Build autonomous AI agents in Python.
Upsonic is a Python framework for constructing autonomous and traditional AI agents using Claude (via the Anthropic API, specifically models like claude-sonnet-4-5) alongside other LLMs. The framework offers two primary agent classes: `AutonomousAgent`, which restricts all file and shell operations to a declared workspace directory and blocks path traversal and dangerous commands, and `Agent`, a more conventional task-runner that accepts custom Python functions decorated with `@tool`. Both classes connect to external services through MCP tool integration, giving agents access to third-party data sources and APIs. The repository also ships prebuilt community agents such as OpenClaw and Claude Cowork, each bundled with a system prompt and first message for immediate use. A separate OCR module supports a layered document processing pipeline with six interchangeable engines including EasyOCR, Tesseract, PaddleOCR, and DeepSeek OCR. Python developers building production agent workflows, document extraction pipelines, or multi-tool automation systems are the primary audience.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/Upsonic/Upsonic && cp Upsonic/*.md ~/.claude/agents/11 items en este repositorio
Use this agent when you need to create unit tests for your code in unittest.TestCase format, organized in a tests folder with concept-based subfolders. Examples: <example>Context: User has just written a new authentication module and needs comprehensive unit tests. user: 'I just finished writing my user authentication functions in auth.py. Can you help me create unit tests for them?' assistant: 'I'll use the unittest-generator agent to create comprehensive unit tests for your authentication module.' <commentary>Since the user needs unit tests created for their authentication code, use the unittest-generator agent to create properly structured tests in the tests folder with appropriate subfolder organization.</commentary></example> <example>Context: User has implemented new data validation functions and wants to ensure they're properly tested. user: 'I've added several validation functions to my utils.py file. I need unit tests to make sure they handle edge cases correctly.' assistant: 'Let me use the unittest-generator agent to create thorough unit tests for your validation functions.' <commentary>The user needs unit tests for their validation functions, so use the unittest-generator agent to create comprehensive tests with edge case coverage.</commentary></example>
Perform structured code reviews with actionable feedback. Use when a user asks to review code, check code quality, find bugs, audit security, improve performance, or assess maintainability. Trigger when user says things like "review this code", "check for bugs", "is this code secure", "any issues with this", "code quality check", or pastes code asking for feedback. Also trigger for pull request reviews and pre-merge code checks. Do NOT trigger for writing new code from scratch, refactoring requests without review context, or general programming questions.
Analyze, explore, clean, and visualize datasets with statistical rigor. Use when user asks to analyze data, find patterns, compute statistics, create visualizations, clean messy data, or explore a dataset. Trigger when user says things like "analyze this data", "what trends do you see", "find patterns in", "create a chart", "clean this dataset", "run statistics on", "what does this data tell us", or provides CSV/Excel/JSON data for exploration. Also trigger for A/B test analysis, cohort analysis, and data quality assessments. Do NOT trigger for simple data format conversions, database query writing without analysis, or ETL pipeline design.
Summarize documents, articles, conversations, code, and technical content into concise, accurate summaries. Use when user asks to summarize, condense, create a TL;DR, write an executive summary, extract key points, or distill content. Trigger when user says things like "summarize this", "give me the key points", "TL;DR", "what are the main takeaways", "condense this", "brief me on this", or provides long content asking for a shorter version. Also trigger for meeting notes summaries, research paper abstracts, and changelog summaries. Do NOT trigger for rewriting or paraphrasing at similar length, translation, or content generation from scratch.
Resumen de Subagents
<div align="center">
<img width="947" alt="Upsonic_README" src="https://github.com/user-attachments/assets/acb3f413-e4fe-44a6-9aff-40d4e9031188" />
# Upsonic
**Build Autonomous AI Agents in Python**
[](https://badge.fury.io/py/upsonic)
[](LICENCE)
[](https://pypi.org/project/upsonic/)
[](https://github.com/Upsonic/Upsonic)
[](https://github.com/Upsonic/Upsonic/issues)
[](https://docs.upsonic.ai)
[](https://discord.gg/pmYDMSQHqY)
[Documentation](https://docs.upsonic.ai) • [Quickstart](https://docs.upsonic.ai/get-started/quickstart) • [Examples](https://docs.upsonic.ai/examples) • [Discord](https://discord.gg/pmYDMSQHqY)
</div>
---
## Overview
Upsonic is a Python framework for building autonomous agents like OpenClaw and Claude Cowork, as well as more traditional agent systems.
## Quick Start
### Installation
```bash
uv pip install upsonic
# pip install upsonic
```
### IDE Integration
Add Upsonic docs as a source in your coding tools:
**Cursor:** Settings → Indexing & Docs → Add `https://docs.upsonic.ai/llms-full.txt`
Also works with VSCode, Windsurf, and similar tools.
---
## Create Autonomous Agent
### Build Your Own
```python
from upsonic import AutonomousAgent, Task
agent = AutonomousAgent(
model="anthropic/claude-sonnet-4-5",
workspace="/path/to/logs"
)
task = Task("Analyze server logs and detect anomaly patterns")
agent.print_do(task)
```
All file and shell operations are restricted to `workspace`. Path traversal and dangerous commands are blocked.
