diff --git a/.gitignore b/.gitignore
index 080df8c..338e374 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
 .DS_Store
 plans/
-.skillopt-backups
\ No newline at end of file
+.skillopt-backups
+tests/
diff --git a/README.md b/README.md
index b41d0ea..df39032 100644
--- a/README.md
+++ b/README.md
@@ -28,8 +28,9 @@ Every past session, subagent, and workflow -- queryable by your agent.
 Most history tools help humans find old chats.
 
 Obelisk is built for agents. It exposes past work as structured data: sessions,
-messages, tool calls, subagents, workflows, file history, failures, and parent
-chains. The agent writes the query, runs it locally, and answers in plain language.
+messages, tool calls, subagents, workflows, file history, failures, parent
+chains, and human-approved markdown memories. The agent writes the query, runs
+it locally, and answers in plain language.
 
 You don't manage history. You ask questions about past work.
 
@@ -88,6 +89,10 @@ Runs it via node runtime.mjs --query <script>
 Reads the JSON result, answers you in natural language
 ```
 
+When a retrieval produces a memory worth keeping, the agent proposes a markdown
+memory file. After user approval, it registers that file with the narrow
+`runtime.mjs --remember <script>` runtime, which exposes only `remember()`.
+
 **The core idea: don't make humans browse, tag, or organize sessions.**
 Don't invent a rigid query DSL either.
 
@@ -101,10 +106,11 @@ references only when the question needs them:
 
 - `search(text)` — FTS5 full-text search, returns matches with surrounding context
 - `context(uuid)` — full story around a message (parent chain, subagent/workflow metadata)
-- `sql(query, ...params)` — raw SQL for anything else
+- `sql(query, ...params)` — read-only SQL for structured queries
 
-**Structured shortcuts** — session, summary, subagent, workflow, file-history,
-failure, raw-window, and parent-chain helpers over the same SQLite data.
+**Structured shortcuts** — session, memory, summary, subagent, workflow,
+file-history, failure, raw-window, and parent-chain helpers over the same
+SQLite data.
 
 **References** — agent reads on demand when the task needs deeper structure:
 
@@ -126,6 +132,7 @@ schema stay out of the first prompt until the agent needs them.
 | **Subagents** | `subagents/agent-<id>.jsonl` | Agent type, description, full conversation |
 | **Workflows** | `workflows/wf_<runId>.json` | Script, structured result, agent count |
 | **Workflow agents** | `subagents/workflows/wf_<runId>/` | Per-agent transcripts linked to workflow |
+| **Memories** | markdown files registered by the agent after user approval | Prior conclusions linked to source sessions/messages |
 
 Full-text search via FTS5 covers message text across every layer, while the SQLite tables preserve the structure agents need for investigation.
 
diff --git a/SKILL.md b/SKILL.md
index e1708b8..aaa5c6e 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -4,6 +4,7 @@ description: >
   Search and query past Claude Code session history.
   Reactive: when the user asks "how did I fix X", "what did we do last time", "find the session where", "上次怎么修的", "之前的session", "历史记录".
   Proactive: when the user references past work you lack context for, when you're about to modify a file with complex edit history, when the user says "继续之前的" or "continue where we left off", or when understanding prior decisions would improve your current response.
+  Memory: when the user says "记住这个", "remember this", "写入记忆", "save this conclusion", or when you determine a retrieval result contains a conclusion worth persisting.
 allowed-tools:
   - Read
   - Bash(node:*)
@@ -43,6 +44,8 @@ Custom query:
 3. Parse JSON stdout and answer with concise evidence.
 
 The query file runs inside `(async () => { ... })()`. Use `return` to emit JSON.
+Query scripts are read-only: `remember()` is not available, and `sql()` only
+accepts read-only SELECT/WITH queries.
 
 ## Query Routing
 
@@ -97,7 +100,7 @@ expand vertically from one evidence point without dumping the whole session.
 
 ### `sql(query, ...params)`
 
-Raw SQL with `?` placeholders. Returns array rows.
+Read-only SQL SELECT/WITH with `?` placeholders. Returns array rows.
 
 Before writing non-trivial SQL, read `references/schema.md`. Common safe joins:
 
@@ -107,7 +110,7 @@ Before writing non-trivial SQL, read `references/schema.md`. Common safe joins:
