offgrid-ai 0.8.4 → 0.8.6

package/README.md

@@ -29,24 +29,28 @@ offgrid-ai stop     # stop a running server
 
 ## Install
 
-One command. Installs Node.js if you don't have it, then installs offgrid-ai.
+### Recommended: one command installer
+
+Installs Node.js if you don't have it, then installs offgrid-ai and adds it to your PATH. Prints a welcome message so you know it worked.
 
 ```bash
 curl -fsSL https://raw.githubusercontent.com/eeshansrivastava89/offgrid-ai/main/install.sh | bash
 ```
 
-Or if you already have Node.js:
+Or review the install script first:
 
 ```bash
-npm install -g offgrid-ai@latest --prefer-online
+curl -fsSL https://raw.githubusercontent.com/eeshansrivastava89/offgrid-ai/main/install.sh | less
 ```
 
-Or review the install script first:
+### Already have Node.js?
 
 ```bash
-curl -fsSL https://raw.githubusercontent.com/eeshansrivastava89/offgrid-ai/main/install.sh | less
+npm install -g offgrid-ai@latest --prefer-online
 ```
 
+This works without extra flags, but npm hides postinstall output by default, so you won't see the welcome message. Open a new terminal window or run `source ~/.zshrc` and then `offgrid-ai`.
+
 ## How it works
 
 1. **Auto-detect everything.** Scans for GGUF models in LM Studio and Hugging Face cache directories, and checks managed backends like Ollama/oMLX through their local APIs. Reads model metadata (quantization, context size, vision, thinking mode) directly from GGUF files. No presets, no manual configuration.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "offgrid-ai",
-  "version": "0.8.4",
+  "version": "0.8.6",
   "description": "Privacy-first CLI for running local LLMs — discover, configure, run, benchmark",
   "author": "Eeshan Srivastava (https://eeshans.com)",
   "type": "module",

package/src/benchmark.mjs

@@ -727,6 +727,44 @@ async function queryOllamaMetrics(profile) {
   };
 }
 
+// ── Unload model from server memory after benchmark ────────────────────────
+
+export async function unloadModelFromServer(profile) {
+  const backend = backendFor(profile.backend);
+
+  if (backend.id === "ollama") {
+    const apiBaseUrl = (profile.baseUrl
+      ? profile.baseUrl.replace(/\/v1\/?$/u, "")
+      : backend.apiBaseUrl).replace(/\/$/u, "");
+
+    try {
+      await fetch(`${apiBaseUrl}/api/generate`, {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ model: profile.modelAlias, prompt: "", stream: false, keep_alive: 0 }),
+        signal: AbortSignal.timeout(10000),
+      });
+      return { unloaded: true, backend: backend.id };
+    } catch (err) {
+      return { unloaded: false, backend: backend.id, error: err.message };
+    }
+  }
+
+  if (backend.id === "llama-cpp" || backend.id === "llama-cpp-mtp") {
+    // llama.cpp unloads when the server process exits; no HTTP unload API exists.
+    // If offgrid-ai started the server, stopProfile already handled it.
+    return { unloaded: false, backend: backend.id, reason: "stop server to unload" };
+  }
+
+  if (backend.id === "omlx") {
+    // oMLX does not expose a model-unload endpoint. The model stays resident
+    // until the oMLX server process is stopped.
+    return { unloaded: false, backend: backend.id, reason: "no unload API available" };
+  }
+
+  return { unloaded: false, backend: backend.id, reason: "unsupported backend" };
+}
+
 // ── Finalize benchmark run metadata ──────────────────────────────────────
 
 export async function finalizeBenchmarkRun(runDirectory, runResult, speedMetrics) {
@@ -869,6 +907,7 @@ export async function runPreparedBenchmark(profile, runDirectory, options = {})
         console.log(result.stopped ? pc.green(`[stop] ${result.message}`) : pc.dim(`[stop] ${result.message}`));
       }
     }
+    await unloadModelFromServer(profile).catch(() => {});
   }
 
   return metadata;

package/src/postinstall.mjs

@@ -26,12 +26,6 @@ if (isHermesPrefix(prefix, process.env.HOME)) {
 const npmBin = join(prefix, "bin");
 const marker = "# Added by offgrid-ai installer";
 const pathLine = `export PATH="${npmBin}:$PATH"`;
-const currentPath = process.env.PATH ?? "";
-
-if (currentPath.split(":").includes(npmBin)) {
-  console.log(`offgrid-ai is already on PATH (${npmBin})`);
-  process.exit(0);
-}
 
 const home = process.env.HOME;
 if (!home) {