### Use Our Prebuilt Ones
Prebuilt autonomous agents are ready-to-run agents built by the Upsonic community, each packaging a skill, system prompt, and first message so you can go from install to running in seconds. The collection is [open to contributions](https://github.com/Upsonic/Upsonic/tree/master/src/upsonic/prebuilt), bring your agent and open a PR.
Learn more: [Prebuilt Autonomous Agents](https://docs.upsonic.ai/concepts/prebuilt-autonomous-agents/overview)
> **Next steps:** Connect a [Sandbox Provider (E2B)](https://docs.upsonic.ai/concepts/autonomous-agent/overview) for isolated cloud execution environments.
---
## Create Traditional Agent
```python
from upsonic import Agent, Task
agent = Agent(model="anthropic/claude-sonnet-4-5", name="Stock Analyst Agent")
task = Task(description="Analyze the current market trends")
agent.print_do(task)
```
### Add Custom Tools
```python
from upsonic import Agent, Task
from upsonic.tools import tool
@tool
def sum_tool(a: float, b: float) -> float:
"""
Add two numbers together.
Args:
a: First number
b: Second number
Returns:
The sum of a and b
"""
return a + b
task = Task(
description="Calculate 15 + 27",
tools=[sum_tool]
)
agent = Agent(model="anthropic/claude-sonnet-4-5", name="Calculator Agent")
result = agent.print_do(task)
```
> **Next steps:** Integrate [MCP Tools](https://docs.upsonic.ai/concepts/tools/mcp-tools/overview) to connect your agents to thousands of external data sources and services.
---
## OCR and Document Processing
Upsonic provides a unified OCR interface with a layered pipeline: Layer 0 handles document preparation (PDF to image conversion, preprocessing), Layer 1 runs the OCR engine.
```bash
uv pip install "upsonic[ocr]"
```
```python
from upsonic.ocr import OCR
from upsonic.ocr.layer_1.engines import EasyOCREngine
engine = EasyOCREngine(languages=["en"])
ocr = OCR(layer_1_ocr_engine=engine)
text = ocr.get_text("invoice.pdf")
print(text)
```
Supported engines: EasyOCR, RapidOCR, Tesseract, PaddleOCR, DeepSeek OCR, DeepSeek via Ollama.
Learn more: [OCR Documentation](https://docs.upsonic.ai/concepts/ocr/overview)
---
## Check Our Videos
<table>
<tr>
<td align="center">
<a href="https://www.youtube.com/watch?v=GOYko0KfBtg">
<img src="https://img.youtube.com/vi/GOYko0KfBtg/maxresdefault.jpg" width="400" alt="Upsonic Demo Video 1"/>
</a>
</td>
<td align="center">
<a href="https://www.youtube.com/watch?v=ulUEFIolesQ">
<img src="https://img.youtube.com/vi/ulUEFIolesQ/maxresdefault.jpg" width="400" alt="Upsonic Demo Video 2"/>
</a>
</td>
</tr>
</table>
---
## Documentation and Resources
- **[Documentation](https://docs.upsonic.ai)** - Complete guides and API reference
- **[Quickstart Guide](https://docs.upsonic.ai/get-started/quickstart)** - Get started in 5 minutes
- **[Examples](https://docs.upsonic.ai/examples)** - Real-world examples and use cases
- **[API Reference](https://docs.upsonic.ai/reference)** - Detailed API documentation
## Community and Support
> **💬 [Join our Discord community!](https://discord.gg/pmYDMSQHqY)** — Ask questions, share what you're building, get help from the team, and connect with other developers using Upsonic.
- **[Discord](https://discord.gg/pmYDMSQHqY)** - Chat with the community and get real-time support
- **[Issue Tracker](https://github.com/Upsonic/Upsonic/issues)** - Report bugs and request features
- **[Changelog](https://docs.upsonic.ai/changelog)** - See what's new in each release
## License
Upsonic is released under the MIT License. See [LICENCE](LICENCE) for details.
## Contributing
We welcome contributions from the community! Please read our [Contributing Guide](CONTRIBUTING.md) and code of conduct before submitting pull requests.Lo que la gente pregunta sobre Upsonic
¿Qué es Upsonic/Upsonic?
+
Upsonic/Upsonic es subagents para el ecosistema de Claude AI. Build autonomous AI agents in Python. Tiene 7.9k estrellas en GitHub y se actualizó por última vez 3d ago.
¿Cómo se instala Upsonic?
+
Puedes instalar Upsonic clonando el repositorio (https://github.com/Upsonic/Upsonic) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar Upsonic/Upsonic?
+
Nuestro agente de seguridad ha analizado Upsonic/Upsonic y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene Upsonic/Upsonic?
+
Upsonic/Upsonic es mantenido por Upsonic. La última actividad registrada en GitHub es de 3d ago, con 25 issues abiertos.
¿Hay alternativas a Upsonic?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega Upsonic en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/upsonic-upsonic)<a href="https://claudewave.com/repo/upsonic-upsonic"><img src="https://claudewave.com/api/badge/upsonic-upsonic" alt="Featured on ClaudeWave: Upsonic/Upsonic" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.