 - Prefer SQL-side `GROUP BY`, `COUNT`, `MAX`, `ORDER BY`, and `LIMIT` over hand-counting in the final answer.
 
 Tables: `sessions`, `messages`, `tool_calls`, `tool_results`, `summaries`,
-`subagents`, `workflows`, `workflow_agents`, `messages_fts`.
+`memories`, `subagents`, `workflows`, `workflow_agents`, `messages_fts`.
 
 ## Structured Helpers
 
@@ -130,6 +133,7 @@ tiny sample before relying on less common filters.
 - `trace(uuid)` -- parent chain from root to message.
 - `thread(sessionId)` -- full session messages; last resort only.
 - `raw(uuid, opts?)` -- windowed access to the original JSONL line.
+- `memories(opts?)` -- recall memory layer, newest first. opts: `{ query, project, sessionId, sessions, after, before, branch, limit }`. `query` filters summary/path by terms. Returns registered memory records (id, path, summary, project, session_id, created_at). Read the file at `path` for full content.
 
 ## Retrieval Contract
 
@@ -144,6 +148,61 @@ If field, context, ordering, FTS, or helper semantics affect the query, read
 `references/retrieval-semantics.md` before coding. If a query errors, read
 `references/pitfalls.md` before retrying.
 
+## Memory Layer
+
+Obelisk has a persistent memory layer alongside raw session data. Every
+retrieval queries both layers: `memories()` for prior conclusions, `search()`
+and helpers for raw session evidence. Use memory as prior notes, not final
+authority. If a memory record influences your answer, say naturally that it was
+previously recorded, and compare it with raw session evidence when correctness
+depends on it. Raw session data is the evidence layer, but one hit is not a
+complete truth; query and cite it compactly.
+
+**Recall:** query `memories({ query: 'topic terms', project: '...' })` to find
+prior conclusions relevant to the current task. Like other list helpers,
+passing a string is treated as `sessionId`, and passing a number is treated as
+`limit`. Read the file at `path` for full content.
+
+**Writing memories:** after a retrieval produces a conclusion worth persisting,
+propose writing a memory file. The user must approve. Flow:
+
+1. Write a markdown file using the `Write` tool (user approves).
+2. Register it via `remember()` in a narrow memory-registration script:
+
+```js
+return remember({
+  path: '.obelisk/memories/design-decision-x.md',
+  session_id: 'current-session-id',
+  message_start: 'uuid-of-first-relevant-msg',
+  message_end: 'uuid-of-last-relevant-msg',
+  summary: 'Detailed summary: what was decided, why, what alternatives were considered, and what constraints drove the choice.'
+})
+```
+
+Run the registration script with:
+
+```bash
+node $SKILL_DIR/scripts/runtime.mjs --remember /tmp/register-memory.mjs
+```
+
+`--remember` exposes only `remember()`. It does not expose `search()`, `sql()`,
+`memories()`, or other retrieval helpers. If you need source IDs, find them
+first with a normal `--query` script.
+
+`remember()` validates that `path` already exists and points to a file. Relative
+paths are resolved against the source session's `project_path` when
+`session_id` is provided, then stored as normalized absolute paths. Prefer
+project-relative paths such as `.obelisk/memories/...` plus `session_id`.
+
+`summary` should be detailed enough that `memories()` results alone can judge
+relevance without reading the file. Include the decision, the reasoning, and
+the key constraints — not just a title.
+
+The `message_start`/`message_end` range marks where in the conversation this
+conclusion was drawn. Use it later to trace back to the original evidence.
+
+Memory records survive index rebuilds. They are never auto-deleted.
+
 ## Minimal Patterns
 
 Search, then expand one promising hit:
diff --git a/references/query-patterns.md b/references/query-patterns.md
index 2f45983..298df8a 100644
--- a/references/query-patterns.md
+++ b/references/query-patterns.md
@@ -1,7 +1,8 @@
 # Obelisk Query Patterns
 
-These are copyable CodeAct patterns for `runtime.mjs --query` scripts. They are
-not new APIs. Adapt them to the user's scope and return compact evidence.
+These are copyable CodeAct patterns for `runtime.mjs --query` scripts, plus one
+`--remember` registration pattern. They are not new APIs. Adapt them to the
+user's scope and return compact evidence.
 
 ## Bounded Search To Context
 
@@ -26,6 +27,76 @@ return hits.slice(0, 5).map(h => {
 });
 ```
 
