@holt-os/holt 0.3.0 → 0.4.0

package/README.md

@@ -38,6 +38,7 @@ During `holt init` you:
 2. **Choose brains** (claude, codex, gemini). Holt installs any you pick that are missing.
 3. **Sign in.** For a newly installed brain, Holt starts that tool's own login (browser or its own prompt). Holt never stores your credentials.
 4. **Pick a default** brain and, optionally, a **launch command** (a short word like `ai` that runs `holt chat`).
+5. **Enable semantic memory.** If you say yes, Holt sets up a local [Ollama](https://ollama.com) with a small embed model so recall works by meaning, fully offline.
 
 ## Using it
 
@@ -61,7 +62,7 @@ Every exchange is saved to `<folder>/.holt/memory/turns.jsonl`, private and loca
 
 Two recall modes, picked automatically:
 
-- **Semantic** (best): if a local [Ollama](https://ollama.com) is running with an embedding model (`ollama pull nomic-embed-text`), recall matches by meaning. Asking "who owns my apartment" finds "my landlord is called Pieter". No API keys, nothing leaves your machine.
+- **Semantic** (best): a local [Ollama](https://ollama.com) with an embedding model, which `holt init` offers to set up for you. Recall matches by meaning: asking "who owns my apartment" finds "my landlord is called Pieter". No API keys, nothing leaves your machine.
 - **Keyword** (fallback): with no Ollama, recall matches by word overlap. Still useful, zero setup.
 
 Inspect it any time:
@@ -69,9 +70,12 @@ Inspect it any time:
 ```bash
 holt memory                    # stats for this folder
 holt memory search <query>     # find remembered moments
+holt memory embed              # embed older moments for semantic recall
 holt memory clear              # wipe this folder's memory
 ```
 
+Turns saved before semantic memory was enabled are upgraded in one pass with `holt memory embed`.
+
 Long conversations stay cheap: only recent turns are replayed verbatim, older context comes back through recall.
 
