# cursor/cookbook

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/cursor-cookbook).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,158 stars · 499 forks · TypeScript

## Links

- GitHub: https://github.com/cursor/cookbook
- awesome-repositories: https://awesome-repositories.com/repository/cursor-cookbook.md

## Description

This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples cover running agents from TypeScript code against local workspaces or cloud runtimes, streaming their output live, and launching them from a terminal. Other examples include a cloud agent kanban dashboard, a task graph orchestrator, an app-prototyping chat, and a realtime voice intake demo.

Several samples go beyond a basic quickstart. The kanban dashboard lists cloud agents as cards grouped by status, repository, or branch, previews their artifacts, and launches new agents from a repository and prompt. The task graph runner splits work into a dependency graph, runs subagents in parallel by rank, passes upstream results to dependents, and shows live progress on a hot-reloading canvas. A bridge example lets programs in other languages drive an agent by exchanging JSON messages. The voice demo connects caller audio directly to a single speech-to-speech model that books appointments, collects intake details, and routes messages using fictional in-memory clinic data.

The collection also covers governance and hosting. Hook-based examples record an audit trail of prompts, shell commands, and file edits, block sensitive prompts, restrict models by repository, and keep documented skills aligned with code changes. Setup guides describe running cloud agent workers on customer-managed AWS infrastructure, using virtual machines with Docker, serverless containers, or Kubernetes. Workers connect outbound over HTTPS only, so no inbound access to the worker host is needed. The terminal coding agent example confines file and shell tools to a single workspace folder.

## Tags

### Artificial Intelligence & ML

- [Coding Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/ai-agent-orchestrators/coding-agent-orchestrators.md) — Runs coding agents from TypeScript code or a terminal, streams output live, and sequences dependent tasks so independent work runs in parallel.
- [Coding Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/ai-agent-tooling/coding-agents.md) — Starts coding agents from apps, scripts, and workflows through a TypeScript API that works against local workspaces and cloud runtimes. ([source](https://github.com/cursor/cookbook#readme))
- [Native Speech-to-Speech Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/native-speech-to-speech-agents.md) — Connects caller audio directly to a single speech-to-speech model that listens, reasons, calls tools, and speaks replies without separate transcription and synthesis stages. ([source](https://github.com/cursor/cookbook/tree/main/voice-agents/grok-patient-intake))
- [Realtime Speech-to-Speech Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/realtime-speech-to-speech-agents.md) — Uses a single realtime speech-to-speech model that takes caller audio and speaks replies directly, calling typed tools mid-conversation without separate transcription or synthesis stages.
- [Customer-Managed Cloud Agent Workers](https://awesome-repositories.com/f/artificial-intelligence-ml/parallel-agent-runs/customer-managed-cloud-agent-workers.md) — Runs agent workers in customer-managed environments to clone repositories, run builds and tests, and reach internal services while orchestration stays hosted. ([source](https://github.com/cursor/cookbook/tree/main/self-hosted-cloud-agent))
- [Agent Run Event Streams](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-run-event-streams.md) — Streams events as an agent run progresses while leaving prompts, models, cancellation, artifacts, and conversation state under the caller's control. ([source](https://github.com/cursor/cookbook#readme))
- [Agent Governance](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-security-and-governance/agent-governance.md) — Ships hook-based examples that audit agent prompts, shell commands and file edits, block sensitive prompts, restrict models by repository, and keep skills aligned with code.
- [CLI Coding Agent Hosts](https://awesome-repositories.com/f/artificial-intelligence-ml/cli-coding-agent-hosts.md) — Runs a coding agent from a command-line tool so developers can hand tasks to an agent from the terminal. ([source](https://github.com/cursor/cookbook/tree/main/sdk))
- [Cloud Agent Launchers](https://awesome-repositories.com/f/artificial-intelligence-ml/cloud-agent-launchers.md) — Lists cloud coding agents as kanban cards by status or repository, previews artifacts, and launches new agents from a repository and prompt. ([source](https://github.com/cursor/cookbook/blob/main/sdk/agent-kanban))
- [Cloud Agent Project Prototyping](https://awesome-repositories.com/f/artificial-intelligence-ml/cloud-agent-project-prototyping.md) — Spins up agents in a sandboxed cloud environment to scaffold new projects and refine ideas from a web interface. ([source](https://github.com/cursor/cookbook#readme))
- [Cross-Language Agent Bridges](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-language-agent-bridges.md) — Lets programs in other languages run a single agent turn by starting a bridge process and exchanging JSON messages. ([source](https://github.com/cursor/cookbook/blob/main/README.md))
- [Headless Agent Runs](https://awesome-repositories.com/f/artificial-intelligence-ml/headless-agent-runs.md) — Creates an agent in a script, sends a fixed prompt, and waits for the run to finish without an editor. ([source](https://github.com/cursor/cookbook/blob/main/sdk/quickstart))
- [App Building Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/mobile-app-agents/app-building-agents.md) — Builds new apps from a plain-language description by running a coding agent inside a chat application that writes the code and refines it step by step. ([source](https://github.com/cursor/cookbook/tree/main/sdk))
- [Parallel Task Graph Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-step-goal-execution/parallel-task-graph-execution.md) — Splits work into a dependency graph, runs subagents in parallel by rank, passes upstream results to dependents, and shows live progress on a canvas.
- [Terminal Coding Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/terminal-coding-agents.md) — Demonstrates a terminal agent loop calling a hosted model with file and shell tools confined to one workspace folder. ([source](https://github.com/cursor/cookbook/blob/main/README.md))