+## Memory Plus Session Evidence
+
+Use this when prior conclusions may exist but the answer still depends on raw
+session evidence. Keep memory as prior notes, not final authority; compare it
+with session evidence in your final answer when correctness matters.
+
+```js
+const project = '%quiet-zero%';
+const topic = 'markdown memory layer';
+const ftsTopic = topic.replace(/[-_]/g, ' ');
+
+const prior_memories = memories({
+  project,
+  query: topic,
+  limit: 5,
+}).map(m => ({
+  id: m.id,
+  path: m.path,
+  session_id: m.session_id,
+  message_start: m.message_start,
+  message_end: m.message_end,
+  created_at: m.created_at,
+  summary: m.summary?.slice(0, 260),
+}));
+
+const session_evidence = search(ftsTopic, { project, limit: 8 })
+  .slice(0, 6)
+  .map(h => ({
+    session_id: h.session.id,
+    session_title: h.session.title,
+    uuid: h.message.uuid,
+    timestamp: h.message.timestamp,
+    snippet: h.message.text?.slice(0, 220),
+  }));
+
+return {
+  query_plan: {
+    project,
+    topic,
+    memory_limit: 5,
+    session_limit: 8,
+  },
+  prior_memories,
+  session_evidence,
+};
+```
+
+## Register Approved Memory
+
+Use this only after the user approves writing memory and the markdown file
+already exists. `remember()` validates the file and stores a normalized absolute
+path, so keep the script small and return the registered record.
+
+Run this script with `runtime.mjs --remember <script>`. The `--remember` runtime
+exposes only `remember()`, not retrieval helpers.
+
+```js
+return remember({
+  path: '.obelisk/memories/memory-layer-design.md',
+  session_id: 'source-session-id',
+  message_start: 'first-message-uuid',
+  message_end: 'last-message-uuid',
+  summary: [
+    'Decision: Obelisk uses one user-facing entry that queries both memory and raw sessions.',
+    'Memory records are prior notes and must be identified naturally when they influence an answer.',
+    'New memory writes require human confirmation before the markdown file is written and registered.',
+  ].join(' '),
+});
+```
+
 ## One-Shot Retrieval For Synthesis
 
 Use this for conclusion, broad history, failure investigation, or file evolution
diff --git a/references/retrieval-semantics.md b/references/retrieval-semantics.md
index 702ece1..fc3091f 100644
--- a/references/retrieval-semantics.md
+++ b/references/retrieval-semantics.md
@@ -13,7 +13,7 @@ Classify the user's request before choosing tools.
 |-------------|--------------|------------|-------------|
 | project name/path, session, cwd, file, time range | scope | `sessions()`, exact SQL on `project_path`, `sessionId`, `fileHistory()` | broad FTS |
 | workflow, subagent, tool call, summary, edit | artifact | `workflows()`, `subagents()`, `summaries()`, `tool_calls`, `tool_results` | all-session search |
-| concept, conclusion, design history, vague memory | semantic | `search()`, summaries, bounded facet sweep | session dumps |
+| concept, conclusion, design history, vague memory | semantic | `memories({ query })`, `search()`, summaries, bounded facet sweep | session dumps |
 
 One-shot retrieval is not all-shot retrieval. A query script may perform
 multiple steps, but the first locator should be the narrowest semantic fit. If a
@@ -23,6 +23,7 @@ unless scoped evidence is insufficient and `query_plan` says why.
 Project-like fields are distinct:
 
 - `sessions.project`: stored Claude Code project slug.
+- `memories.project`: stored project slug copied onto registered memory records.
 - `sessions.project_path`: reconstructed absolute project path.
 - `messages.cwd`: working directory at message time.
 - helper `project`: SQL `LIKE` over `sessions.project`, not exact membership.
@@ -62,23 +63,27 @@ Use the database shape before asking the model to read text.
 
