memorix 1.4.3 → 1.4.4

package/docs/DEVELOPMENT.md

@@ -13,9 +13,9 @@ Memorix is a TypeScript project built around:
 
 ## Current Development Baseline
 
-The current release work targets the **1.3 line** while package metadata may still show the last published version until the release commit is cut.
+The current release work targets the **1.4 line** while package metadata may still show the last published version until the release commit is cut.
 
-Contributors should assume the following areas are part of the 1.3 release line:
+Contributors should assume the following areas are part of the 1.4 release line:
 
 - shared memory across MCP clients, CLI, SDK, dashboard, hooks, and memcode
 - memcode uses Memorix project memory, hooks, `/memory` commands, resumable sessions, and model switching as the bundled terminal agent

package/docs/KNOWN_ISSUES_AND_ROADMAP.md

@@ -1,6 +1,6 @@
 # Memorix 已知边界与路线图
 
-> 最后审阅：2026-08-03（对照 v1.4.0）
+> 最后审阅：2026-08-14（对照 v1.4.3）
 
 这份文档说明仍然成立的产品边界、风险和方向；它不是发布流水账。
 
@@ -32,7 +32,7 @@ Memorix 是本地优先、可插拔的 Agent Memory 系统。它给不同 Agent
 |---|---|---|
 | 项目绑定 | 没有可靠工作区根目录时，MCP 会等待显式根目录、MCP Roots 或会话启动，而不会猜测上一个项目。 | 这是防止跨项目读写的安全边界；首次接入时按客户端的项目根目录配置即可。 |
 | 向量与外部模型 | 可选嵌入提供商、网络和首次模型准备会影响写入或检索延迟。 | 不要把外部 API 的瞬时可用性当作本地数据是否已写入的唯一判断；先用 `memorix status` / `doctor` 看状态。 |
-| 媒体记忆 | 已有受控附件和元数据/向量基础，但 PDF 文本提取、音频转写、视频语义提取仍不是默认的全自动链路。 | 只导入确实需要长期复用的资产；不要把截图或工具输出当作默认记忆来源。 |
+| 媒体记忆 | 已有受控附件和元数据/向量基础，PDF 文本提取与音频转写是显式的受控派生链路；视频语义提取仍不是默认的全自动链路。 | 只导入确实需要长期复用的资产；不要把截图或工具输出当作默认记忆来源。 |
 | 图谱与 Wiki | 它们是从规范记忆和代码状态生成的可追溯投影，不是可任意编辑的 GraphRAG 数据库。 | 先写清楚有来源的知识和决策，让投影自然形成关联；不要把图谱当作另一份手工真相。 |
 | Agent 集成 | 上游客户端会改变 hook、MCP、配置文件和权限模型。 | 使用 `memorix doctor agents` 诊断，优先让 `setup` / `repair` 做非破坏性修复。 |
 | 大规模数据 | 保留、归档、去重和检索预算已存在，但上万至百万级数据仍需要按项目负载做容量验证。 | 为高增长项目配置明确的保留与清理策略，并关注 Dashboard / CLI 的审计信息。 |
@@ -55,7 +55,7 @@ Memorix 是本地优先、可插拔的 Agent Memory 系统。它给不同 Agent
 
 ### 3. 受控的多模态派生能力
 
-- 在现有资产生命周期之上评估 PDF 文本提取、音频转写、视频语义派生；
+- 继续在现有资产生命周期之上评估视频语义派生，保持与 PDF/音频派生相同的来源、成本边界、配额、删除联动和重建路径；
 - 每一类派生都必须有来源、成本边界、配额、删除联动和重建路径；
 - 不把“接受任意 URL / 任意文件”误宣传为完整多模态 RAG。
 

package/docs/MODULES.md

@@ -1,6 +1,6 @@
 # Memorix 模块详解
 
-> 最后更新: 2026-07-30 (v1.3.0)
+> 最后更新: 2026-08-14 (v1.4.3)
 > 本文档详细记录每个模块的实现细节、关键算法和注意事项
 
 > 本文档中的早期 JSON/Orama 章节保留为历史模块说明。当前运行时的

package/docs/README.md

@@ -117,7 +117,7 @@ Historical/deep-reference documents may describe older designs. If they conflict
 
 ## Current Product Line
 
-The released product is on the **1.3 line**. The current baseline has:
+The released product is on the **1.4 line**. The current baseline has:
 
 - `memorix setup --agent <agent> --global` is the default agent integration command
 - `memorix serve` is the manual stdio MCP server for external agents

package/docs/SETUP.md

@@ -2,7 +2,7 @@
 
 Memorix is a local-first shared memory layer for AI coding agents.
 
