tcsenpai/agenticSeek
1
0
Fork 0
mirror of https://github.com/tcsenpai/agenticSeek.git synced 2025-06-06 11:05:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Martin 2025-04-15 19:30:45 +02:00 committed by GitHub
parent aad1b426f0
commit 83e93dcf43
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
README.md
View File

@ -10,7 +10,7 @@ English | [中文](./README_CHS.md) | [繁體中文](./README_CHT.md) | [Franç
**A fully local alternative to Manus AI**, a voice-enabled AI assistant that codes, explores your filesystem, browse the web and correct it's mistakes all without sending a byte of data to the cloud. Built with reasoning models like DeepSeek R1, this autonomous agent runs entirely on your hardware, keeping your data private. **A fully local alternative to Manus AI**, a voice-enabled AI assistant that codes, explores your filesystem, browse the web and correct it's mistakes all without sending a byte of data to the cloud. Built with reasoning models like DeepSeek R1, this autonomous agent runs entirely on your hardware, keeping your data private.
[![Visit AgenticSeek](https://img.shields.io/static/v1?label=Website&message=AgenticSeek&color=blue&style=flat-square)](https://fosowl.github.io/agenticSeek.html) ![License](https://img.shields.io/badge/license-GPL--3.0-green) [![Discord](https://img.shields.io/badge/Discord-Join%20Us-7289DA?logo=discord&logoColor=white)](https://discord.gg/4Ub2D6Fj) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/fosowl.svg?style=social&label=Update%20%40Fosowl)](https://x.com/Martin993886460) [![Visit AgenticSeek](https://img.shields.io/static/v1?label=Website&message=AgenticSeek&color=blue&style=flat-square)](https://fosowl.github.io/agenticSeek.html) ![License](https://img.shields.io/badge/license-GPL--3.0-green) [![Discord](https://img.shields.io/badge/Discord-Join%20Us-7289DA?logo=discord&logoColor=white)](https://discord.gg/XSTKZ8nP) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/fosowl.svg?style=social&label=Update%20%40Fosowl)](https://x.com/Martin993886460)
> 🛠️ **Work in Progress** – Looking for contributors! > 🛠️ **Work in Progress** – Looking for contributors!
@ -211,7 +211,8 @@ If you have a powerful computer or a server that you can use, but you want to us
On your "server" that will run the AI model, get the ip address On your "server" that will run the AI model, get the ip address
```sh ```sh
ip a | grep "inet " | grep -v 127.0.0.1 | awk '{print $2}' | cut -d/ -f1 ip a | grep "inet " | grep -v 127.0.0.1 | awk '{print $2}' | cut -d/ -f1 # local ip
curl https://ipinfo.io/ip # public ip
``` ```
Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP address. Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP address.
@ -244,14 +245,14 @@ You have the choice between using `ollama` and `llamacpp` as a LLM service.
Now on your personal computer: Now on your personal computer:
Change the `config.ini` file to set the `provider_name` to `server` and `provider_model` to `deepseek-r1:14b`. Change the `config.ini` file to set the `provider_name` to `server` and `provider_model` to `deepseek-r1:xxb`.
Set the `provider_server_address` to the ip address of the machine that will run the model. Set the `provider_server_address` to the ip address of the machine that will run the model.
```sh ```sh
[MAIN] [MAIN]
is_local = False is_local = False
provider_name = server provider_name = server
provider_model = deepseek-r1:14b provider_model = deepseek-r1:70b
provider_server_address = x.x.x.x:3333 provider_server_address = x.x.x.x:3333
``` ```
@ -264,14 +265,16 @@ python3 main.py
## **Run with an API** ## **Run with an API**
Set the desired provider in the `config.ini` Set the desired provider in the `config.ini`.
We recommand together AI if you want to use Qwen/Deepseek-r1. openai or other API work as well.
```sh ```sh
[MAIN] [MAIN]
is_local = False is_local = False
provider_name = openai provider_name = together
provider_model = gpt-4o provider_model = deepseek-ai/DeepSeek-R1-Distill-Llama-70B
provider_server_address = 127.0.0.1:5000 provider_server_address = 127.0.0.1:5000 # doesn't matter for non local API provider
``` ```
WARNING: Make sure there is not trailing space in the config. WARNING: Make sure there is not trailing space in the config.
@ -368,9 +371,9 @@ The table below show the available providers:
To select a provider change the config.ini: To select a provider change the config.ini:
``` ```
is_local = False is_local = True
provider_name = openai provider_name = ollama
provider_model = gpt-4o provider_model = deepseek-r1:32b
provider_server_address = 127.0.0.1:5000 provider_server_address = 127.0.0.1:5000
``` ```
`is_local`: should be True for any locally running LLM, otherwise False. `is_local`: should be True for any locally running LLM, otherwise False.
@ -415,7 +418,7 @@ If this section is incomplete please raise an issue.
| 7B | 8GB Vram | ⚠️ Not recommended. Performance is poor, frequent hallucinations, and planner agents will likely fail. | | 7B | 8GB Vram | ⚠️ Not recommended. Performance is poor, frequent hallucinations, and planner agents will likely fail. |
| 14B | 12 GB VRAM (e.g. RTX 3060) | ✅ Usable for simple tasks. May struggle with web browsing and planning tasks. | | 14B | 12 GB VRAM (e.g. RTX 3060) | ✅ Usable for simple tasks. May struggle with web browsing and planning tasks. |
| 32B | 24+ GB VRAM (e.g. RTX 4090) | 🚀 Success with most tasks, might still struggle with task planning | | 32B | 24+ GB VRAM (e.g. RTX 4090) | 🚀 Success with most tasks, might still struggle with task planning |
| 70B+ | 48+ GB Vram (eg. rtx 4090) | 💪 Excellent. Recommended for advanced use cases. | | 70B+ | 48+ GB Vram (eg. mac studio) | 💪 Excellent. Recommended for advanced use cases. |
**Q: Why Deepseek R1 over other models?** **Q: Why Deepseek R1 over other models?**
@ -423,11 +426,11 @@ Deepseek R1 excels at reasoning and tool use for its size. We think it’s a sol
**Q: I get an error running `main.py`. What do I do?** **Q: I get an error running `main.py`. What do I do?**
Ensure Ollama is running (`ollama serve`), your `config.ini` matches your provider, and dependencies are installed. If none work feel free to raise an issue. Ensure local is running (`ollama serve`), your `config.ini` matches your provider, and dependencies are installed. If none work feel free to raise an issue.
**Q: Can it really run 100% locally?** **Q: Can it really run 100% locally?**
Yes with Ollama or Server providers, all speech to text, LLM and text to speech model run locally. Non-local options (OpenAI or others API) are optional. Yes with Ollama, lm-studio or server providers, all speech to text, LLM and text to speech model run locally. Non-local options (OpenAI or others API) are optional.
**Q: Why should I use AgenticSeek when I have Manus?** **Q: Why should I use AgenticSeek when I have Manus?**