[GH-ISSUE #67] [Enhancement]: api importing improvements #36

New Issue

2026-06-06T22:08:09-04:00

yindo commented

2026-06-06 22:08:09 -04:00

Originally created by @s-b-repo on GitHub (Oct 25, 2025).
Original GitHub issue: https://github.com/vxcontrol/pentagi/issues/67

Originally assigned to: @asdek on GitHub.

Target Component

Core Services (Frontend UI/Backend API), AI Agents (Researcher/Developer/Executor)

Enhancement Description

could we load a list of apis from a json,csv or txt so we can mass import multiable apis from diffrent and same model so we can use more isntances at one

Technical Details

it would affect desigin and intergration etc

Designs and Mockups

No response

Alternative Solutions

No response

Verification

I have checked that this enhancement hasn't been already proposed
This enhancement aligns with PentAGI's goal of autonomous penetration testing
I have considered the security implications of this enhancement
I have provided clear use cases and benefits

Originally created by @s-b-repo on GitHub (Oct 25, 2025). Original GitHub issue: https://github.com/vxcontrol/pentagi/issues/67 Originally assigned to: @asdek on GitHub. ### Target Component Core Services (Frontend UI/Backend API), AI Agents (Researcher/Developer/Executor) ### Enhancement Description could we load a list of apis from a json,csv or txt so we can mass import multiable apis from diffrent and same model so we can use more isntances at one ### Technical Details it would affect desigin and intergration etc ### Designs and Mockups _No response_ ### Alternative Solutions _No response_ ### Verification - [ ] I have checked that this enhancement hasn't been already proposed - [ ] This enhancement aligns with PentAGI's goal of autonomous penetration testing - [ ] I have considered the security implications of this enhancement - [ ] I have provided clear use cases and benefits

yindo added the enhancement label 2026-06-06 22:08:10 -04:00

yindo closed this issue

2026-06-06 22:08:10 -04:00

yindo commented

2026-06-06 22:08:10 -04:00

@asdek commented on GitHub (Oct 25, 2025):

Hello @s-b-repo,

Thanks for the suggestion! To implement this properly, I need to understand a few things:

What kind of APIs do you want to import? (LLM providers, search engines, etc.)
How would you use this feature? Where in the UI should it be?
If you import multiple instances of the same model, how should PentAGI choose which one to use?

Could you share an example of what you're trying to achieve? This would help me understand exactly what you need

@asdek commented on GitHub (Oct 25, 2025): Hello @s-b-repo, Thanks for the suggestion! To implement this properly, I need to understand a few things: - What kind of APIs do you want to import? (LLM providers, search engines, etc.) - How would you use this feature? Where in the UI should it be? - If you import multiple instances of the same model, how should PentAGI choose which one to use? Could you share an example of what you're trying to achieve? This would help me understand exactly what you need

yindo commented

2026-06-06 22:08:10 -04:00

@s-b-repo commented on GitHub (Oct 26, 2025):

Hello @s-b-repo,

Thanks for the suggestion! To implement this properly, I need to understand a few things:
* What kind of APIs do you want to import? (LLM providers, search engines, etc.)

* How would you use this feature? Where in the UI should it be?

* If you import multiple instances of the same model, how should PentAGI choose which one to use?
Could you share an example of what you're trying to achieve? This would help me understand exactly what you need

like say you have multiable paid istances of chatgpt you want to use or just have a conf for instant configuration when you launch instance in something like docker so you dont have to add the apis everytime

@s-b-repo commented on GitHub (Oct 26, 2025): > Hello [@s-b-repo](https://github.com/s-b-repo), > > Thanks for the suggestion! To implement this properly, I need to understand a few things: > > * What kind of APIs do you want to import? (LLM providers, search engines, etc.) > > * How would you use this feature? Where in the UI should it be? > > * If you import multiple instances of the same model, how should PentAGI choose which one to use? > > > Could you share an example of what you're trying to achieve? This would help me understand exactly what you need like say you have multiable paid istances of chatgpt you want to use or just have a conf for instant configuration when you launch instance in something like docker so you dont have to add the apis everytime

yindo commented

2026-06-06 22:08:10 -04:00

@asdek commented on GitHub (Mar 19, 2026):

hey @s-b-repo

this has actually been solved with PR #185!

we added support for four new providers (Moonshot, Alibaba Cloud, z.ai, DeepSeek), but more importantly we expanded full LiteLLM integration which addresses exactly what you're asking for.

check out this guide:
https://github.com/vxcontrol/pentagi?tab=readme-ov-file#using-litellm-proxy

how it works:

set up LiteLLM once with all your API keys from different providers
create a single unified API key in LiteLLM
configure PentAGI to use that one key

what you get:

major providers (OpenAI, Anthropic, Gemini, AWS Bedrock) work through pass-through mode
other providers use *_PROVIDER variables where PentAGI automatically adds model prefixes
you can have 10+ configured providers in the UI
add LiteLLM as a custom provider to mix models from different cloud LLM providers in a single agent configuration

this means you can configure everything once in your docker environment and never have to re-add APIs. all configuration is in .env file and persists across container restarts.

closing this as resolved since LiteLLM integration covers this use case. let me know if you need help setting it up!

@asdek commented on GitHub (Mar 19, 2026): hey @s-b-repo this has actually been solved with PR #185! we added support for four new providers (Moonshot, Alibaba Cloud, z.ai, DeepSeek), but more importantly we expanded **full LiteLLM integration** which addresses exactly what you're asking for. check out this guide: https://github.com/vxcontrol/pentagi?tab=readme-ov-file#using-litellm-proxy **how it works:** 1. set up LiteLLM once with all your API keys from different providers 2. create a single unified API key in LiteLLM 3. configure PentAGI to use that one key **what you get:** - **major providers** (OpenAI, Anthropic, Gemini, AWS Bedrock) work through pass-through mode - **other providers** use `*_PROVIDER` variables where PentAGI automatically adds model prefixes - you can have 10+ configured providers in the UI - add LiteLLM as a custom provider to mix models from different cloud LLM providers in a single agent configuration this means you can configure everything once in your docker environment and never have to re-add APIs. all configuration is in `.env` file and persists across container restarts. closing this as **resolved** since LiteLLM integration covers this use case. let me know if you need help setting it up!

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: vxcontrol/pentagi#36