 ## Brains

package/dist/cli.js

@@ -252,81 +252,8 @@ function runInteractive(cmd, args) {
   });
 }
 
-// src/commands/init.ts
-function parseBrains(raw, found) {
-  const s = raw.trim().toLowerCase();
-  if (s === "") return found.length ? found : [...BRAIN_IDS];
-  if (s === "all") return [...BRAIN_IDS];
-  const picked = s.split(/[\s,]+/).filter((x) => BRAIN_IDS.includes(x));
-  if (picked.length) return [...new Set(picked)];
-  return found.length ? found : ["claude"];
-}
-async function init() {
-  const { ask, close } = createReader();
-  if (!await ensureTrusted(ask)) {
-    close();
-    return;
-  }
-  console.log(c.accent("Holt setup") + c.dim(`  (${workspace()})`) + "\n");
-  console.log("Looking for agent CLIs on your machine...\n");
-  const found = [];
-  for (const id of BRAIN_IDS) {
-    const ok = isInstalled(BRAIN_DEFS[id].command);
-    console.log(`  ${ok ? c.green("found  ") : c.dim("missing")}  ${BRAIN_DEFS[id].label} (${BRAIN_DEFS[id].command})`);
-    if (ok) found.push(id);
-  }
-  console.log("");
-  const chosen = parseBrains(
-    await ask('Which brains do you want? claude, codex, gemini (comma-separated, or "all"): ') ?? "",
-    found
-  );
-  console.log(c.dim(`  using: ${chosen.join(", ")}`));
-  const toInstall = chosen.filter((id) => !isInstalled(BRAIN_DEFS[id].command));
-  const loginWanted = /* @__PURE__ */ new Set();
-  for (const id of toInstall) {
-    const a = (await ask(`  ${BRAIN_DEFS[id].label} is not installed. Sign in after install? [Y/n] `) ?? "").trim().toLowerCase();
-    if (a !== "n" && a !== "no") loginWanted.add(id);
-  }
-  const defPick = chosen.includes("claude") ? "claude" : chosen[0];
-  const dans = (await ask(`
-Default brain? [${chosen.join("/")}] (${defPick}): `) ?? "").trim();
-  const defaultBrain = chosen.includes(dans) ? dans : defPick;
-  const aliasAns = (await ask('Launch command? Type a custom word like "ai", or press enter to keep "holt": ') ?? "").trim();
-  let aliasNote = "";
-  if (aliasAns && aliasAns !== "holt") {
-    if (isInstalled(aliasAns)) console.log(c.dim(`  note: "${aliasAns}" already exists; the alias will shadow it in new shells.`));
-    const r = installAlias(aliasAns);
-    aliasNote = r.ok ? c.green(`  alias "${aliasAns}" -> holt chat added to ${r.file} (run: source ${r.file})`) : c.red("  " + r.message);
-  }
-  close();
-  for (const id of toInstall) {
-    const s = BRAIN_SETUP[id];
-    console.log("\n" + c.accent(`Installing ${BRAIN_DEFS[id].label}`) + c.dim(`  (${s.install.join(" ")})`));
-    const code = await runInteractive(s.install[0], s.install.slice(1));
-    console.log(code === 0 ? c.green(`  ${BRAIN_DEFS[id].label} installed.`) : c.red(`  Install failed (exit ${code}). Run manually: ${s.install.join(" ")}`));
-  }
-  for (const id of toInstall) {
-    if (!loginWanted.has(id) || !isInstalled(BRAIN_DEFS[id].command)) continue;
-    const s = BRAIN_SETUP[id];
-    console.log("\n" + c.accent(`Sign in to ${BRAIN_DEFS[id].label}`));
-    console.log(c.dim(`  Starting "${s.login.join(" ")}". Complete sign-in, then exit that tool to return here.`));
-    await runInteractive(s.login[0], s.login.slice(1));
-  }
-  const cfg = loadConfig() ?? defaultConfig();
-  for (const id of BRAIN_IDS) cfg.brains[id].enabled = chosen.includes(id) && isInstalled(BRAIN_DEFS[id].command);
-  cfg.defaultBrain = cfg.brains[defaultBrain].enabled ? defaultBrain : BRAIN_IDS.find((id) => cfg.brains[id].enabled) ?? null;
-  saveConfig(cfg);
-  console.log("\n" + c.green("Saved to ./.holt/config.json"));
-  if (aliasNote) console.log(aliasNote);
-  if (cfg.defaultBrain) console.log("Start chatting:  " + c.accent(aliasAns && aliasAns !== "holt" ? aliasAns : "holt chat") + "\n");
-  else console.log(c.dim('No brain is ready yet. Install one, then run "holt init" again.\n'));
-}
-
-// src/commands/chat.ts
-import { randomUUID as randomUUID2 } from "crypto";
-
 // src/memory.ts
-import { appendFileSync, readFileSync as readFileSync4, existsSync as existsSync4, mkdirSync as mkdirSync2, rmSync, statSync } from "fs";
+import { appendFileSync, readFileSync as readFileSync4, writeFileSync as writeFileSync4, existsSync as existsSync4, mkdirSync as mkdirSync2, rmSync, statSync } from "fs";
 import { join as join3 } from "path";
 import { randomUUID } from "crypto";
 var OLLAMA_URL = process.env.HOLT_OLLAMA_URL || "http://127.0.0.1:11434";
@@ -341,6 +268,9 @@ function newSessionId() {
   return randomUUID().slice(0, 8);
 }
 var embedProbe = null;
+function resetEmbedProbe() {
+  embedProbe = null;
+}
 async function embeddingsAvailable() {
   if (embedProbe !== null) return embedProbe;
   try {
@@ -437,6 +367,131 @@ async function recall(query, currentSession, k = 4) {
   scored.sort((a, b) => b.score - a.score);
   return scored.slice(0, k);
 }
+async function backfillEmbeddings(onProgress) {
+  const turns = loadTurns();
+  const missing = turns.filter((t) => !Array.isArray(t.emb));
+  if (missing.length === 0) return { embedded: 0, total: 0 };
+  let done = 0;
+  let embedded = 0;
+  for (const t of missing) {
+    const e = await embed(t.content);
+    if (e) {
+      t.emb = e;
+      embedded++;
+    }
+    done++;
+    if (onProgress) onProgress(done, missing.length);
+  }
+  mkdirSync2(memDir(), { recursive: true });
+  writeFileSync4(memPath(), turns.map((t) => JSON.stringify(t)).join("\n") + "\n", "utf8");
+  return { embedded, total: missing.length };
+}
+
+// src/commands/init.ts
+function parseBrains(raw, found) {
+  const s = raw.trim().toLowerCase();
+  if (s === "") return found.length ? found : [...BRAIN_IDS];
+  if (s === "all") return [...BRAIN_IDS];
