vxcontrol/pentagi
1
0
Fork 0
mirror of https://github.com/vxcontrol/pentagi.git synced 2026-07-20 12:37:04 -04:00
Code Issues 45 Packages Projects Releases 9 Wiki Activity

[GH-ISSUE #14] [Enhancement]: Please add OpenRouter connection #7

New Issue
Closed
opened 2026-06-06 22:07:54 -04:00 by yindo · 1 comment
yindo commented 2026-06-06 22:07:54 -04:00
Owner
Copy Link
Copy Source

Originally created by @iain0901 on GitHub (Mar 20, 2025).
Original GitHub issue: https://github.com/vxcontrol/pentagi/issues/14

Originally assigned to: @asdek on GitHub.

Target Component

Core Services (Frontend UI/Backend API)

Enhancement Description

There are many models on OpenRouter and can accept many context lengths

Technical Details

No response

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 @iain0901 on GitHub (Mar 20, 2025). Original GitHub issue: https://github.com/vxcontrol/pentagi/issues/14 Originally assigned to: @asdek on GitHub. ### Target Component Core Services (Frontend UI/Backend API) ### Enhancement Description There are many models on OpenRouter and can accept many context lengths ### Technical Details _No response_ ### Designs and Mockups _No response_ ### Alternative Solutions _No response_ ### Verification - [x] I have checked that this enhancement hasn't been already proposed - [x] This enhancement aligns with PentAGI's goal of autonomous penetration testing - [x] I have considered the security implications of this enhancement - [x] I have provided clear use cases and benefits
yindo added the enhancementhelp wanted labels 2026-06-06 22:07:54 -04:00
yindo closed this issue 2026-06-06 22:07:54 -04:00
yindo commented 2026-06-06 22:07:54 -04:00
Author
Owner
Copy Link
Copy Source

@asdek commented on GitHub (Mar 24, 2025):

Hi @iain0901,

thank you for your question, PentAGI has already supported OpenRouter and DeepInfra at least.

Using OpenRouter

  1. Configure your .env file with the following settings:

    LLM_SERVER_URL=https://openrouter.ai/api/v1
LLM_SERVER_KEY=your_api_key
LLM_SERVER_MODEL=
LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml

  2. Run the ctester utility with the pre-configured OpenRouter provider file:

    docker run --rm \
  -v $(pwd)/.env:/opt/pentagi/.env \
  vxcontrol/pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/openrouter.provider.yml -verbose

Using Deep Infra

  1. Configure your .env file with the following settings:

    LLM_SERVER_URL=https://api.deepinfra.com/v1/openai
LLM_SERVER_KEY=your_api_key
LLM_SERVER_MODEL=
LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/deepinfra.provider.yml

  2. Run the ctester utility with the pre-configured Deep Infra provider file:

    docker run --rm \
  -v $(pwd)/.env:/opt/pentagi/.env \
  vxcontrol/pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/deepinfra.provider.yml -verbose

Customizing Models and Context Lengths

You can customize provider configurations to test specific models with various context lengths. For example:

simple:
  model: "openai/gpt-4o"
  temperature: 0.7
  max_tokens: 4000

agent:
  model: "anthropic/claude-3.7-sonnet"
  temperature: 0.1
  max_tokens: 8000

# other agents

Testing Workflow

  1. Run baseline tests with the default configuration.
  2. Experiment with different models for each agent type.
  3. Compare results by examining success rates and latencies.
  4. Deploy the optimal configuration in your production environment.

For more detailed instructions, please refer to the Testing LLM Agents section in our README or you can see #17

Notes: both files /opt/pentagi/conf/deepinfra.provider.yml and /opt/pentagi/conf/openrouter.provider.yml are available in original the latest docker image vxcontrol/pentagi

In additional you could check reports for these providers in the repo:

<!-- gh-comment-id:2747689465 --> @asdek commented on GitHub (Mar 24, 2025): Hi @iain0901, thank you for your question, PentAGI has already supported OpenRouter and DeepInfra at least. ### Using OpenRouter 1. **Configure your `.env` file** with the following settings: ``` LLM_SERVER_URL=https://openrouter.ai/api/v1 LLM_SERVER_KEY=your_api_key LLM_SERVER_MODEL= LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml ``` 2. **Run the `ctester` utility** with the pre-configured OpenRouter provider file: ```bash docker run --rm \ -v $(pwd)/.env:/opt/pentagi/.env \ vxcontrol/pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/openrouter.provider.yml -verbose ``` ### Using Deep Infra 1. **Configure your `.env` file** with the following settings: ``` LLM_SERVER_URL=https://api.deepinfra.com/v1/openai LLM_SERVER_KEY=your_api_key LLM_SERVER_MODEL= LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/deepinfra.provider.yml ``` 2. **Run the `ctester` utility** with the pre-configured Deep Infra provider file: ```bash docker run --rm \ -v $(pwd)/.env:/opt/pentagi/.env \ vxcontrol/pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/deepinfra.provider.yml -verbose ``` ### Customizing Models and Context Lengths You can customize provider configurations to test specific models with various context lengths. For example: ```yaml simple: model: "openai/gpt-4o" temperature: 0.7 max_tokens: 4000 agent: model: "anthropic/claude-3.7-sonnet" temperature: 0.1 max_tokens: 8000 # other agents ``` ### Testing Workflow 1. **Run baseline tests** with the default configuration. 2. **Experiment with different models** for each agent type. 3. **Compare results** by examining success rates and latencies. 4. **Deploy the optimal configuration** in your production environment. For more detailed instructions, please refer to the [Testing LLM Agents](https://github.com/vxcontrol/pentagi#-testing-llm-agents) section in our README or you can see #17 Notes: both files [/opt/pentagi/conf/deepinfra.provider.yml](https://github.com/vxcontrol/pentagi/blob/master/examples/configs/deepinfra.provider.yml) and [/opt/pentagi/conf/openrouter.provider.yml](https://github.com/vxcontrol/pentagi/blob/master/examples/configs/openrouter.provider.yml) are available in original the latest docker image `vxcontrol/pentagi` In additional you could check reports for these providers in the repo: * [Deep Infra](https://github.com/vxcontrol/pentagi/blob/master/examples/tests/deepinfra-report.md) * [OpenRouter](https://github.com/vxcontrol/pentagi/blob/master/examples/tests/openrouter-report.md)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
enhancement
help wanted
pull-request
Mirrored from GitHub Pull Request
 question
No Label enhancement help wanted
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: vxcontrol/pentagi#7
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?