Main
Keep it local-first: pair a local LLM with IDE context to avoid sending sensitive code to third-party APIs when not needed.
Use the security tools as guardrails: run gitleaks/opengrep/trivy during review to catch common issues early.
Define a repeatable workflow: e.g., generate → test → scan → refactor, rather than free-form prompting inside the IDE.
Document model/runtime requirements for your team so plugin behavior is consistent across machines.
README (excerpt)
DevoxxGenie
Devoxx Genie is a fully Java-based LLM Code Assistant plugin for IntelliJ IDEA, designed to integrate with local LLM providers such as Ollama, LMStudio, GPT4All, Llama.cpp and Exo but also cloud based LLM's such as OpenAI, Anthropic, Mistral, Groq, Gemini, DeepInfra, DeepSeek, Kimi, GLM, OpenRouter, Azure OpenAI and Amazon Bedrock
🆕 Security Scanning — Run Gitleaks (secret detection), OpenGrep (SAST) and Trivy (dependency CVEs) directly from the LLM agent. Findings are automatically created as prioritised tasks in the Spec Browser for tracking and remediation!
🆕 Spec Driven Development (SDD) — Define tasks in Backlog.md, browse them in the Spec Browser with Task List and Kanban Board views, then let the Agent implement them autonomously! Use the Agent Loop to run multiple tasks in a single batch with dependency ordering and automatic advancement.
🆕 AI-powered Inline Code Completion — Get context-aware code suggestions as you type using Fill-in-the-Middle (FIM) models via Ollama or LM Studio!
Source-backed notes
- README includes a table listing tools like Gitleaks/OpenGrep/Trivy with example
brew install ...commands. - Repo is MIT licensed and recently pushed (verified via GitHub API).
- The project is an IntelliJ IDEA plugin per repository naming and README framing.
FAQ
- Do I need Homebrew?: Only if you want the optional security tools; the plugin itself installs via IntelliJ.
- Is it open source?: Yes—MIT licensed (verified via GitHub API).
- What are the tools for?: README lists gitleaks/opengrep/trivy for secrets/SAST/dependency scanning workflows.