What makes Laiye-OCR notable?

1.4K downloads. Trust evidence available

How should Laiye-OCR be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Laiye-OCR

Enables AI-powered parsing and key information extraction from high-frequency documents including invoices, orders, receipts, long texts, and common Chinese...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.4k

Updated

Oct 10, 2026

Version

1.10.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.4K downloadsadoption · observed Oct 10, 2026
Latest release: 1.10.3release · observed Apr 24, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17cqxy7t90jwwf5x1jhnss4td85c8ch:laiye-ocr

Install using `clawhub skill install s17cqxy7t90jwwf5x1jhnss4td85c8ch:laiye-ocr` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/laiye-adp/laiye-ocr before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-laiye-adp-laiye-ocr/snapshot"

Documentation

CLAWHUB

145,113 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agentic-doc-parse-and-extract
description: Enables AI-powered parsing and key information extraction from high-frequency documents including invoices, orders, receipts, long texts, and common Chinese identity & credential documents. Supports reusable custom templates for non-standard business files. Features batch concurrent processing to automate document workflows for finance, administration, HR data entry and other departments.
---
# agentic-doc-parse-and-extract Skill

agentic-doc-parse-and-extract is an official command-line tool released by Laiye Technology's ADP (Agentic Document Processing) product, enabling both humans and AI agents to invoke ADP capabilities in the terminal for document parsing and extraction.

## Quick Start Guide for AI Agents

### Core Workflow
1. **Install dependencies**: On first execution, install the ADP CLI tool and dependencies by following the instructions in [references/examples.md](references/examples.md).
2. **Discover commands**: Run `adp schema` to get the machine-readable JSON spec of all commands, parameters, types, and defaults.
3. **Authentication**: On first execution, run `adp config get` to verify credentials. If no valid configuration exists, prompt the user to provide an API Key.
4. **Check Application**: On first execution, retrieve the application list via `adp app-id list`. For subsequent executions, prioritize `adp app-id cache` (cached in context). If the cache is unavailable, refresh it by calling `adp app-id list` again.
5. **Execute**: Run `adp extract url <URL> --app-id <ID>` or `adp parse url <URL> --app-id <ID>`.
6. **Query**: Check results asynchronously with `adp extract query <task_id>` or `adp parse query <task_id>`.
7. **Error handling**: When a command fails, parse the stderr JSON to determine error type and recovery action. See [references/error-handling.md](references/error-handling.md).

### Common Scenarios → Command Mapping
| User Intent | Recommended Command | Handling Rules |
| :---------- | :------------------ | :------------- |
| - Read full document content<br>- Parse layout & structure<br>- Convert document to text<br>- Process / analyze full document | `adp parse` | - Sync processing for small files<br>- Async processing (`--async` parameter) for files >20MB or >200 pages |
| - Extract key fields (amount, date, name, ID, etc.)<br>- Output structured results (JSON/table) | `adp extract` | - Use Extract directly, **no need to parse first**<br>- Use matched existing app<br>- Create a custom extraction app if the document type is not in the known app list |
| Batch processing of local files | `adp extract local <folder path>` <br> `adp parse local <folder path> `  | Batch processing can accept files from the local folder. |
| Batch processing of URL files | `adp extract url <URL list file path>` <br> `adp parse url <URL list file path> `  | If you need to process multiple URLs in a batch, you can first save the list of URLs in a text fil

README.md

<div align="center">
<a id="agentic_doc_parse_and_extract"></a>

# 📄 Laiye Agentic Document Processing CLI (agentic_doc_parse_and_extract)

agentic_doc_parse_and_extract is the official command-line tool released by Laiye Technology's ADP (Agentic Document Processing) product, enabling both humans and AI Agents to invoke ADP capabilities in the terminal for document parsing and extraction.

