mpaepper/llm_agents 排名第 5,882，有 1,059 个星标。
同类别比较
mpaepper/llm_agents 排名第 5,882，此处有 8 个同类条目；microsoft/lets-learn-mcp-python 排名第 5,873。
同类别比较| 名称 | 排名 | 指标 |
|---|
| LangChain-OpenTutorial/LangChain-OpenTutorial | 5,838 | - 语言:
- Jupyter Notebook
- 星标数:
- 1,117
- 分叉数:
- 347
- 简介:
- LangChain, LangGraph Open Tutorial for everyone!
|
|---|
| Ma-Lab-Berkeley/deep-representation-learning-book | 5,849 | - 语言:
- TeX
- 星标数:
- 1,097
- 分叉数:
- 118
- 简介:
- Learning Deep Representations of Data Distributions
|
|---|
| KalyanKS-NLP/LLM-Interview-Questions-and-Answers-Hub | 5,861 | - 星标数:
- 1,082
- 分叉数:
- 174
- 简介:
- 100+ LLM interview questions with answers.
|
|---|
| microsoft/lets-learn-mcp-python | 5,873 | - 语言:
- Python
- 星标数:
- 1,070
- 分叉数:
- 198
- 简介:
- MCP Python Tutorial
|
|---|
| PacktPublishing/Deep-Learning-with-Keras | 5,894 | - 语言:
- Jupyter Notebook
- 星标数:
- 1,048
- 分叉数:
- 697
- 简介:
- Code repository for Deep Learning with Keras published by Packt
|
|---|
| mryab/efficient-dl-systems | 5,899 | - 语言:
- Jupyter Notebook
- 星标数:
- 1,042
- 分叉数:
- 151
- 简介:
- Efficient Deep Learning Systems course materials
|
|---|
| junfanz1/Awesome-Senior-Engineer-Algorithms-Review | 5,911 | - 星标数:
- 1,032
- 分叉数:
- 263
- 简介:
- Data Structure Algorithms, (GenAI/ML) System Design, Machine Learning, DevOps coding interview practices
|
|---|
| datawhalechina/machine-learning-toy-code | 5,917 | - 语言:
- Jupyter Notebook
- 星标数:
- 1,025
- 分叉数:
- 200
- 简介:
- 《机器学习》（西瓜书）代码实战
|
|---|
关键参数与规格
关键参数与规格| 参数 | 值 |
|---|
| 语言 | Python |
|---|
| 类别 | Tutorials |
|---|
| 星标数 | 1,059 |
|---|
| 分叉数 | 85 |
|---|
| 贡献者 | 4 |
|---|
| 创建日期 | 2023-04-04 |
|---|
| 更新日期 | 2026-10-16 |
|---|
| 1 天星标数 | 1 |
|---|
| 7 天星标数 | 2 |
|---|
| 排名 | 5,882 |
|---|
| 上次排名 | 11,757 |
|---|
| 排名变化 | 5,875 |
|---|
| 7 天星标排名 | 8,268 |
|---|
| 上次 7 天星标排名 | 7,116 |
|---|
| 7 天星标排名变化 | -1,152 |
|---|
| 总星标排名 | 10,675 |
|---|
| 上次总星标排名 | 10,674 |
|---|
| 总星标排名变化 | -1 |
|---|
| 国家 | Germany |
|---|
README 摘录
LLM Agents Small library to build agents which are controlled by large language models (LLMs) which is heavily inspired by langchain . The goal was to get a better grasp of how such an agent works and understand it all in very few lines of code. Langchain is great, but it already has a few more files and abstraction layers, so I thought it would be nice to build the most important parts of a simple agent from scratch. Some more
infos are in this Hacker News discussion from April 5th 2023 and the related blog post . How it works The agent works like this: It gets instructed by a prompt which tells it the basic way to solve a task using tools Tools are custom build components which the agent can use The agent runs in a loop of Thought, Action, Observation, Thought, . The LLM gets the new information appended to the prompt in each loop cycle and thus can
act on that information Once the agent has enough information it provides the final answer For more details on how it works, check out this blog post How to use it You can install this library locally by running: inside it's directory after cloning it. You also need to provide the following env variables: to use the OpenAI API (obtainable at: to use the Google Search in case you use that tool (obtainable at: You can simply export them in
bash like: Then you can run the script and ask your question. To construct your own agent do it like this: Of course, you can also build your custom tools or omit tools, for exmaple if you don't want to create a SERPAPI key.
常见问题
记录了多少星标和分叉？
mpaepper/llm_agents 有 1,059 个星标和 85 个分叉。
仓库排名是多少？
mpaepper/llm_agents 排名第 5,882。
记录的语言和类别是什么？
mpaepper/llm_agents 有 1,059 个星标，语言为 Python，类别为 Tutorials。
哪个仓库排名最接近？
mpaepper/llm_agents 与 microsoft/lets-learn-mcp-python 比较，后者排名第 5,873，有 1,070 个星标。
LLM Agents
Small library to build agents which are controlled by large language models (LLMs) which is heavily inspired by langchain.
The goal was to get a better grasp of how such an agent works and understand it all in very few lines of code.
Langchain is great, but it already has a few more files and abstraction layers, so I thought it would be nice to build the most important parts of a simple agent from scratch.
Some more infos are in this Hacker News discussion from April 5th 2023 and the related blog post.
How it works
The agent works like this:
- It gets instructed by a prompt which tells it the basic way to solve a task using tools
- Tools are custom build components which the agent can use
- So far, I've implemented the ability to execute Python code in a REPL, to use the Google search and to search on Hacker News
- The agent runs in a loop of Thought, Action, Observation, Thought, ...
- The Thought and Action (with the Action Input to the action) are the parts which are generated by an LLM
- The Observation is generated by using a tool (for example the print outputs of Python or the text result of a Google search)
- The LLM gets the new information appended to the prompt in each loop cycle and thus can act on that information
- Once the agent has enough information it provides the final answer
For more details on how it works, check out this blog post
How to use it
You can install this library locally by running:
pip install -r requirements.txt
pip install -e .
inside it's directory after cloning it.
You also need to provide the following env variables:
You can simply export them in bash like: export OPENAI_API_KEY='sh-lsdf....'
Then you can run the script python run_agent.py and ask your question.
To construct your own agent do it like this:
from llm_agents import Agent, ChatLLM, PythonREPLTool, HackerNewsSearchTool, SerpAPITool
agent = Agent(llm=ChatLLM(), tools=[PythonREPLTool(), SerpAPITool(), HackerNewsSearchTool()])
result = agent.run("Your question to the agent")
print(f"Final answer is {result}")
Of course, you can also build your custom tools or omit tools, for exmaple if you don't want to create a SERPAPI key.