install the latest unreleased `main` instead of a
> PyPI release:
> `uv tool install "hawk[cli] @ git+https://github.com/METR/hawk#subdirectory=hawk"`.
Then configure the CLI for your deployment, authenticate, and submit an eval:
```bash
export HAWK_API_URL=https://api.hawk.example.com
hawk login
hawk eval-set path/to/your.eval-set.yaml
hawk web
```
See [Running Evaluations](https://hawk.metr.org/user-guide/running-evaluations/), the [CLI reference](https://hawk.metr.org/user-guide/cli-reference/), and [`hawk/README.md`](hawk/README.md) for CLI usage.
Scripts can call the same API without Click via [`hawk[client]`](https://hawk.metr.org/user-guide/python-client/).
If you do not already have an eval-set YAML, follow the [running evaluations guide](https://hawk.metr.org/user-guide/running-evaluations/) to create one.
## Deploy Your Own Hawk Instance
If you do not have a Hawk deployment to connect to, the [Quick Start](https://hawk.metr.org/getting-started/) walks through deploying Hawk on AWS from zero. You will need an AWS account, a domain name, Pulumi, Docker, Python, Node.js, and `uv`.
Use the [configuration reference](https://hawk.metr.org/getting-started/configuration/) for DNS, authentication, networking, and optional integrations.
## What You Can Do
- 📋 **One YAML, full grid.** Define tasks, agents, and models. Hawk runs every combination.
- ☸️ **Kubernetes-native.** Each eval gets its own pod and fresh virtualenv. Sandboxes run in separate pods with network isolation.
- 🔑 **Built-in LLM proxy.** Managed proxy for OpenAI, Anthropic, and Google Vertex with automatic token refresh. Bring your own keys if you prefer.
- 📡 **Live monitoring.** `hawk logs -f` streams logs in real-time. `hawk status` returns a structured JSON report.
- 🖥️ **Web UI.** Browse eval sets, filter samples by score and full-text search, compare across runs, export to CSV.
- 🔍 **Scout scanning.** Run scanners over transcripts from previous evals.
- 🗄️ **Data warehouse.** Results land in PostgreSQL with trigram search and covering indexes.
- 🔒 **Access control.** Model group permissions gate who can run models, view logs, and scan eval sets.
- 💻 **Local mode.** `hawk local eval-set` runs the same config on your machine for debugging.
## What Hawk Deploys
When you run `pulumi up`, Hawk creates the following infrastructure on AWS:
| Component | Service | Purpose |
| ---------------- | ------------------------------- | ------------------------------------------------------- |
| Compute (evals) | EKS | Runs evaluation jobs as isolated Kubernetes pods |
| Compute (API) | ECS Fargate | Hosts the Hawk API server and LLM proxy |
| Database | Aurora PostgreSQL Serverless v2 | Results warehouse with IAM auth, auto-pauses when idle |
| Storage | S3 | Eval logs, written directly by Inspect AI |
| Event processing | EventBridge + Lambda + AWS Batch | Tags logs and imports them into the warehouse |
| Web viewer | ECS Fargate | Browse and analyze evaluation results (static SPA) |
| Networking | VPC + ALB | Internet-facing load balancer with TLS (configurable) |
| DNS | Route53 | Service discovery and public DNS |
Aurora can auto-pause and Karpenter can scale workload nodes to zero when idle. The EKS control plane, Karpenter controller node group, ECS services, ALB, and networking remain provisioned.
## Architecture
```mermaid
flowchart TD
CLI["<b>hawk CLI</b>"]
Client["<b>hawk.client</b><br/><i>scripts · hawk[client]</i>"]
API["Hawk API Server<br/><i>FastAPI on ECS Fargate</i>"]
EKS["Kubernetes (EKS)<br/><i>Scaled by Karpenter</i>"]
Runner["Runner Pod<br/><i>Creates virtualenv, runs inspect_ai.eval_set()</i>"]
Sandbox["Sandbox Pod(s)<br/><i>Isolated execution · Cilium network policies</i>"]
S3[("S3<br/><i>Eval logs</i>")]
S3Events["EventBridge<br/><i>S3 Object Created</i>"]
JobStatusUpdated["job_status_updated<br/><i>Lambda · tags files, emits events</i>"]
EvalEvents["EventBridge<br/><i>EvalCompleted</i>"]
Importer["eval_log_importer<br/><i>AWS Batch · imports to warehouse</i>"]
DB[("Aurora PostgreSQL<br/><i>Results warehouse</i>")]
Viewer["Web Viewer<br/><i>ECS Fargate · Browse, filter, export</i>"]
Middleman["Middleman<br/><i>LLM Proxy</i>"]
LLMs["LLM Providers<br/><i>OpenAI · Anthropic · Google · etc.</i>"]
CLI --> API
Client --> API
API -- "Validates config & auth<br/>Creates Helm release" --> EKS
EKS --> Runner
EKS --> Sandbox
Runner -- "Writes logs" --> S3
Runner <-- "API calls" --> Middleman
Middleman --> LLMs
S3 --> S3Events
S3Events --> JobStatusUpdated
JobStatusUpdated --> EvalEvents
EvalEvents --> Importer
Importer --> DB
Viewer -- "Browser calls" --> API
```
See the [Architecture docs](https://hawk.metr.org/infrastructure/architecture/) for the full component breakdown.
## Documentation
Full documentation lives at **[hawk.metr.org](https://hawk.metr.org/)**:
- [**Quick Start**](https://hawk.metr.org/getting-started/) — deploy Hawk on AWS from zero
- [**Installation**](https://hawk.metr.org/getting-started/installation/) — install the CLI and run your first eval
- [**Running Evaluations**](https://hawk.metr.org/user-guide/running-evaluations/) — eval set configs, secrets, local runs
- [**Running Scans**](https://hawk.metr.org/user-guide/running-scans/) — Inspect Scout scans over transcripts
- [**CLI Reference**](https://hawk.metr.org/user-guide/cli-reference/) — full command reference
- [**Python client**](https://hawk.metr.org/user-guide/python-client/) — `hawk[client]` API
- [**Configuration Reference**](https://hawk.metr.org/getting-started/configuration/) — every Pulumi config key
- [**Infrastructure**](https://hawk.metr.org/infrastructure/architecture/) — architecture, security, database, deployment, teardown
## Repository Structure
```
infra/ Pulumi infrastructure (Python) — VPC, EKS, ALB, ECS, RDS, Lambdas
hawk/ Hawk application (Python + React) — CLI, hawk.client, API, runner, core, web viewer
middleman/ LLM proxy (OpenAI, Anthropic, Google Vertex)
docs/ Documentation site (published to hawk.metr.org)
```
## Contributing
See the [Contributing guide](https://hawk.metr.org/contributing/) for developer setup, local development (Docker Compose or Minikube), testing, and code quality guidelines.
## License
[MIT](LICENSE)