diff --git a/docs/docs.json b/docs/docs.json
index 88cea7782f4..87552f035ff 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -56,8 +56,12 @@
},
{
"group": "Agents",
- "icon": "cloud",
- "pages": ["hub/agents/intro"]
+ "icon": "robot",
+ "pages": [
+ "hub/agents/intro",
+ "hub/agents/overview",
+ "hub/agents/create-and-edit"
+ ]
},
"hub/sharing",
"hub/source-control"
@@ -343,7 +347,8 @@
"x": "https://twitter.com/continuedev",
"github": "https://github.com/continuedev/continue",
"linkedin": "https://linkedin.com/company/continuedev",
- "discord": "https://discord.gg/vapESyrFmJ"
+ "discord": "https://discord.gg/vapESyrFmJ",
+ "youtube": "https://www.youtube.com/@continuedev"
}
},
"contextual": {
diff --git a/docs/hub/agents/create-and-edit.mdx b/docs/hub/agents/create-and-edit.mdx
new file mode 100644
index 00000000000..58be7b5ea66
--- /dev/null
+++ b/docs/hub/agents/create-and-edit.mdx
@@ -0,0 +1,261 @@
+---
+title: "Create and Edit Agents"
+description: "Build custom AI workflows with prompts, rules, and tools through the Continue Hub interface"
+sidebarTitle: "Create & Edit"
+---
+
+
+ You can only create and edit Agents through Mission Control in the Continue Hub web interface.
+ This ensures proper validation, versioning, and team collaboration features.
+
+
+## Try an Agent First: Your 60-Second Challenge
+
+Before creating your own agent, let's see one in action! The fastest way to experience the power of Continue agents is with our demo repository.
+
+
+
+### See an Agent Create a Pull Request in Under 60 Seconds
+
+
+
+ Get a safe sandbox to experiment with:
+
+ **Option 1: GitHub Web Interface**
+ Visit [github.com/continuedev/demo-project](https://github.com/continuedev/demo-project) and click **Fork**
+
+ **Option 2: GitHub CLI**
+ ```bash
+ gh repo fork continuedev/demo-project
+ ```
+
+
+
+ Go to [hub.continue.dev/agents](https://hub.continue.dev/agents) and:
+ - **Connect GitHub** and authorize Continue when prompted
+ - This gives agents access to create PRs in your repositories
+
+
+
+ **Target your forked demo repo** and try one of these commands:
+
+
+
+ ```
+ Create a new function that calculates fibonacci numbers.
+ ```
+
+
+
+ ```
+ Fix the TypeError in api/users.ts
+ ```
+
+
+
+ ```
+ Add comprehensive README documentation with setup instructions.
+ ```
+
+
+
+
+
+ **Result:** A fully-formed Pull Request opens in your demo repo with:
+ - Complete implementation or fix
+ - Proper commit messages
+ - Detailed PR description
+ - Ready for review and merge
+
+
+
+
+ **Why Use the Demo Repo?**
+ - **Safe testing environment** - No risk to your production code
+ - **Pre-configured issues** - Common bugs and features to practice with
+ - **Immediate results** - See agents in action without setup complexity
+ - **Learn by example** - Study the generated code and PR descriptions
+
+
+
+ Once you see how agents work with the demo repo, you'll understand exactly how to create and customize your own for real projects!
+
+
+---
+
+## Creating an Agent
+
+ 
+
+
+
+
+ From the Continue Hub top navigation bar, select **"+"** β **"New Agent"**.
+
+ This opens the **Create an Agent (beta)** form with all required fields.
