Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Makefile
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
.PHONY: help sync openapi-spec openapi-spec-check test test-extras test-all test-models test-sdk lint lint-fix typecheck check build build-models build-server build-sdk publish publish-models publish-server publish-sdk hooks-install hooks-uninstall prepush evaluators-test evaluators-lint evaluators-lint-fix evaluators-typecheck evaluators-build galileo-test galileo-lint galileo-lint-fix galileo-typecheck galileo-build sdk-ts-generate sdk-ts-overlay-test sdk-ts-name-check sdk-ts-generate-check sdk-ts-build sdk-ts-test sdk-ts-lint sdk-ts-typecheck sdk-ts-release-check sdk-ts-publish-dry-run sdk-ts-publish
.PHONY: help sync openapi-spec openapi-spec-check test test-extras test-all test-sdk lint lint-fix typecheck check build build-models build-server build-sdk publish publish-models publish-server publish-sdk hooks-install hooks-uninstall prepush evaluators-test evaluators-lint evaluators-lint-fix evaluators-typecheck evaluators-build galileo-test galileo-lint galileo-lint-fix galileo-typecheck galileo-build sdk-ts-generate sdk-ts-overlay-test sdk-ts-name-check sdk-ts-generate-check sdk-ts-build sdk-ts-test sdk-ts-lint sdk-ts-typecheck sdk-ts-release-check sdk-ts-publish-dry-run sdk-ts-publish

# Workspace package names
PACK_MODELS := agent-control-models
Expand Down
8 changes: 6 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,9 @@ Explore real-world integrations with popular agent frameworks, or jump to [Quick
- **[Galileo Luna-2 Integration](examples/galileo/)** — AI-powered toxicity detection
- **[CrewAI SDK Integration](examples/crewai/)** — Working example on integrating with third party Agent SDKs and using Agent Control along side their guardrails
- **[DeepEval Integration](examples/deepeval/)** — Working Example on How to create custom evaluators to use with your controls
- **[Agent Control Demo](examples/agent_control_demo/)** — Basic agent control demonstration
- **[Steer Action Demo](examples/steer_action_demo/)** — Example of using the steer action for correction and retry
- **[Strands Agents](examples/strands_agents/)** — Integration with Strands Agents framework

## Quick start

Expand Down Expand Up @@ -290,12 +293,13 @@ Agent Control is built as a monorepo with these components:

```
agent-control/
├── sdks/python/ # Python SDK (agent-control)
├── sdks/python/ # Python SDK (agent-control-sdk)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added to architecture

├── sdks/typescript/ # TypeScript SDK (generated)
├── server/ # FastAPI server (agent-control-server)
├── engine/ # Evaluation engine (agent-control-engine)
├── models/ # Shared models (agent-control-models)
├── evaluators/ # Evaluator implementations (agent-control-evaluators)
├── scripts/ # Build and utility scripts
├── ui/ # Next.js web dashboard
└── examples/ # Usage examples
```
Expand Down Expand Up @@ -334,7 +338,7 @@ For detailed development workflows, see [CONTRIBUTING.md](CONTRIBUTING.md).
- **[Python SDK](sdks/python/README.md)** — SDK installation, usage, and API reference
- **[Server](server/README.md)** — Server setup, configuration, and deployment
- **[UI Dashboard](ui/README.md)** — Web dashboard setup and usage
- **[Evaluators](evaluators/README.md)** — Available evaluators and custom evaluator development
- **[Evaluators](evaluators/builtin/README.md)** — Available evaluators and custom evaluator development

## Contributing

Expand Down
10 changes: 5 additions & 5 deletions docs/OVERVIEW.md
Original file line number Diff line number Diff line change
Expand Up @@ -590,15 +590,15 @@ class ContentModerationEvaluator(Evaluator[ContentModerationEvaluatorConfig]):

```bash
# Core SDK
pip install agent-control
pip install agent-control-sdk

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Install SDK in Quickstart


# Server
pip install agent-control-server

# With Galileo Luna-2 evaluator support
pip install agent-control-evaluator-galileo
# Or via convenience extra:
pip install agent-control-server[galileo]
pip install agent-control-evaluators[galileo]

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Overview is now broken into different articles in the docs repo.
Everything about evaluators is now under Evaluators section in docs. For galileo evaluators, it can be found here.

```

### Quick Start
Expand Down Expand Up @@ -646,10 +646,10 @@ docker-compose up

## Roadmap

- [ ] Web UI for control management
- [x] Web UI for control management

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This section is not in Quick Start anymore in docs

- [ ] More built-in evaluators (OpenAI Moderation, Perspective API, etc.)
- [ ] Metrics and analytics dashboard
- [ ] Multi-language SDK support (TypeScript, Go)
- [x] Metrics and analytics dashboard
- [ ] Multi-language SDK support expansion (Go)
- [ ] Webhook notifications for violations

---
Expand Down
23 changes: 17 additions & 6 deletions server/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -183,18 +183,29 @@ GET /api/v1/agents/{agent_name}/controls

```bash
# Create control
POST /api/v1/controls
Body: { "control": {...} }
PUT /api/v1/controls
Body: { "name": "my-control" }

# List controls
GET /api/v1/controls?skip=0&limit=100
GET /api/v1/controls?cursor=123&limit=100

# Get control
GET /api/v1/controls/{control_id}

# Update control
PUT /api/v1/controls/{control_id}
Body: { "control": {...} }
# Get control data
GET /api/v1/controls/{control_id}/data

# Update control metadata
PATCH /api/v1/controls/{control_id}
Body: { "name": "new-name", "enabled": true }

# Update control data
PUT /api/v1/controls/{control_id}/data
Body: { "data": {...} }

# Validate control data without saving
POST /api/v1/controls/validate
Body: { "data": {...} }

# Delete control
DELETE /api/v1/controls/{control_id}
Expand Down
Loading