Audience
Software engineering teams seeking a tool to harness AI assistants effectively without sacrificing correctness or context awareness
About Brokk
Brokk is an AI-native code assistant built to handle large, complex codebases by giving language models compiler-grade understanding of code structure, semantics, and dependencies. It enables context management by selectively loading summaries, diffs, or full files into a workspace so that the AI sees just the relevant portions of a million-line codebase rather than everything. Brokk supports actions such as Quick Context, which suggests files to include based on embeddings and structural relevance; Deep Scan, which uses more powerful models to recommend which files to edit or summarize further; and Agentic Search, allowing multi-step exploration of symbols, call graphs, or usages across the project. The architecture is grounded in static analysis via Joern (offering type inference beyond simple ASTs) and uses JLama for fast embedding inference to guide context changes. Brokk is offered as a standalone Java application (not an IDE plugin) to let users supervise AI workflows clearly.