+
+
+
+
+ Configure your agent with the following fields:
+
+ | Field | What to Enter | Example |
+ |-------|---------------|---------|
+ | **Name** | Display name shown in the Hub | `GitHub PR Agent` |
+ | **Prompt** | First instruction the agent receives | `Open a GitHub PR to fix the specified issue.` |
+ | **Description** | What the agent does | `Creates a pull request and includes AI-generated summaries.` |
+ | **Tools (MCPs)** | Select built-in or custom MCPs | `GitHub, PostHog, Supabase` |
+ | **Rules** | Add any organizational rules | `continuedev/gh-pr-commit-workflow, continuedev/summarization` |
+ | **Model** | Choose a default LLM | `Claude Sonnet 4.5` |
+ | **Owner + Slug** | Determines namespace | `my-org/github-pr-agent` |
+ | **Visibility** | Access level | `Public, Organization, or Private` |
+
+
+ **Tip**: Start with a simple prompt and add complexity through rules and tools. The prompt should be a clear, single instruction that defines the agent's primary goal.
+
+
+
+
+ As you fill in the fields, the right-hand panel shows a live preview of your agent's YAML configuration:
+
+ ```yaml
+ name: Open PR with Fix
+ description: Open a GitHub PR to fix the specified issue
+ tools: built_in, anthropic/github-mcp
+ rules:
+ - continuedev/gh-pr-commit-workflow
+ - continuedev/summarization
+ model: Claude Sonnet 4.5
+ visibility: public
+ ```
+
+ This preview helps you verify the configuration before creating the agent.
+
+
+
+ Click **"Create Agent"** to save and publish it.
+
+ Your agent is immediately available to run in:
+ - Mission Control web interface
+ - TUI mode: `cn --agent your-org/your-agent-name`
+ - Headless mode: `cn --agent -p your-org/your-agent-name "prompt" --auto`
+
+
+
+## Editing an Agent
+
+You can edit any agent you own or that belongs to your organization.
+
+
+
+ From the **Agents** page or Mission Control view, click your agent's name, then select **"Edit Agent"**.
+
+
+
+ You can modify any of these components:
+
+
+
+ **Refine task behavior**
+
+ ```
+ # Before
+ Fix the bug in the authentication system
+
+ # After
+ Fix the authentication bug by:
+ 1. Identifying the root cause
+ 2. Implementing a secure solution
+ 3. Adding appropriate tests
+ 4. Opening a PR with detailed explanation
+ ```
+
+
+
+ **Enforce team standards**
+
+ Add or remove organizational rules:
+ - `continuedev/security-first` - Always scan for vulnerabilities
+ - `continuedev/test-coverage` - Require tests for new code
+ - `my-org/style-guide` - Follow company coding standards
+
+
+
+ **Connect additional systems**
+
+ - Add GitHub MCP for repository operations
+ - Include Sentry MCP for error monitoring
+ - Connect Supabase MCP for database operations
+ - Use custom MCPs for internal tools
+
+
+
+ **Adjust behavior and access**
+
+ - **Model**: Switch between Claude, GPT-4, or other supported LLMs
+ - **Visibility**: Control who can see and use the agent
+ - Public: Anyone can discover and use
+ - Organization: Only your team members
+ - Private: Only you can access
+
+
+
+
+
+ Click **"Update Agent"** when finished.
+
+ The updated version is instantly available to your team with automatic versioning for change tracking.
+
+
+
+
+ Test your agent thoroughly to ensure they interact as expected.
+
+
+## Example Agent Configurations
+
+Here are proven agent configurations you can create or use as inspiration:
+
+
+
+ **Snyk Continuous AI Agent** - Comprehensive security scanning with Snyk MCP integration.
+
+ Automates dependency analysis, vulnerability scanning, and creates remediation PRs with AI-powered fix suggestions.
+
+
+
+ **Netlify Continuous AI Agent** - Performance optimization with A/B testing and monitoring.
+
+ Tracks Core Web Vitals, identifies regressions, and provides optimization recommendations.
+
+
+
+ **Sentry Continuous AI Agent** - Automated error analysis and issue creation.
+
+ Monitors production errors, provides root cause analysis, and creates actionable GitHub issues.
+
+
+
+ **GitHub Manager AI Agent** - Comprehensive GitHub workflow automation.