### Business & Productivity Software

- [Agent Progress Boards](https://awesome-repositories.com/f/business-productivity-software/agent-progress-boards.md) — Lists cloud coding agents as kanban cards grouped by status or repository, previews artifacts, and launches new agents from a repository and prompt. ([source](https://github.com/cursor/cookbook/blob/main/README.md))
- [Appointment Scheduling Systems](https://awesome-repositories.com/f/business-productivity-software/appointment-scheduling-systems.md) — Finds open slots, registers patients, and books, lists, cancels, or reschedules appointments during a live voice conversation. ([source](https://github.com/cursor/cookbook/blob/main/voice-agents/grok-patient-intake))

### Development Tools & Productivity

- [Agent Event Hooks](https://awesome-repositories.com/f/development-tools-productivity/event-automation-hooks/agent-event-hooks.md) — Runs configured hook scripts on agent events such as prompt submission, shell commands, and file edits to log, block, or follow up, failing closed on errors.
- [Agent Task Dependency Resolvers](https://awesome-repositories.com/f/development-tools-productivity/task-dependency-management/agent-task-dependency-resolvers.md) — Executes a graph of dependent agent tasks ordered by dependency so each step runs only after its prerequisites finish. ([source](https://github.com/cursor/cookbook/tree/main/sdk))
- [Hot Reloading Previews](https://awesome-repositories.com/f/development-tools-productivity/hot-reloading-previews.md) — Re-renders a preview frame live as agents write streamed output into a canvas file that recompiles on every write.

### DevOps & Infrastructure

- [Agent Worker Deployments on AWS](https://awesome-repositories.com/f/devops-infrastructure/agent-worker-deployments-on-aws.md) — Provides setup guides for running agent workers on AWS virtual machines with Docker, serverless containers, or Kubernetes, including trade-offs and troubleshooting. ([source](https://github.com/cursor/cookbook/tree/main/self-hosted-cloud-agent))
- [Worker Connections](https://awesome-repositories.com/f/devops-infrastructure/self-hosted-instances/worker-connections.md) — Connects self-hosted cloud agent workers outbound over HTTPS to the hosted orchestration service, so no inbound access to the worker host is needed.
- [Self-Hosted Agent Servers](https://awesome-repositories.com/f/devops-infrastructure/self-hosted-server-platforms/self-hosted-agent-servers.md) — Guides running cloud agent workers on customer-managed AWS servers using containers on virtual machines or serverless containers. ([source](https://github.com/cursor/cookbook/blob/main/README.md))
- [Self-Hosted Infrastructure](https://awesome-repositories.com/f/devops-infrastructure/self-hosted-infrastructure.md) — Guides running cloud agent workers on customer-managed AWS servers or containers with autoscaling and outbound-only HTTPS connections to the hosted service.

