Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
openJiuwen agent-core provides a complete set of SDK capabilities related to AI Agent development, running, optimization, and evolution.
| Date | Stars |
|---|---|
| 2026-07-31 | 363 |
| 2026-08-06 | 403 |
| 2026-08-15 | 412 |
| 2026-08-18 | 421 |
| 2026-08-19 | 422 |
| 2026-08-20 | 426 |
| 2026-08-21 | 426 |
| 2026-08-22 | 425 |
| 2026-08-23 | 425 |
| 2026-08-24 | 426 |
| 2026-08-25 | 418 |
| 2026-08-26 | 419 |
| 2026-08-27 | 417 |
| 2026-08-28 | 419 |
| 2026-08-29 | 421 |
| 2026-08-30 | 420 |
| 2026-08-31 | 420 |
| 2026-09-01 | 420 |
| 2026-09-02 | 421 |
| 2026-09-03 | 422 |
| 2026-09-04 | 424 |
| 2026-09-05 | 424 |
| 2026-09-06 | 424 |
| 2026-09-07 | 427 |
| 2026-09-08 | 427 |
| 2026-09-09 | 427 |
| 2026-09-10 | 428 |
| 2026-09-11 | 428 |
| 2026-09-12 | 428 |
| 2026-09-13 | 429 |
| 2026-09-14 | 429 |
| 2026-09-15 | 430 |
| 2026-09-16 | 430 |
| 2026-09-17 | 432 |
| 2026-09-18 | 432 |
| 2026-09-19 | 430 |
| 2026-09-20 | 430 |
| 2026-09-21 | 431 |
| 2026-09-22 | 432 |
| 2026-09-23 | 434 |
| 2026-09-24 | 436 |
| 2026-09-25 | 436 |
| 2026-09-26 | 437 |
| 2026-09-27 | 438 |
| 2026-09-28 | 438 |
| 2026-09-29 | 440 |
| 2026-09-30 | 438 |
| 2026-10-01 | 438 |
| 2026-10-02 | 438 |
| 2026-10-03 | 440 |
| 2026-10-04 | 440 |
| 2026-10-05 | 441 |
| 2026-10-07 | 441 |
| 2026-10-08 | 443 |
| 2026-10-09 | 446 |
| 2026-10-10 | 446 |
| 2026-10-11 | 446 |
| 2026-10-12 | 446 |
| 2026-10-13 | 447 |
| 2026-10-14 | 449 |
| 2026-10-15 | 450 |
| 2026-10-16 | 451 |
| 2026-10-17 | 451 |
| 2026-10-18 | 451 |
| 2026-10-19 | 452 |
| 2026-10-20 | 459 |
| 2026-10-21 | 458 |
| 2026-10-22 | 461 |
| 2026-10-23 | 462 |
| 2026-10-24 | 463 |
| 2026-10-25 | 464 |
| 2026-10-26 | 464 |
| 2026-10-27 | 465 |
| 2026-10-28 | 467 |
| 2026-10-29 | 466 |
| 2026-10-30 | 466 |
| 2026-10-31 | 466 |
| 2026-11-01 | 465 |
| 2026-11-02 | 464 |
| 2026-11-03 | 465 |
| 2026-11-04 | 467 |
Today
+2 stars today
This week
— stars this week
This month
+26 stars this month
Momentum
23.0
growth rate 0.00%/day
# openJiuwen Core
[中文版](README.zh.md) | [English Version](README.md)
## Introduction
**openJiuwen Core** is a Python SDK for large language model applications, providing a high-performance runtime for agents running on the **openJiuwen** framework. This development toolkit not only encapsulates multi-level, easy-to-use external interfaces for Agent creation, workflow orchestration, large language model invocation, and tool calling, but also includes a built-in high-performance runtime supporting asynchronous IO and streaming processing, enabling agent state saving and interruption recovery. Additionally, it comes equipped with a series of agent debugging and optimization tools, including prompt auto-optimization, prompt generation, and full-link observability. The **openJiuwen Core** development toolkit balances flexibility and stability, helping developers efficiently build stable large language model applications.
## Why Choose openJiuwen Core?
- **Ready-to-use Components**: Provides rich pre-built components, including intent recognition, questioners, large language model invocation, tool components, and more, significantly lowering the development threshold.
- **Efficient and Accurate Task Execution**: Built-in high-performance execution engine supports asynchronous parallel graph execution, component concurrency, streaming processing, and other capabilities, ensuring high efficiency and accuracy when agents execute tasks.
- **Flexible and Controllable Multi-Workflow Jump Capability**: Supports agents managing multiple workflows in the same session, allows users to freely switch between different workflows, and ensures checkpoint recovery for interrupted workflows through the framework. This solves the need for users to switch between different task scenarios in the same conversation, providing flexible multi-task management capabilities.
- **Practical Prompt Development and Optimization Capabilities**: Input requirements to generate suitable prompts with one click, combined with real-world scenario datasets for automatic optimization iteration, helping developers quickly produce high-quality prompts and lowering the development threshold for core agent capabilities.
## Quick Start
### Installation
- Operating System: Compatible with Windows, Linux, and macOS.
- Python Version: Python version should be 3.11 or higher, but lower than 3.14. Please check your Python version before use, Python 3.11.4 is recommended.
**Install from PyPI**
```bash
pip install -U openjiuwen
```
### Example
Let's create a simple WorkflowAgent that calls a workflow to generate a piece of text:
```python
import os
import asyncio
from openjiuwen.core.workflow import Start, End, LLMComponent, LLMCompConfig, generate_workflow_key
from openjiuwen.core.foundation.llm import ModelRequestConfig, ModelClientConfig
from openjiuwen.core.runner.runner import Runner
from openjiuwen.core.single_agent.legacy import WorkflowAgentConfig
from openjiuwen.core.application.workflow_agent import WorkflowAgent
from openjiuwen.core.workflow import Workflow, WorkflowCard
# TODO: Please provide your LLM configuration information
os.environ.setdefault("API_BASE", "your_api_base")
os.environ.setdefault("API_KEY", "your_api_key")
os.environ.setdefault("MODEL_PROVIDER", "your_provider")
os.environ.setdefault("MODEL_NAME", "your_model_name")
os.environ.setdefault("LLM_SSL_VERIFY", "false")
# Create LLM configuration object
model_client_config = ModelClientConfig(
client_provider=os.getenv("MODEL_PROVIDER"),
api_key=os.getenv("API_KEY"),
api_base=os.getenv("API_BASE"),
verify_ssl=os.getenv("LLM_SSL_VERIFY").lower() == "true"
)
model_config = ModelRequestConfig(
model=os.getenv("MODEL_NAME")
)
# Create workflow configuration
workflow_card = WorkflowCard(
id="generate_text_workflow",
name="generate_text",
version="1.0",
description="Generate text based on user input",
input_params={
"type": "object",
Excerpt of 9,968 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e2bad25f13471ebf, llm:Repository description: 'openJiuwen agent-core provides a complete set of SDK capabilities related to AI Agent development, running, optimization, and evolution.' Language: Python. No topics provided.
matched fp:e2bad25f13471ebf, llm:Repository description: 'openJiuwen agent-core provides a complete set of SDK capabilities related to AI Agent development, running, optimization, and evolution.' Language: Python. No topics provided.
matched fp:e2bad25f13471ebf, llm:Repository description: 'openJiuwen agent-core provides a complete set of SDK capabilities related to AI Agent development, running, optimization, and evolution.' Language: Python. No topics provided.