+
+ Handles issue triage, PR reviews, and release note generation with natural language prompts.
+
+
+
+ **Supabase Continuous AI Agent** - Database security and management workflows.
+
+ Audits Row Level Security, identifies vulnerabilities, and generates fixes automatically.
+
+
+
+
+## Troubleshooting
+
+Common issues and solutions:
+
+| Problem | Solution |
+|---------|----------|
+| **Agent doesn't complete tasks** | Simplify the prompt, add more specific instructions, verify tool permissions |
+| **Tools aren't working** | Check MCP configuration, verify API keys and permissions in Hub settings |
+| **Inconsistent behavior** | Add rules to enforce consistent patterns, test with various input scenarios |
+| **Performance issues** | Consider model choice, simplify complex multi-step workflows, optimize tool usage |
diff --git a/docs/hub/agents/intro.mdx b/docs/hub/agents/intro.mdx
index 5004498d02f..7cfb49b1eb6 100644
--- a/docs/hub/agents/intro.mdx
+++ b/docs/hub/agents/intro.mdx
@@ -1,31 +1,61 @@
---
-title: "Agents Introduction"
-description: "Run and manage background agents in Mission Control"
-sidebarTitle: "Agents"
+title: "Getting Started with Agents"
+description: "Quick start guide for running AI workflows in Mission Control"
+sidebarTitle: "Getting Started"
---
+
+ Mission Control is your web interface for running and managing AI agents. Get started in minutes with pre-built workflows for security scanning, GitHub management, analytics insights, and more.
+
+
Mission Control is in beta. Please share any feedback with us in [GitHub discussions](https://github.com/continuedev/continue/discussions/8051).
-Mission Control is a way to run and manage background agents in Continue. You can use it to kick off:
-- Addressing small nitpicks and bugs
-- Building boilerplate-heavy features
-- Investigating an issue to kickstart your work
-- [Automated security scanning](../../guides/snyk-mcp-continue-cookbook)
-- Running repeatable tasks with your own rules, prompts, and MCP servers
-- Much more!
-
-## Quickstart
-
-To kick off your first agent
+Use Mission Control to kick off agents for:
+- **Bug fixes & code quality** - Address nitpicks and technical debt
+- **Feature development** - Build boilerplate-heavy features
+- **Security & compliance** - [Automated vulnerability scanning](../../guides/snyk-mcp-continue-cookbook)
+- **Investigation & analysis** - Research issues to kickstart your work
+- **Custom workflows** - Run repeatable tasks with your own rules and prompts
-1. Go to [hub.continue.dev/agents](https://hub.continue.dev/agents)
+## Quick Start
-
+
+
+ Go to [hub.continue.dev/agents](https://hub.continue.dev/agents) and connect with your GitHub account.
+
+ 
+
+
+
+ Select from pre-configured agents or create your own:
+
+
+
+ `continuedev/snyk-continuous-ai-agent`
+ Finds vulnerabilities and creates fix PRs
+
+
+
+ `continuedev/github-project-manager-agent`
+ Triages issues and manages workflows
+
+
+
+
+
+ Enter a prompt and watch your agent work:
+
+ ```
+ "Fix the TypeError in api/users.ts and open a PR with tests"
+ ```
+
+
-2. Connect with your GitHub account
-3. Enter the prompt for your agent
+
+ **New to agents?** Check out our [pre-configured agents](/hub/agents/overview#pre-configured-agents) to test out a workflow immediately.
