A VSCode extension that leverages local LLMs like Llama 3 and CodeQwen to provide context-aware code generation. It uses FastAPI and Ollama to ensure team insights remain private and portable across development environments.
Tech Stack
PythonAI, ML & Data
Why companion?
• Local code processing
• Team context integration
• Supports multiple OSS LLMs
Limitations
• Requires local GPU
• Setup of Ollama backend
• Inference latency
2/26/2026
Last Update
9
Forks
6
Issues
Apache-2.0
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to companion instantly boosts your runway.
