strix
strix copied to clipboard
usestrix
Open-source AI agents for penetration testing
I have fixed the **RuntimeError: dictionary changed size during iteration in tui.py**. The issue was caused by the UI thread iterating over tool_executions while the background agent thread was updating...
### Summary Strix works correctly with **Azure OpenAI** when using Azure’s **OpenAI-compatible API** (`/openai/v1`), but this is currently undocumented and non-obvious for users. This issue proposes documenting the correct configuration...
**I Need a flag that will let Strix work with non vision LLMs** i run all AI agents using the OpenRouter's free models to save costs since agents do use...
Issue link: https://github.com/usestrix/strix/issues/187 ### Support for non vision models adding this flag _STRIX_DISABLE_IMAGES_ to allow strix to run on LLM's that do not support images as input **Problem:** most cheaper...
### This resolves #164 By detecting macOS by falling back on docker.from_env() if no macOS socket is found. On macOS, Docker Desktop exposes its socket at non-standard paths (~/.docker/run/docker.sock and...
### Summary This PR fixes Issue #164 where Strix fails to detect Docker on macOS even when Docker Desktop is running. `docker.from_env()` only checks Linux-style sockets and does not detect...
Hello, I hope you are well This template, like the previous ones, was created for the SSTI bug.
Our current Playwright-based browser layer effectively requires vision/screenshot reasoning. Non-vision LLMs can’t interact with the browser today. Motivations: Non‑vision model support: Browser Use exposes browser control via higher‑level APIs designed...