[English](README.md) | [Simplified Chinese](README-CN.md)

</div>

## 🚀 About Laiye ADP

ADP is Laiye's **intelligent agent document processing product (Agentic Document Processing, referred to as ADP)** , based on the general understanding ability of large models, without relying on rules and annotations, with the general understanding ability of multi-language, MultiModal Machine Learning, and multi-scene; autonomous planning and execution of intelligent agents, able to understand task goals, autonomous planning steps, invoke tools, and complete complex tasks; end-to-end business automation, from document input to business decision-making to human-machine collaboration, forming a complete closed loop.

**agentic-doc-parse-and-extract** is the official open-source CLI tool of ADP, supporting both manual terminal invocation and automatic invocation via AI Skill. With a single command, it can accomplish: structured document parsing + intelligent extraction of key fields, covering all scenarios including invoices, orders, certificates, bills, and general documents, outputting standard JSON, and seamlessly integrating with automation and AI workflows.

---

### 💡 Core Features

agentic-doc-parse-and-extract focuses on intelligent processing of the entire document workflow, taking into account both manual terminal calls and automatic calls by AI Agents. Its core functions cover all scenarios of parsing, extraction, and batch processing, requiring no complex configuration, and operations can be completed with a single command:

| Function Name | Function Description | Optimal Scenario |
|---------|------------------|----------|
| **Document Parsing** | Automatically recognize multi-format documents such as PDFs and images, convert messy unstructured content (e.g., scanned documents, handwritten text, complex layout documents) into standardized Structured Data, while preserving the original document hierarchy and key relationships | Convert unstructured documents into Structured Data for LLM reading and subsequent extraction |
| **Out Of The Box Document Extraction** | Based on the native AI capabilities of the ADP large model, it comes with built-in standardized extraction models for invoices, receipts, orders, commonly used certificates in China, etc. No need to configure rules or manual annotation, one-click extraction of key fields from various types of general documentation, outputting standard JSON | Account Payable automation, expense management, procurement automation, quick entry of card and certificate information into the syst

_meta.json

{
  "ownerId": "kn770b2vgq91s7c13mz7syttqh81xj81",
  "slug": "laiye-ocr",
  "version": "1.10.3",
  "publishedAt": 1777027461260
}

references/commands.md

# ADP CLI Complete Command Reference

> This document is strictly aligned with the CLI's built-in `adp schema` output. Agent can also run `adp schema` to get the machine-readable JSON version of this spec.

## Global Options

| Option | Type | Description |
|--------|------|-------------|
| `--lang` | string | Set language (`en` or `zh`) |
| `--json` | boolean | Output in JSON format (recommended for Agent) |
| `--quiet` | boolean | Suppress all output except errors |

---

## config — Configuration Management

### `adp config set`

Set API Key or Base URL.

| Option | Type | Required | Description |
|--------|------|----------|-------------|
| `--api-key` | string | No | API Key for authentication |
| `--api-base-url` | string | No | API Base URL |

### `adp config get`

View current configuration (no options).

### `adp config clear`

Clear all configuration.

| Option | Type | Description |
|--------|------|-------------|
| `--force`, `-y` | boolean | Skip confirmation prompt |

---

## app-id — Application Management

### `adp app-id list`

Query available applications.

| Option | Type | Required | Default | Description |
|--------|------|----------|---------|-------------|
| `--app-label` | string | No | — | Filter by application label |
| `--app-type` | integer | No | — | Filter by application type: `0`=system preset, `1`=custom; omit to list all |
| `--limit` | integer | No | 120 | Maximum number of results |

### `adp app-id cache`

View cached application list (no options). Cache is permanent and does not expire.

---

## credit — Credit Balance

### `adp credit`

Check current account credit balance.

| Option | Type | Required | Description |
|--------|------|----------|-------------|
| `--api-key` | string | No | Override configured API Key |

---

## parse — Document Parsing

Parses the entire document to retrieve full text, layout, structure, and content.

