Most coding tasks only depend on a small part of a repository, but an AI coding agent can end up reading a lot of unrelated code. That means more tokens, higher API cost, more latency, and potentially more irrelevant context for the model.
Faber is an open-source AI coding agent for the terminal that uses a code graph to find relevant files and symbols before loading context. It reduces unnecessary context and repeated API cost through code-graph-guided search, prompt caching, and concise output. It supports Claude, OpenAI Codex, and local models, plus Git-aware workflows, undo/redo, memory, and detailed token and cost tracking.
