qualixar/superlocalmemory

SLM Cache stores repeated file reads, search results, and tool output behind stable keys. Use it to check for a hit first, then fill on miss; it fails open on errors and never blocks the task.

SLM Governance defines role-based behavior for SuperLocalMemory in governed workspaces. It covers retention policies, audit trails, GDPR export and erasure, and when agents may read or write under admin, member, or viewer access.

SLM Graph indexes a codebase as a structural graph and answers questions about callers, callees, inheritance, blast radius, and semantic code search. Use it to understand how code connects, what changes may break, and to assemble review context.

SLM Loop runs bounded, gate-verified iterations using SuperLocalMemory as a durable ledger. Use it for tasks with a checkable acceptance condition, and report the exact terminal status when the independent gate passes or a bound stops the run.

SLM Mesh lets multiple AI agent sessions on the same machine discover each other, share transient state, send messages, and lock files to avoid conflicts. Use it when coordinating parallel work across sessions via MCP.

SLM Profile isolates memory into separate workspaces and lets you switch the active MCP tool tier at runtime. Use it when working across distinct projects, clients, or environments and check the current profile with slm status.

SLM Profile isolates memory, code graphs, and tools into separate profiles. Use it when switching between projects, clients, or environments, and check the active profile with slm status.

SLM Recall searches SuperLocalMemory for facts, decisions, and prior context. Use it when you need to find what was said or decided, and before storing new memory to avoid duplicates.

SLM Scope controls memory visibility across profiles as personal, shared, or global. Use it when a user explicitly asks to store or recall facts across workspaces on the same machine.

SLM Session manages SuperLocalMemory session lifecycle. Use session_init at the start of a fresh session to load context and get a session_id, then close_session when work is done to write temporal summaries.

SLM Status reports SuperLocalMemory health, optimization counters, and system state. Use it to verify compression and cache savings, check the active profile, and run preflight diagnostics with doctor output.

Slm Graph indexes a codebase as a structural graph and answers questions about callers, callees, inheritance, and change impact. Use it to navigate unfamiliar code, assemble review context, and check what changed since the last index.

Slm Remember captures durable facts, decisions, constraints, and gotchas into SuperLocalMemory. Use it when you need to persist a conclusion across sessions and recall first to avoid duplicates.

SuperLocalMemory stores, searches, and manages AI agent memories in a local data root. It is used when you need persistent memory with JSON CLI output, MCP access, and optional networked features kept separate.

SuperLocalMemory Compress reduces large text, tool output, or transcripts to save context space, with optional reversible storage for later recovery. Use it when session content is getting too large; if compression fails, continue with the original text.