@zenithfoundry/slm-gate 1.2.1 → 1.2.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +11 -1
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -258,7 +258,17 @@ flowchart LR
258
258
 
259
259
  ## Quick Start
260
260
 
261
- You need Node.js 22+, pnpm 10+ and [Ollama](https://ollama.com/download) running. This is the setup for a 16 GB machine with Claude Code; other editors and machine sizes are in the [setup guide](docs/setup.md).
261
+ You need a Mac or Linux computer with 16 GB of RAM or more, Node.js 22+ and [Ollama](https://ollama.com/download) running.
262
+
263
+ ```bash
264
+ npm install -g @zenithfoundry/slm-gate
265
+ slm-gate init # creates ~/.slm-gate/.env for this computer and prints the next steps
266
+ slm-gate doctor # after the `ollama pull` line init printed
267
+ ```
268
+
269
+ Then add an MCP server to your coding tool that runs `slm-gate` with the argument `mcp`; for Claude Code: `claude mcp add --scope user slm-gate -- slm-gate mcp`. The [Install from npm](docs/install-from-npm.md) guide walks through every step: any coding tool, any AI provider or fully local, toolboxes, updates.
270
+
271
+ **From source** (to change `slm-gate` itself). You also need pnpm 10+. This is the setup for a 16 GB machine with Claude Code; other editors and machine sizes are in the [setup guide](docs/setup.md).
262
272
 
263
273
  ```bash
264
274
  git clone https://github.com/zenithfoundry/slm-gate.git small-language-model-gate
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@zenithfoundry/slm-gate",
3
- "version": "1.2.1",
3
+ "version": "1.2.2",
4
4
  "type": "module",
5
5
  "description": "A decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly quota.",
6
6
  "license": "MIT",
@@ -53,7 +53,7 @@
53
53
  "@modelcontextprotocol/sdk": "^1.30.1",
54
54
  "@opentelemetry/sdk-node": "^0.222.0",
55
55
  "better-sqlite3": "^13.0.3",
56
- "dotenv": "^16.4.5",
56
+ "dotenv": "^18.0.3",
57
57
  "markdown-it": "^15.0.2",
58
58
  "ollama": "^0.6.3",
59
59
  "zod": "^3.23.8",