### `adp parse local <file-path>`

Parse local file or folder (batch mode when path is a folder).

| Option | Type | Required | Default | Description |
|--------|------|----------|---------|-------------|
| `--app-id` | string | **Yes** | — | Application ID |
| `--async` | boolean | No | false | Enable asynchronous processing |
| `--no-wait` | boolean | No | false | Submit async task and return immediately (use with `--async`) |
| `--export` | string | No | — | Export results to specified path |
| `--timeout` | integer | No | 900 | Timeout in seconds |
| `--concurrency` | integer | No | 1 | Concurrent processing count (max 1 free, max 2 paid) |
| `--retry` | integer | No | 0 | Number of retries on failure (exponential backoff) |

### `adp parse url <url>`

Parse document from URL. When the URL points to a text file containing a list of URLs (one per line), batch mode is activated.

| Option | Type | Required | Default | Description |
|--------|------|----------|---------|-------------|
|

references/error-handling.md

# ADP CLI Error Handling Guide for Agent

> This document defines all error types, exit codes, and recommended Agent recovery strategies.

## Error Output Format

Errors are output to **stderr**. In JSON mode (`--json` or non-TTY), the format is:

```json
{
  "type": "ERROR_TYPE",
  "message": "Human-readable error description",
  "fix": "Suggested fix action",
  "retryable": true,
  "details": {"context": "command_name"}
}
```

Key field for Agent: **`retryable`** — if `true`, the Agent should retry with exponential backoff.

---

## Error Types and Agent Recovery Strategies

### AUTH_ERROR (Exit Code: 4)

**Triggers:** Invalid API Key, expired API Key, authentication failed, 401/403 HTTP status.

**Agent strategy:**
1. Run `adp config get` to check if API Key is configured
2. If not configured → prompt user to provide API Key
3. If configured but invalid → prompt user to verify/update API Key
4. Do NOT retry automatically — authentication errors are not transient

### PARAM_ERROR (Exit Code: 2)

**Triggers:** Invalid JSON format, unsupported file type, invalid parameter value, missing required parameter.

**Agent strategy:**
1. Read the `message` field to identify which parameter is wrong
2. Fix the parameter and retry
3. Common fixes:
   - JSON parse error → validate JSON syntax in `--extract-fields` or `--long-doc-config`
   - Unsupported file type → check file extension is one of: .jpg, .jpeg, .png, .bmp, .tiff, .tif, .pdf, .doc, .docx, .xls, .xlsx
   - Invalid enum value → check `--parse-mode` is one of: `advance`, `standard`, `agentic`

### RESOURCE_ERROR (Exit Code: 3)

**Triggers:** app-id not found, file not found, task not found, version not found, 404 HTTP status.

**Agent strategy:**
1. If app-id not found → run `adp app-id list` to refresh, then retry with correct app-id
2. If local file not found → verify file path exists
3. If task not found → the task_id may be incorrect or expired
4. Do NOT retry with same parameters

### NETWORK_ERROR (Exit Code: 1)

**Triggers:** Connection refused, DNS lookup failure, timeout, TLS handshake error.

**Agent strategy:**
1. This is retryable — retry with exponential backoff (2s, 4s, 8s)
2. Max 3 retries
3. If still failing → check network connectivity, verify `--api-base-url` is correct
4. Consider using `--timeout` with a larger value for slow networks

### API_ERROR (Exit Code: 1)

**Triggers:** Rate limiting (429), server error (5xx), generic API failures.

**Agent strategy:**
1. If 429 (rate limited) → wait 30 seconds, then retry
2. If 5xx → retry with exponential backoff, max 3 attempts
3. If persistent → suggest user contact support ([email protected])

### CONFLICT_ERROR (Exit Code: 5)

**Triggers:** Resource already exists, duplicate app name.

**Agent strategy:**
1. If creating custom-app with duplicate name → use a different `--app-name`
2. If updating → check current state with `custom-app get-conf

Github ReposUpdated 19h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.