+  const picked = s.split(/[\s,]+/).filter((x) => BRAIN_IDS.includes(x));
+  if (picked.length) return [...new Set(picked)];
+  return found.length ? found : ["claude"];
+}
+async function init() {
+  const { ask, close } = createReader();
+  if (!await ensureTrusted(ask)) {
+    close();
+    return;
+  }
+  console.log(c.accent("Holt setup") + c.dim(`  (${workspace()})`) + "\n");
+  console.log("Looking for agent CLIs on your machine...\n");
+  const found = [];
+  for (const id of BRAIN_IDS) {
+    const ok = isInstalled(BRAIN_DEFS[id].command);
+    console.log(`  ${ok ? c.green("found  ") : c.dim("missing")}  ${BRAIN_DEFS[id].label} (${BRAIN_DEFS[id].command})`);
+    if (ok) found.push(id);
+  }
+  console.log("");
+  const chosen = parseBrains(
+    await ask('Which brains do you want? claude, codex, gemini (comma-separated, or "all"): ') ?? "",
+    found
+  );
+  console.log(c.dim(`  using: ${chosen.join(", ")}`));
+  const toInstall = chosen.filter((id) => !isInstalled(BRAIN_DEFS[id].command));
+  const loginWanted = /* @__PURE__ */ new Set();
+  for (const id of toInstall) {
+    const a = (await ask(`  ${BRAIN_DEFS[id].label} is not installed. Sign in after install? [Y/n] `) ?? "").trim().toLowerCase();
+    if (a !== "n" && a !== "no") loginWanted.add(id);
+  }
+  const defPick = chosen.includes("claude") ? "claude" : chosen[0];
+  const dans = (await ask(`
+Default brain? [${chosen.join("/")}] (${defPick}): `) ?? "").trim();
+  const defaultBrain = chosen.includes(dans) ? dans : defPick;
+  const aliasAns = (await ask('Launch command? Type a custom word like "ai", or press enter to keep "holt": ') ?? "").trim();
+  let aliasNote = "";
+  if (aliasAns && aliasAns !== "holt") {
+    if (isInstalled(aliasAns)) console.log(c.dim(`  note: "${aliasAns}" already exists; the alias will shadow it in new shells.`));
+    const r = installAlias(aliasAns);
+    aliasNote = r.ok ? c.green(`  alias "${aliasAns}" -> holt chat added to ${r.file} (run: source ${r.file})`) : c.red("  " + r.message);
+  }
+  let wantMemorySetup = false;
+  const embedReady = await embeddingsAvailable();
+  if (embedReady) {
+    console.log(c.dim("\nSemantic memory: ready (local Ollama with " + EMBED_MODEL + " detected)."));
+  } else {
+    const ollamaHere = isInstalled("ollama");
+    const q = ollamaHere ? `Semantic memory needs a local embed model. Pull ${EMBED_MODEL} with Ollama now? [Y/n] ` : "Enable private semantic memory? Installs Ollama plus a small local embed model. Everything stays on your machine. [Y/n] ";
+    const a = (await ask("\n" + q) ?? "").trim().toLowerCase();
+    wantMemorySetup = a !== "n" && a !== "no";
+    if (!wantMemorySetup) console.log(c.dim('  Okay. Memory still works with keyword recall; run "holt init" again anytime.'));
+  }
+  close();
+  for (const id of toInstall) {
+    const s = BRAIN_SETUP[id];
+    console.log("\n" + c.accent(`Installing ${BRAIN_DEFS[id].label}`) + c.dim(`  (${s.install.join(" ")})`));
+    const code = await runInteractive(s.install[0], s.install.slice(1));
+    console.log(code === 0 ? c.green(`  ${BRAIN_DEFS[id].label} installed.`) : c.red(`  Install failed (exit ${code}). Run manually: ${s.install.join(" ")}`));
+  }
+  for (const id of toInstall) {
+    if (!loginWanted.has(id) || !isInstalled(BRAIN_DEFS[id].command)) continue;
+    const s = BRAIN_SETUP[id];
+    console.log("\n" + c.accent(`Sign in to ${BRAIN_DEFS[id].label}`));
+    console.log(c.dim(`  Starting "${s.login.join(" ")}". Complete sign-in, then exit that tool to return here.`));
+    await runInteractive(s.login[0], s.login.slice(1));
+  }
+  if (wantMemorySetup) {
+    if (!isInstalled("ollama")) {
+      if (process.platform === "darwin" && isInstalled("brew")) {
+        console.log("\n" + c.accent("Installing Ollama") + c.dim("  (brew install ollama)"));
+        const code = await runInteractive("brew", ["install", "ollama"]);
+        if (code === 0) await runInteractive("brew", ["services", "start", "ollama"]);
+        else console.log(c.red('  Install failed. Get Ollama from https://ollama.com/download and run "holt init" again.'));
+      } else {
+        console.log(c.dim('\n  Get Ollama from https://ollama.com/download, then run "holt init" again to finish memory setup.'));
+      }
+    }
+    if (isInstalled("ollama")) {
+      console.log("\n" + c.accent("Pulling embed model") + c.dim(`  (ollama pull ${EMBED_MODEL})`));
+      const code = await runInteractive("ollama", ["pull", EMBED_MODEL]);
+      if (code !== 0) {
+        console.log(c.dim('  Could not pull. Start Ollama (open the app or run "ollama serve"), then run:'));
+        console.log(c.dim(`    ollama pull ${EMBED_MODEL}`));
+      }
+      resetEmbedProbe();
+      if (await embeddingsAvailable()) console.log(c.green("  Semantic memory is ready. Chats in trusted folders are stored and recalled locally."));
+    }
+  }
+  const cfg = loadConfig() ?? defaultConfig();
+  for (const id of BRAIN_IDS) cfg.brains[id].enabled = chosen.includes(id) && isInstalled(BRAIN_DEFS[id].command);
+  cfg.defaultBrain = cfg.brains[defaultBrain].enabled ? defaultBrain : BRAIN_IDS.find((id) => cfg.brains[id].enabled) ?? null;
+  saveConfig(cfg);
+  console.log("\n" + c.green("Saved to ./.holt/config.json"));
+  if (aliasNote) console.log(aliasNote);
+  if (cfg.defaultBrain) console.log("Start chatting:  " + c.accent(aliasAns && aliasAns !== "holt" ? aliasAns : "holt chat") + "\n");
+  else console.log(c.dim('No brain is ready yet. Install one, then run "holt init" again.\n'));
+}
+
+// src/commands/chat.ts
+import { randomUUID as randomUUID2 } from "crypto";
 