+
## Example Workflow Tasks
@@ -36,7 +66,7 @@ Here are some example tasks you can try with your agents:
- "Fix the TypeError in api/users.ts where the user object might be undefined"
- "Add null checks to all database query results in the services/ directory"
- - "Fix all ESLint warnings in the components folder"
+ - "Fix all ESLint warnings in the components folder and open a PR"
- "Update deprecated React lifecycle methods to hooks in legacy components"
@@ -52,10 +82,10 @@ Here are some example tasks you can try with your agents:
+ - "Run a complete security scan and create GitHub issues for critical vulnerabilities"
- "Scan the codebase for hardcoded API keys and move them to environment variables"
- "Add input sanitization to all user-facing form fields"
- - "Update all npm packages with known security vulnerabilities"
- - "Implement rate limiting on the /api/login endpoint"
+ - "Update npm packages with security vulnerabilities and test compatibility"
@@ -87,12 +117,74 @@ Here are some example tasks you can try with your agents:
-## How to use background agents
+## Ways to Run Agents
-The practice of using background agents, which we call Continuous AI, requires practice and forethought to set up the right guiderails and habits to fit your development workflow, much like learning to work with a larger engineering team. We are constantly sharing our learnings on the [Continuous AI Blog](https://blog.continue.dev), but these few high-level tips are a great way to quickly become successful with agents:
+Choose the method that fits your workflow:
-- Practice first with the [Continue CLI](../../guides/cli) in "TUI mode". The Continue CLI is used to run agents, so you can easily test your prompts locally.
-- Identify and begin with tasks that you are confident can be accomplished by Continue. For example, ask Continue to fix a small bug where you already know the solution is simple.
-- Once you have merged a PR created by Continue, be increasingly ambitious with your tasks. By being willing to start tasks that might not succeed on the first try, you will learn about prompting best practices and limitations of current language models.
-- Use thorough prompts. Workflows can run for a long time to complete their task, so it is worthwhile to invest in sharing all of the important details.
-- Discuss the use of agents with your team. Truly embracing Continuous AI likely means acknowledging that a higher volume of PRs will be created and adjusting your code review habits.
+
+
+ **Web interface for interactive use**
+
+ Perfect for:
+ - Exploring agent capabilities
+ - Reviewing outputs before action
+ - Team collaboration
+ - One-time tasks
+
+ Access at [hub.continue.dev/agents](https://hub.continue.dev/agents)
+
+
+
+ **Terminal interface for development**
+
+ ```bash
+ cn --agent continuedev/github-project-manager-agent
+ ```
+
+ Perfect for:
+ - Local development workflows
+ - Testing agent behavior
+ - Interactive debugging
+ - Quick iterations
+
+
+
+ **Automated execution for CI/CD**
+
+ ```bash
+ cn --agent continuedev/snyk-continuous-ai-agent -p "Run security scan" --auto
+ ```
+
+ Perfect for:
+ - Scheduled workflows
+ - CI/CD integration
+ - Webhook triggers
+ - Background processing
+
+
+
+## Best Practices for Success
+
+The practice of using agents (Continuous AI) requires thoughtful setup of guardrails and habits:
+
+
+
+ Begin with tasks you're confident Continue can handle, like fixing known bugs with simple solutions.
+
+
+
+ Test with [Continue CLI](../../guides/cli) in TUI mode before deploying automation.
+
+
+
+ Agents can run for extended periods - invest time in detailed prompts with all important context.
+
+
+
+ Discuss agent usage and adjust code review habits for higher PR volumes.
+
+
+
+
+ **Learn More**: Explore advanced patterns and case studies on the [Continuous AI Blog](https://blog.continue.dev).
+
diff --git a/docs/hub/agents/overview.mdx b/docs/hub/agents/overview.mdx
new file mode 100644
index 00000000000..e4dc90a02f8
--- /dev/null
+++ b/docs/hub/agents/overview.mdx
@@ -0,0 +1,201 @@
+---
+title: "Agents Overview"
+description: "Standardized AI workflows that combine prompts, rules, and tools to complete specific, repeatable tasks"
+sidebarTitle: "Overview"
+---
+
+
+ Agents are custom AI workflows that combine a prompt, rules, and tools (MCPs and more) to complete specific, repeatable tasks.
+ They live in the Continue Hub and can be executed from Mission Control (web interface), TUI mode, or headless automation.
