ClariLayer

A memory, docs, and repo context layer for engineering agents, providing typed persistent memory, RAG document retrieval, and repository-aware tools to recall decisions, runbooks, and operational knowledge across sessions.

Enables AI coding agents to keep durable project memory across sessions and retrieve token-budgeted context packs, so they can recall decisions, gotchas, and TODOs and locate relevant code without rereading entire repositories.

Provides a unified context system for AI coding agents with memory, knowledge graph, specs, and code graph subsystems, all stored in SQLite. Enables persistent recall of decisions, conventions, errors, project knowledge, and code structure.

Gives AI coding agents on-demand retrieval of workspace context, documentation, lessons, decisions and handoffs from a five-level (GLOBAL → WORKSPACE → PROJECT → FEATURE → SESSION) store, so they start with a small rule set instead of re-reading bloated docs. Exposes tools for dependency routing, knowledge search, doc reading and health checks backed by a zero-dependency SQLite + FTS5 memory with cross-project sharing of global-scoped knowledge.