 Ordering and context are semantic:
 
-- `sessions()`, `summaries()`, `workflows()`, and `failures()` are newest first.
+- `sessions()`, `memories()`, `summaries()`, `workflows()`, and `failures()` are newest first.
 - `fileHistory()` is oldest first.
 - `search().context` is temporal neighbors in one session, not causal context.
 - `context(uuid)` and `trace(uuid)` are for parent-chain/causal expansion.
 
 ### Evidence Before Conclusion
 
-Obelisk stores original structure, not precompiled claims. It has sessions,
-messages, summaries, tool calls/results, files, subagents, workflows, parent
-chains, and raw JSONL windows. It does not store "claim", "stance",
-"contradiction", or "conclusion" entities.
+Obelisk's raw session layer stores original structure, not precompiled claims:
+sessions, messages, summaries, tool calls/results, files, subagents, workflows,
+parent chains, and raw JSONL windows. The memory layer can store
+human-approved markdown conclusions, but treat them as prior notes to compare
+against raw evidence when correctness matters.
 
 For semantic questions, build a task-local evidence view:
 
 ```js
 {
   query_plan: { mode, scope, facets, limits },
+  prior_memories: [
+    { id, path, session_id, created_at, summary }
+  ],
   evidence: [
     { type, id, session_id, timestamp, facet, snippet }
   ],
@@ -86,8 +91,8 @@ For semantic questions, build a task-local evidence view:
 }
 ```
 
-Then synthesize the conclusion in the final answer. Do not pretend the evidence
-view is a stored Obelisk entity.
+Then synthesize the conclusion in the final answer. Do not pretend the raw
+evidence view is itself a stored Obelisk entity.
 
 ## Text Search Semantics
 
diff --git a/references/schema.md b/references/schema.md
index d3f78b9..c1277d0 100644
--- a/references/schema.md
+++ b/references/schema.md
@@ -177,6 +177,28 @@ CREATE TABLE index_state (
 );
 ```
 
+### memories
+
+Human-approved markdown memory records registered in Obelisk. The markdown
+file at `path` is the durable memory content; `summary` is the compact retrieval
+surface.
+
+```sql
+CREATE TABLE memories (
+  id            TEXT PRIMARY KEY,   -- memory record ID
+  session_id    TEXT,               -- FK -> sessions.id where the memory was drawn, if known
+  project       TEXT,               -- project slug used for scoped recall
+  message_start TEXT,               -- first relevant message UUID, if known
+  message_end   TEXT,               -- last relevant message UUID, if known
+  path          TEXT,               -- normalized absolute markdown memory file path
+  summary       TEXT,               -- retrieval summary of the memory
+  created_at    TEXT                -- ISO 8601 registration time
+);
+```
+
+Indexes: `idx_memories_project(project)`,
+`idx_memories_session(session_id)`, `idx_memories_created(created_at)`.
+
 ### Key Relationships
 
 ```
@@ -185,8 +207,10 @@ sessions.id        <--  tool_calls.session_id
 sessions.id        <--  tool_results.session_id
 sessions.id        <--  subagents.session_id
 sessions.id        <--  workflows.session_id
+sessions.id        <--  memories.session_id
 messages.uuid      <--  tool_calls.message_uuid
 messages.uuid      <--  tool_results.message_uuid
+messages.uuid      <--  memories.message_start / memories.message_end
 messages.agent_id  -->  subagents.agent_id      (for subagent messages)
 messages.agent_id  -->  workflow_agents.agent_id (for workflow agent messages)
 tool_calls.id      <--  tool_results.tool_use_id
@@ -197,8 +221,9 @@ workflows.run_id   <--  workflow_agents.run_id
 
 ## 2. Query API Reference
 
-All functions are available as globals inside `--query` scripts.
-Scripts run in an async IIFE with a 30-second timeout.
+Read helpers are available as globals inside `--query` scripts. Memory write
+helpers are available only inside `--remember` scripts. Scripts run in an async
+IIFE with a 30-second timeout.
 