+
+
+## What Are Agents?
+
+Agents let your team standardize common workflows like opening GitHub PRs, summarizing analytics, or auditing security. Each agent includes:
+
+### Agent Components
+
+| **Component** | **Description** | **Example** |
+|----------------|-----------------|--------------|
+| **Prompt** | The agentβs main instruction that defines what it does and how it should behave. Additional user input is appended when invoked. | Example prompt: βSummarize ongoing work with status, blockers, and next steps. Use markdown formatting and a concise, professional tone.β |
+| **Rules** | Define consistent standards or behaviors that guide how the agent responds. Rules help ensure reliability across team usage. | βAlways include related issue or PR links when summarizing work.β |
+| **Tools / MCPs** | External systems or integrations the agent can call to complete tasks. MCPs (Model Context Protocols) extend functionality through APIs. | GitHub, PostHog, Supabase |
+| **Model** | The large language model that powers the agentβs reasoning and output generation. | Claude Sonnet 4.5 |
+| **Visibility** | Determines who can view or use the agent. Controls access at creation time. | Public, Organization, or Private |
+
+
+ Mission Control is in beta. Please share any feedback with us in [GitHub discussions](https://github.com/continuedev/continue/discussions/8051).
+
+
+## Ways to Run Agents
+
+You can run Agents in three main ways:
+
+
+
+ **Interactive web interface**
+
+ Trigger from the Continue Hub and review results in real-time.
+
+ ```bash
+ # Navigate to hub.continue.dev/agents
+ # Click "Run Agent" on any agent
+ # Monitor progress and review outputs
+ ```
+
+ Perfect for: Interactive debugging, reviewing agent outputs, team collaboration
+
+
+
+ **Interactive terminal mode**
+
+ Launch from terminal for live interaction and testing.
+
+ ```bash
+ cn --agent my-org/github-pr-agent
+ # Interactive chat interface opens
+ # Type your specific request
+ # Review and approve actions
+ ```
+
+ Perfect for: Local development, testing prompts, quick one-off tasks
+
+
+
+ **Automated execution**
+
+ Run one-off or scheduled tasks automatically without interaction.
+
+ ```bash
+ cn -p --agent my-org/snyk-agent "Run weekly security scan" --auto
+ ```
+
+ Perfect for: CI/CD pipelines, scheduled tasks, webhook integrations
+
+
+
+## Pre-configured Agents
+
+Skip the setup and use battle-tested agents from our cookbook collection:
+
+
+
+ `continuedev/snyk-continuous-ai-agent`
+ Finds vulnerabilities and opens PRs with fixes
+
+
+
+ `continuedev/github-project-manager-agent`
+ Triages issues and manages project workflows
+
+
+
+ `continuedev/posthog-continuous-ai-agent`
+ Analyzes user data and creates actionable tasks
+
+
+
+ `continuedev/netlify-continuous-ai-agent`
+ Monitors Core Web Vitals and optimizes deployments
+
+
+
+ `continuedev/supabase-agent`
+ Audits RLS security and generates migrations
+
+
+
+ `continuedev/dlt-agent`
+ Inspects pipelines and debugs load errors
+
+
+
+
+ **Explore More Agents**: Browse the complete collection of pre-configured agents and MCP integration cookbooks in our [Guides Overview](/guides/overview#mcp-integration-cookbooks).
