A standalone Rust memory engine for AI coding assistants. Single binary, zero runtime deps. Graph-vector hybrid with MCP tools.
Agent
Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.
Agent
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
Agent
Wave 1 agent: creates baseline context memories for batches of source files and packages. Produces 1 memory per file + 1 per package, linked with PARTOF edges.
Agent
Maps a codebase using team-based deep analysis with priority-driven agent assignments. Use after initial project setup, when pending-analysis memories appear, or periodically to refresh the knowledge graph.
Agent
Wave 2 agent: discovers cross-file patterns within Louvain clusters. Identifies naming conventions, shared structures, and recurring approaches. Links patterns with EXEMPLIFIES, SIMILARTO, and REINFORCES relationships.
Agent
Wave 3 agent: analyzes authentication, authorization, input validation, and trust boundaries. Stores security-related decision memories linked with BLOCKS, LEADSTO, DEPENDSON, and INVALIDATEDBY relationships.
Agent
Wave 2 agent: performs deep analysis of critical and important symbols. Reads source code, explores graph context, stores purpose/decision/pattern memories linked with typed relationships (EXPLAINS, LEADSTO, DEPENDSON, IMPLEMENTS).
Agent
Wave 3 agent: documents testing patterns, test organization, coverage gaps, and testing conventions across the codebase. Links test memories with EXPLAINS, EXEMPLIFIES, DEPENDSON, and SIMILARTO relationships.