 ### Simple Layer
 
@@ -250,15 +275,18 @@ return { chain_length: c.parentChain.length, session_title: c.session?.title };
 
 #### `sql(query, ...params)`
 
-Raw SQL with parameterized bindings. Returns an array of row objects.
+Read-only SQL with parameterized bindings. Returns an array of row objects.
 
 | Param | Type | Description |
 |-------|------|-------------|
-| `query` | `string` | SQL SELECT statement |
+| `query` | `string` | SQL SELECT/WITH statement |
 | `...params` | `any` | Bind parameters (positional `?`) |
 
 **Returns:** `Array<Object>` -- each row as `{ column: value }`.
 
+Write statements are rejected. Use `--remember` and `remember()` for memory
+registration after user approval.
+
 ```js
 const rows = sql('SELECT id, title FROM sessions WHERE project = ? ORDER BY ended_at DESC LIMIT 5', 'Users-tomiya-Code-quiet-zero');
 return rows;
@@ -412,6 +440,76 @@ const qz = sessions({ project: '%quiet-zero%', limit: 5 });
 return qz.map(s => ({ title: s.title, branch: s.git_branch, ended: s.ended_at }));
 ```
 
+#### `memories(opts?)`
+
+Registered markdown memory records. Like other list helpers, passing a string
+is treated as `sessionId`, and passing a number is treated as `limit`.
+
+| Param | Type | Description |
+|-------|------|-------------|
+| `opts.query` | `string` | Term filter over `summary` and `path`; hyphens/underscores are treated as spaces |
+| `opts.project` | `string` | SQL `LIKE` pattern over `memories.project` |
+| `opts.sessionId` | `string` | Restrict to one source session |
+| `opts.sessions` | `string[]` | Restrict to a set of source session IDs |
+| `opts.after` | `string` | ISO 8601 lower bound on `created_at` |
+| `opts.before` | `string` | ISO 8601 upper bound on `created_at` |
+| `opts.branch` | `string` | Filter by source session git branch (exact match) |
+| `opts.limit` | `number` | Max results (default 50) |
+
+**Returns:** `Array<memory_row>` ordered by `created_at` descending.
+
+`query` is a lightweight term filter, not FTS5 ranking. Use it to avoid pulling
+all recent memories, then read the markdown file at `path` when a memory looks
+relevant.
+
+```js
+const prior = memories({
+  project: '%quiet-zero%',
+  query: 'memory layer markdown',
+  limit: 5,
+});
+return prior.map(m => ({
+  id: m.id,
+  path: m.path,
+  session_id: m.session_id,
+  summary: m.summary?.slice(0, 240),
+}));
+```
+
+#### `remember(record)`
+
+Register a human-approved markdown memory file. This is a write helper, not a
+recall helper; use it only after the user has approved writing memory. It is
+available only in scripts run with `runtime.mjs --remember`.
+
+`--remember` exposes only `remember()`, not `search()`, `sql()`, `memories()`,
+or other retrieval helpers. If source IDs are unknown, find them first with a
+normal `--query` script.
+
+| Param | Type | Description |
+|-------|------|-------------|
+| `record.path` | `string` | Existing markdown file path. Relative paths resolve against the source session `project_path` when `session_id` is provided, otherwise against the runtime cwd |
+| `record.summary` | `string` | Required retrieval summary: decision, reasoning, constraints |
+| `record.session_id` | `string` | Source session ID, if known |
+| `record.message_start` | `string` | First relevant source message UUID, if known |
+| `record.message_end` | `string` | Last relevant source message UUID, if known |
+| `record.project` | `string` | Project slug override. Defaults from `sessions.project` for `session_id` |
+
+`remember()` validates that `path` exists and is a regular file. It stores the
+normalized absolute path in `memories.path`.
+
+**Returns:** `{ id, path, project, created_at }`.
+
+```js
+return remember({
+  path: '.obelisk/memories/memory-layer-design.md',
+  session_id: 'source-session-id',
+  message_start: 'first-message-uuid',
+  message_end: 'last-message-uuid',
+  summary: 'Decision: keep Obelisk as one user-facing entry that queries both memory and raw session evidence. Memory is prior notes, not final authority.',
+});
+```
+
 ---
 
