SLM Loop

SLM Loop is an AI Engineering skill for Claude Code, published by qualixar in superlocalmemory.

223 stars34 forkson qualixar/superlocalmemoryAdded 2026/09/03Repository updated 2026/09/03

agent-memoryagent-reliabilityai-agentsclaude-codecursorknowledge-graphllm-memorylocal-firstmcpmcp-serverpersistent-memoryqualixarsemantic-searchvector-searchwindsurf

Install in seconds

Install SLM Loop

Copy SLM Loop into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/qualixar/superlocalmemory/tree/main/antigravity-plugin/skills/slm-loop ~/.claude/skills/slm-loop

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/qualixar/superlocalmemory.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: antigravity-plugin/skills/slm-loop/SKILL.md in qualixar/superlocalmemory
Installs to: ~/.claude/skills/slm-loop
Collection: One of 15 skills cataloged from this repository
Category: AI Engineering — 2793 skills

What SLM Loop does

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 Loop is cataloged under AI Engineering on DirSkills. SLM Loop comes from a repository tagged agent-memory, agent-reliability, ai-agents, claude-code and cursor.

Documentation

README

Excerpt

slm-loop — Bounded, gate-verified agent loops

The one rule

A bounded loop is complete only when an independent gate passes — not when the agent claims it is finished. The agent's own "I'm done" signal is recorded for audit and is never used to terminate the loop. If you take one thing from this skill: the gate is the authority.

Use a bounded loop whenever the goal has a mechanical, checkable contract: a test suite, a JSON schema, a linter, a reconciliation rule, a citation checker, a security scan. When the goal is subjective, keep a human approval gate (see rungs below).

What SLM adds

Every lap is written to SuperLocalMemory as a durable, queryable memory (tagged loop:<name>, session loop:<run_id>). That makes a run:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about SLM Loop

What else does qualixar publish alongside SLM Loop?
SLM Loop is one of 15 skills that DirSkills catalogs from qualixar/superlocalmemory, the repository it ships in. Its siblings there include SLM Cache, SLM Governance and SLM Graph. Each one is a separate skill with its own page in this directory, installs the same way SLM Loop does, and is maintained by qualixar in that same repository. The rest of the collection is listed on the qualixar/superlocalmemory page.
How does SLM Loop compare to other AI Engineering skills?
SLM Loop ranks #2548 by stars among the 2793 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of SLM Loop against them. Open each page to compare what they document and how they install.