+
+
+{/* ## Webhook Integrations
+
+Trigger Agents automatically through secure webhooks for CI/CD integration:
+
+```bash
+POST /webhooks/ingest/:webhookId
+{
+ "payload": { "trigger": "nightly-security-scan" }
+}
+```
+
+Perfect for connecting with:
+- GitHub Actions workflows
+- Monitoring alerts (Sentry, DataDog)
+- Deployment pipelines
+- Scheduled maintenance tasks */}
+
+## Collaboration
+
+Agents are organizational assets β once created, everyone in your org can use them:
+
+| Role | Permissions |
+|------|-------------|
+| **Public** | Use, create, remix, and delete Agents |
+| **Organization** | Share agents with your team |
+| **Private** | Create, edit, and delete Agents for your personal use |
+
+## Getting Started
+
+
+
+ Start with a cookbook agent like `continuedev/github-project-manager-agent`:
+
+ ```bash
+ cn --agent continuedev/github-project-manager-agent "List open issues labeled bug"
+ ```
+
+
+
+ Test agents locally before automation:
+
+ ```bash
+ cn --agent continuedev/snyk-continuous-ai-agent
+ # Interactive mode - perfect for learning how to use the agent for your use case
+ ```
+
+
+
+ Ready to build custom workflows? Learn how in our [Create and Edit guide](/hub/agents/create-and-edit).
+
+
+
+ Integrate with CI/CD using headless mode and webhooks for continuous workflows.
+
+
+
+## Best Practices
+
+The practice of using background agents, which we call Continuous AI, requires forethought to set up the right guardrails:
+
+- **Start Small**: Begin with tasks you're confident Continue can accomplish
+- **Use Thorough Prompts**: Agents can run for extended periods, so invest in detailed instructions
+- **Test Locally First**: Practice with TUI mode before deploying to production
+- **Team Alignment**: Discuss agent usage and adjust code review habits for higher PR volume
+- **Iterate and Improve**: Be willing to refine prompts based on results
+
+## Next Steps
+
+
+
+ Build your first custom agent with prompts, rules, and tools
+
+
+
+ Browse pre-built agents for security, analytics, and more
+
+
+
+ Learn to run agents from the command line
+
+
+
+ Access the web interface to manage agents
+
+
\ No newline at end of file
diff --git a/docs/hub/introduction.mdx b/docs/hub/introduction.mdx
index 2dd9b32daf0..3ae6e5d9448 100644
--- a/docs/hub/introduction.mdx
+++ b/docs/hub/introduction.mdx
@@ -7,25 +7,25 @@ description: "Central platform for discovering, creating, and sharing AI coding
## What You Can Do on the Hub
-
-
-
+
- Use a combinations of models, tools, and rules for different coding contexts. [Learn more →](/hub/configs/intro)
+
+
+ Manage organizations, API keys, secrets, and integrations. Configure models, MCP servers, and connected tools all in one place.
-
-
-
- Run background agents that complete tasks automatically in your repositories. [Learn more →](/hub/workflows/intro)
-
+
+ Search existing agents or build custom, reusable agents. Standardize prompts, rules, and tools to match your workflows and share with your team.
+
+
+ Launch and monitor agents across your repositories. Trigger on events or schedules and track performance.
## Hub Components
-Both configs and agents are built from reusable components that you can create, share, and customize:
+Agents are built from reusable components that you can create, share, and customize:
@@ -59,7 +59,7 @@ Both configs and agents are built from reusable components that you can create,
- Components are the building blocks used in both configs and agents. When you create a component on the hub, it becomes available for use in any config or agent.
+ Components are the building blocks for agents. When you create a component on the hub, it becomes available according to the permissions you set.
diff --git a/docs/images/hub/assets/images/agent-mission-control.gif b/docs/images/hub/assets/images/agent-mission-control.gif
new file mode 100644
index 00000000000..5fe52efb042
Binary files /dev/null and b/docs/images/hub/assets/images/agent-mission-control.gif differ
diff --git a/docs/images/hub/assets/images/hub-overview.jpg b/docs/images/hub/assets/images/hub-overview.jpg
new file mode 100644
index 00000000000..adbf435c1bc
Binary files /dev/null and b/docs/images/hub/assets/images/hub-overview.jpg differ
diff --git a/docs/images/hub/create-an-agent.gif b/docs/images/hub/create-an-agent.gif
new file mode 100644
index 00000000000..6914cd7a5fe
Binary files /dev/null and b/docs/images/hub/create-an-agent.gif differ