 ## 3. Common Query Patterns
diff --git a/scripts/db.mjs b/scripts/db.mjs
index 55265af..b194ad1 100644
--- a/scripts/db.mjs
+++ b/scripts/db.mjs
@@ -54,6 +54,13 @@ CREATE INDEX IF NOT EXISTS idx_sa_session ON subagents(session_id);
 CREATE INDEX IF NOT EXISTS idx_wf_session ON workflows(session_id);
 CREATE INDEX IF NOT EXISTS idx_wa_run ON workflow_agents(run_id);
 CREATE INDEX IF NOT EXISTS idx_summaries_session ON summaries(session_id);
+CREATE TABLE IF NOT EXISTS memories (
+  id TEXT PRIMARY KEY, session_id TEXT, project TEXT,
+  message_start TEXT, message_end TEXT,
+  path TEXT, summary TEXT, created_at TEXT);
+CREATE INDEX IF NOT EXISTS idx_memories_project ON memories(project);
+CREATE INDEX IF NOT EXISTS idx_memories_session ON memories(session_id);
+CREATE INDEX IF NOT EXISTS idx_memories_created ON memories(created_at);
 `;
 
 function openDb() {
diff --git a/scripts/query.mjs b/scripts/query.mjs
index c98ab59..20e4802 100644
--- a/scripts/query.mjs
+++ b/scripts/query.mjs
@@ -24,8 +24,21 @@ function buildWhere(opts, aliases) {
 
 const BASH_EXIT_PAT = 'Exit code %';
 
+function assertReadOnlySql(sql) {
+  const text = String(sql || '').trim();
+  if (!/^(SELECT|WITH)\b/i.test(text)) {
+    throw new Error('sql() only supports read-only SELECT/WITH queries');
+  }
+  if (/\b(INSERT|UPDATE|DELETE|REPLACE|CREATE|DROP|ALTER|PRAGMA|VACUUM|ATTACH|DETACH)\b/i.test(text)) {
+    throw new Error('sql() only supports read-only SELECT/WITH queries');
+  }
+}
+
 function createQueryApi(db) {
-  const q = (sql, ...p) => db.prepare(sql).all(...p);
+  const q = (sql, ...p) => {
+    assertReadOnlySql(sql);
+    return db.prepare(sql).all(...p);
+  };
 
   const search = (text, opts = {}) => {
     const { limit = 20, sessionId, project, after, before, cwd } = opts;
@@ -213,7 +226,65 @@ function createQueryApi(db) {
     };
   };
 
-  return { sql: q, search, context, trace, thread, subagents, workflows, workflowTree, fileHistory, failures, sessions, recent, summaries, raw };
+  const memories = (optsOrSid) => {
+    const opts = normalizeOpts(optsOrSid);
+    const { limit = 50, query } = opts;
+    const needsJoin = opts.branch;
+    const { where: baseWhere, params } = buildWhere(opts, {
+      sessionId: 'mem.session_id',
+      project: 'mem.project',
+      timestamp: 'mem.created_at',
+      branch: 's.git_branch',
+    });
+    const terms = String(query || '')
+      .trim()
+      .replace(/[-_]/g, ' ')
+      .split(/\s+/)
+      .filter(Boolean);
+    let where = baseWhere;
+    for (const term of terms) {
+      where += " AND lower(coalesce(mem.summary,'') || ' ' || coalesce(mem.path,'')) LIKE ?";
+      params.push(`%${term.toLowerCase()}%`);
+    }
+    params.push(limit);
+    const join = needsJoin ? 'LEFT JOIN sessions s ON s.id=mem.session_id' : '';
+    return db.prepare(`SELECT mem.* FROM memories mem ${join} WHERE ${where} ORDER BY mem.created_at DESC LIMIT ?`).all(...params);
+  };
+
+  return { sql: q, search, context, trace, thread, subagents, workflows, workflowTree, fileHistory, failures, sessions, recent, summaries, raw, memories };
 }
 
