Find the right small language model (SLM) for a task, based on given context. Live rule-based matching against the HuggingFace API.

SDLC gate checker — CLI & Web UI — using local SLM (Ollama) or cloud AI. Weighted eval, severity, consensus, code eval, auto-fix, pipeline gen.

Copy the following code in the entry point of your application for example: **main.ts** or **main.js**.

A plugin command script for the https://github.com/CityOfNewYork/patterns-cli that will compile Twig view templates. Replaces the default Slm compiler.

Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.

CLI tool for the Alveare Private SLM Inference-as-a-Service platform

Official TypeScript SDK for the Alveare Private SLM Inference-as-a-Service platform

Semantic linter powered by a local SLM

loader for webpack using svg-slm to optimize the *.svg file

TokenRanger — context compression plugin for OpenClaw. Reduces cloud LLM token costs by 50-80% via local SLM summarization (Ollama).

Evaluate and migrate AI API calls in your codebase to use ScaleDown SLMs for cost reduction

Local SLM trained on your Claude Code sessions. When Claude quota runs out, OpenCode keeps working like Claude.

The knife in the hands of Salome. Killed John, her lover.

Tembory node for n8n AI Agents with operational memory, tool history and decision state

TokenRanger Commercial — Advanced context compression with hybrid validation system. Reduces cloud LLM token costs by 50-80% via local SLM summarization with metrics collection, in-vivo analysis, and learning loop.

Copy the following code in the entry point of your application for example: **main.ts** or **main.js**.

No description provided.

Route AI coding agents (Claude Code, Codex, Continue, Cline, OpenCode, OpenClaw, Junie CLI, JetBrains AI) through the NeoSmith router — same experience, ~60% lower inference cost.

Scientific real-agent A/B benchmark harness for CentR

TypeScript definitions for consolidate