### Software Engineering & Architecture

- [Dependency-Ordered Task Execution](https://awesome-repositories.com/f/software-engineering-architecture/dependency-ordered-task-execution.md) — Sorts subtasks into dependency ranks, runs each rank in parallel, and injects parent output snippets into child prompts so dependents wait for prerequisites.
- [Parallel Subagent Orchestrators](https://awesome-repositories.com/f/software-engineering-architecture/parallel-subagent-orchestrators.md) — Splits a task into a dependency graph and runs the pieces in parallel across local subagents with live status. ([source](https://github.com/cursor/cookbook#readme))
- [Dependency-Aware Task Orchestration](https://awesome-repositories.com/f/software-engineering-architecture/task-scheduling/dependency-aware-task-orchestration.md) — Sorts subtasks into dependency ranks and runs each rank concurrently so independent work fans out and dependents wait. ([source](https://github.com/cursor/cookbook/blob/main/sdk/dag-task-runner))

### Security & Cryptography

- [Model Usage Blocklists](https://awesome-repositories.com/f/security-cryptography/model-usage-blocklists.md) — Blocks prompt submissions when both the chosen model and the git origin repository name match configured substring blocklists, failing closed on errors. ([source](https://github.com/cursor/cookbook/blob/main/hooks))
- [Prompt Secret Scanning](https://awesome-repositories.com/f/security-cryptography/pii-data-leakage-prevention/prompt-secret-scanning.md) — Scans submitted prompts for secrets or sensitive data and blocks them before reaching the model, optionally deferring to a data-loss or secret-scanning service. ([source](https://github.com/cursor/cookbook/blob/main/hooks))
- [Agent Read and Write Folder Confinement](https://awesome-repositories.com/f/security-cryptography/project-root-file-read-restrictions/agent-read-and-write-folder-confinement.md) — Confines agent file and shell tools to one workspace folder, rejecting absolute paths, parent traversal, and symlink escapes while capping output, run time, and tool rounds. ([source](https://github.com/cursor/cookbook/blob/main/sdk/grok-coding-agent-cli))
- [Agent Tool Auditing](https://awesome-repositories.com/f/security-cryptography/third-party-script-security/activity-auditing/agent-tool-auditing.md) — Records each agent action through project hooks into an audit log so teams can review what the agent did and when. ([source](https://github.com/cursor/cookbook/blob/main/README.md))
- [Workspace Path Sandboxes](https://awesome-repositories.com/f/security-cryptography/workspace-path-sandboxes.md) — Resolves every file and shell tool path inside one workspace folder, blocking absolute paths, traversal, and symlink escapes while capping output, run time, and tool rounds.

### System Administration & Monitoring

- [Agent Activity Audit Trails](https://awesome-repositories.com/f/system-administration-monitoring/agent-activity-audit-trails.md) — Records prompt submissions, shell commands and results, and file edits as structured entries to a local file or an internal audit service. ([source](https://github.com/cursor/cookbook/tree/main/hooks))
- [Agent Hook Audit Logs](https://awesome-repositories.com/f/system-administration-monitoring/agent-hook-audit-logs.md) — Writes structured line-by-line records of prompts, shell commands, shell results, and file edits, and can forward them to internal logging or monitoring services. ([source](https://github.com/cursor/cookbook/blob/main/hooks))
- [Line-Delimited JSON Protocols](https://awesome-repositories.com/f/system-administration-monitoring/automated-server-maintenance/json-automation-protocols/line-delimited-json-protocols.md) — Exchanges newline-delimited JSON messages with a child bridge process so any language with standard JSON support can drive a coding agent turn.

### User Interface & Experience

- [Agent Interaction Streams](https://awesome-repositories.com/f/user-interface-experience/ui-event-streams/agent-interaction-streams.md) — Streams an agent's responses and tool usage live into a chat window so users can follow the work as it happens. ([source](https://github.com/cursor/cookbook/blob/main/sdk/app-builder))

### Web Development

- [Task Progress Streams](https://awesome-repositories.com/f/web-development/real-time-data-streaming/task-progress-streams.md) — Streams agent output token by token into a canvas file so each task card updates live as work progresses. ([source](https://github.com/cursor/cookbook/blob/main/sdk/dag-task-runner))