ArgosBrain
argosbrain.comStop your AI coding agent from forgetting your codebase.
Dev Toolsai-codingmcpcode-memoryllm-agentsruststatic-analysiscontext-window
About
ArgosBrain is a local, deterministic memory layer for AI coding agents like Claude Code, Cursor, Codex CLI, and GitHub Copilot. It parses a codebase into a structural graph using Tree-sitter and SCIP, enabling agents to query symbols, callers, and imports via MCP in sub-millisecond time at zero token cost. By eliminating redundant file re-reads, it claims to reduce agent token usage by up to 94% and extend AI budget runway significantly.
Problem
AI coding agents repeatedly re-read the same codebase files every session, wasting tokens and budget while still missing symbols and making errors.
For
Software developers and AI engineering teams using AI coding agents like Claude Code, Cursor, or Codex CLI
How it works
A local Rust binary indexes the codebase into a structural graph via Tree-sitter and SCIP, then exposes MCP tools so any compatible AI agent can query symbols, callers, and call graphs in sub-millisecond time without loading files into context.
Business model
freemium
Status
launched