canonical: https://jentic.com/apis/screenpi.pe/screenpi-pe

# Screenpipe API

Screenpipe local REST API for searching and managing screen and audio recordings. Screenpipe is an AI-powered screen and audio memory tool that records, indexes, and allows searching of everything displayed on screen or heard through audio. The API exposes 13 endpoints.

## For AI agents

Programmatically search screen and audio content, keyword search. Covers 13 operations.

## Scope

Does not handle payments, communications, or crm - use for hr and recruiting only.

## Capabilities

- Search screen and audio content
- Keyword search
- Server health check
- List audio devices
- Start audio recording
- Stop audio recording

## Use cases

### HR and Recruiting Operations

Use the Screenpipe API to perform hr recruiting operations programmatically. The API provides 13 endpoints covering core functionality including search screen and audio content, keyword search, server health check.

Example prompt: Call GET /search to search screen and audio content

### Automated Audio Management

Automate audio operations by combining multiple Screenpipe API endpoints. Agents can keyword search and then server health check in a single workflow.

Example prompt: Call GET `/search/keyword` to keyword search, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Screenpipe API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually.

Example prompt: Search Jentic for 'search screen and audio content', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/search` | Search screen and audio content |
| GET | `/search/keyword` | Keyword search |
| GET | `/health` | Server health check |
| GET | `/audio/list` | List audio devices |
| POST | `/audio/start` | Start audio recording |
| POST | `/audio/stop` | Stop audio recording |
| GET | `/vision/list` | List monitors |
| GET | `/frames/{id}` | Get frame data |

## Key resources

- **Audio** — Operations related to Audio
- **Frames** — Operations related to Frames
- **Search** — Operations related to Search
- **System** — Operations related to System
- **Tags** — Operations related to Tags

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 71 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 87 / 100
  - Developer Experience & Jentic Compatibility: 62 / 100
  - AI-Readiness & Agent Experience: 48 / 100
  - Agent Usability: 94 / 100
  - Security: 100 / 100
  - AI Discoverability: 100 / 100
- **View full report:** https://jentic.com/apis/screenpi.pe/screenpi-pe/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the Screenpipe API by hand means standing up its request layer against screenpi.pe, coordinating the audio and vision capture calls, and building your own retry handling. Through Jentic you install once, import Screenpipe from the API Directory, store its credential once, and your agent calls it.
- **Permission scoping:** Screenpipe exposes search, audio, vision, and frame operations, so you limit the agent to the operations it needs, such as searching screen and audio content or listing audio. You choose the operations it may call, so starting or stopping audio capture is not included unless you add it.
- **Credential handling:** Your Screenpipe credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'search screen and audio content' or 'list captured audio', and Jentic returns the matching Screenpipe operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Greenhouse** — Alternative hr recruiting API
- **Lever** — Alternative hr recruiting API
- **Workday** — Complementary hr recruiting API

## FAQ

### What authentication does the Screenpipe API use?

The Screenpipe API uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I search screen and audio content with the Screenpipe API?

Yes. Use the GET /search endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Screenpipe API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I search screen and audio content through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'search screen and audio content'. Jentic returns the matching Screenpipe API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Screenpipe API have?

The Screenpipe API exposes 13 endpoints covering audio, frames, search operations.

### Can I limit what my agent is allowed to do with the Screenpipe API?

Yes. The Screenpipe API exposes search, audio, vision, and frame operations, and because Jentic One is self-hosted, your own rules decide which of those the agent may call. You can allow it to search screen and audio content or list audio devices while withholding operations like starting or stopping audio recording. The agent can only invoke the operations and credentials you have granted it.