 // src/commands/setting.ts
 function printStatus(cfg) {
@@ -550,6 +605,9 @@ async function chat() {
   console.log(c.dim(
     `Memory: ${stats.turns} moments from ${stats.sessions} session${stats.sessions === 1 ? "" : "s"} in this folder (recall: ${embedOk ? "embeddings via local Ollama" : "keyword match"}).`
   ));
+  if (embedOk && stats.withEmbeddings < stats.turns) {
+    console.log(c.dim(`  ${stats.turns - stats.withEmbeddings} older moments lack embeddings. Run "holt memory embed" to upgrade them.`));
+  }
   console.log(c.dim("Type a message. Commands: /brain  /memory  /setting  /clear  /help  /exit\n"));
   while (true) {
     const raw = await ask(c.accent("\u203A "));
@@ -676,6 +734,28 @@ async function memoryCmd(sub, rest = []) {
     close();
     return;
   }
+  if (action === "embed") {
+    if (!await embeddingsAvailable()) {
+      console.log(c.dim(`
+  No local Ollama with ${EMBED_MODEL} reachable. Run "holt init" to set it up.
+`));
+      close();
+      return;
+    }
+    const missing = loadTurns().filter((t) => !Array.isArray(t.emb)).length;
+    if (missing === 0) {
+      console.log(c.dim("\n  All moments already have embeddings.\n"));
+      close();
+      return;
+    }
+    console.log("");
+    const r = await backfillEmbeddings((done, total) => {
+      process.stdout.write(`\r  embedding ${done}/${total}...`);
+    });
+    console.log("\n" + c.green(`  Done. ${r.embedded} of ${r.total} moments embedded.`) + "\n");
+    close();
+    return;
+  }
   if (action === "search") {
     const q = rest.join(" ").trim();
     if (!q) {
@@ -703,13 +783,18 @@ async function memoryCmd(sub, rest = []) {
   console.log(`  embedded    ${s.withEmbeddings} of ${s.turns}`);
   console.log(`  size        ${(s.bytes / 1024).toFixed(1)} KB  (./.holt/memory/turns.jsonl)`);
   console.log(`  recall via  ${embedOk ? "embeddings (local Ollama)" : "keyword match (start Ollama with an embed model for semantic recall)"}`);
+  if (embedOk && s.withEmbeddings < s.turns) {
+    console.log(c.dim(`
+  ${s.turns - s.withEmbeddings} moments lack embeddings. Run "holt memory embed" to upgrade them to semantic recall.`));
+  }
   console.log(c.dim("\n  holt memory search <query>   find remembered moments"));
+  console.log(c.dim("  holt memory embed            embed older moments for semantic recall"));
   console.log(c.dim("  holt memory clear            wipe this folder's memory\n"));
   close();
 }
 
 // src/cli.ts
-var VERSION = "0.3.0";
+var VERSION = "0.4.0";
 var BANNER = `
   \u2588\u2588\u2557  \u2588\u2588\u2557 \u2588\u2588\u2588\u2588\u2588\u2588\u2557 \u2588\u2588\u2557  \u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2557
   \u2588\u2588\u2551  \u2588\u2588\u2551\u2588\u2588\u2554\u2550\u2550\u2550\u2588\u2588\u2557\u2588\u2588\u2551  \u255A\u2550\u2550\u2588\u2588\u2554\u2550\u2550\u255D

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@holt-os/holt",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "description": "An open-source personal agent OS: any LLM, private memory you can see and walk.",
   "type": "module",
   "license": "MIT",