-export { createQueryApi };
+function createRememberApi(db) {
+  const resolveMemoryPath = (memoryPath, sessionId) => {
+    let base = null;
+    if (sessionId) {
+      base = db.prepare('SELECT project_path FROM sessions WHERE id=?').get(sessionId)?.project_path || null;
+    }
+    const resolved = path.isAbsolute(memoryPath)
+      ? path.normalize(memoryPath)
+      : path.resolve(base || process.cwd(), memoryPath);
+    let stat;
+    try {
+      stat = fs.statSync(resolved);
+    } catch {
+      throw new Error(`remember() memory file does not exist: ${resolved}`);
+    }
+    if (!stat.isFile()) throw new Error(`remember() memory path is not a file: ${resolved}`);
+    return resolved;
+  };
+
+  const remember = ({ path: memoryPath, session_id, message_start, message_end, summary, project }) => {
+    if (!memoryPath || !summary) throw new Error('remember() requires path and summary');
+    const normalizedPath = resolveMemoryPath(memoryPath, session_id);
+    const id = `mem-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
+    const proj = project || db.prepare('SELECT project FROM sessions WHERE id=?').get(session_id)?.project || null;
+    const created_at = new Date().toISOString();
+    db.prepare('INSERT OR REPLACE INTO memories (id, session_id, project, message_start, message_end, path, summary, created_at) VALUES (?,?,?,?,?,?,?,?)').run(
+      id, session_id || null, proj, message_start || null, message_end || null, normalizedPath, summary, created_at);
+    return { id, path: normalizedPath, project: proj, created_at };
+  };
+
+  return { remember };
+}
+
+export { createQueryApi, createRememberApi };
diff --git a/scripts/runtime.mjs b/scripts/runtime.mjs
index dd16777..fd365e7 100644
--- a/scripts/runtime.mjs
+++ b/scripts/runtime.mjs
@@ -7,10 +7,9 @@ const vm = require('node:vm');
 
 import { DB_PATH, openDb } from './db.mjs';
 import { buildIndex } from './indexer.mjs';
-import { createQueryApi } from './query.mjs';
+import { createQueryApi, createRememberApi } from './query.mjs';
 
-function executeQuery(db, scriptContent) {
-  const api = createQueryApi(db);
+function executeScript(api, scriptContent) {
   const sandbox = {
     ...api, JSON, Math, Array, Object, Set, Map, Date, RegExp,
     parseInt, parseFloat, String, Number, Boolean, Error, Promise, console, setTimeout,
@@ -19,6 +18,14 @@ function executeQuery(db, scriptContent) {
   return vm.runInNewContext(`(async()=>{${scriptContent}})()`, ctx, { timeout: 30000 });
 }
 
+function executeQuery(db, scriptContent) {
+  return executeScript(createQueryApi(db), scriptContent);
+}
+
+function executeRemember(db, scriptContent) {
+  return executeScript(createRememberApi(db), scriptContent);
+}
+
 function main() {
   const args = process.argv.slice(2);
   if (args[0] === '--build') {
@@ -42,7 +49,16 @@ function main() {
       .catch(e => { process.stdout.write(JSON.stringify({ error: e.message, stack: e.stack }) + '\n'); db.close(); process.exitCode = 1; });
     return;
   }
-  process.stderr.write('Usage:\n  node runtime.mjs --build\n  node runtime.mjs --search "text"\n  node runtime.mjs --query <file.js>\n');
+  if (args[0] === '--remember' && args[1]) {
+    buildIndex();
+    const db = openDb();
+    const script = fs.readFileSync(path.resolve(args[1]), 'utf8');
+    executeRemember(db, script)
+      .then(r => { process.stdout.write(JSON.stringify(r, null, 2) + '\n'); db.close(); })
+      .catch(e => { process.stdout.write(JSON.stringify({ error: e.message, stack: e.stack }) + '\n'); db.close(); process.exitCode = 1; });
+    return;
+  }
+  process.stderr.write('Usage:\n  node runtime.mjs --build\n  node runtime.mjs --search "text"\n  node runtime.mjs --query <file.js>\n  node runtime.mjs --remember <file.js>\n');
   process.exitCode = 1;
 }