-In the 1.1 line, the normal path is:
+In the current release line, the normal path is:
 
 ```bash
 npm install -g memorix
@@ -144,7 +144,7 @@ memorix serve
 
 Use this when your agent only needs a raw local stdio MCP process or you are debugging a manual config. The agent starts `memorix serve` and communicates with it over stdio.
 
-The stdio server defaults to `--mode micro`, which exposes 7 high-signal tools so agent context is not crowded by rarely used schemas. Use `memorix serve --mode lite` for the extended solo memory surface, `--mode team` for coordination tools, or `--mode full` for advanced and MCP Memory compatibility tools.
+The stdio server defaults to `--mode micro`, which exposes 9 high-signal tools so agent context is not crowded by rarely used schemas. Use `memorix serve --mode lite` for the extended solo memory surface, `--mode team` for coordination tools, or `--mode full` for advanced and MCP Memory compatibility tools.
 
 Generic stdio MCP config:
 
@@ -560,7 +560,7 @@ Use the `team`, `task`, `message`, `handoff`, and `lock` CLI commands when you n
 
 ### `memorix` opens memcode
 
-That is expected in the 1.1 line. Use `memorix --help` to see the full CLI and `memorix serve` for MCP.
+That is expected in the current release line. Use `memorix --help` to see the full CLI and `memorix serve` for MCP.
 
 ### No project memory appears
 

package/docs/hooks-architecture.md

@@ -85,7 +85,8 @@ memorix hook <normalized_event> [--agent <agent_name>]
 ```bash
 memorix hooks install
 # 自动检测已安装的 Agent → 生成对应配置文件
-# 支持: --agent cursor|windsurf|claude|copilot|kiro
+# 支持: --agent claude|codex|cursor|windsurf|copilot|opencode|kiro|antigravity|gemini-cli|trae
+# openclaw/hermes/omp/codex 的 hooks 随插件包安装，使用 `memorix setup --agent <agent>`
 # 支持: --project (仅当前项目) | --global (全局)
 ```
 

package/llms-full.txt

@@ -2,11 +2,11 @@
 
 > Local-first shared memory layer for AI coding agents.
 
-Memorix is a TypeScript/Node.js project that gives AI coding agents persistent, project-aware memory. It targets software development workflows, not generic chat. It works across Claude Code, Codex, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and any agent that can speak MCP over stdio or HTTP. Integrations usually start with `memorix setup --agent <agent> --global`, which installs the recommended user-level package or config for that agent: plugin packages when supported, package or extension entries, MCP config, generated guidance, hooks, skills, or the bundled terminal agent.
+Memorix is a TypeScript/Node.js project that gives AI coding agents persistent, project-aware memory. It targets software development workflows, not generic chat. It works across Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and any agent that can speak MCP over stdio or HTTP. Integrations usually start with `memorix setup --agent <agent> --global`, which installs the recommended user-level package or config for that agent: plugin packages when supported, package or extension entries, MCP config, generated guidance, hooks, skills, or the bundled terminal agent.
 
 If you are an AI coding agent helping a user install, operate, or troubleshoot Memorix, read `docs/AGENT_OPERATOR_PLAYBOOK.md` before taking action. It is the main reference for install, runtime selection, Git/project binding, MCP integration, hooks, and troubleshooting.
 
-## 1.3 Multi-Dimensional Memory Model
+## 1.4 Multi-Dimensional Memory Model
 
 Memorix is not a transcript dump. The normal agent path is `memorix_project_context` or `memorix context --task "..."`, which assembles a bounded task Workset: current Git/package facts, selected observations and reasoning, Code State freshness, source-backed claims, matching knowledge/workflow starts, cautions, and verification hints.
 
@@ -365,7 +365,7 @@ Docker is for the HTTP service. The container must have access to the repositori
 
 ## Supported Clients
 
-Memorix supports Claude Code, Codex, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, memcode, and other stdio or HTTP MCP clients.
+Memorix supports Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, memcode, and other stdio or HTTP MCP clients.
 
 Support depth differs by client:
 
@@ -474,6 +474,6 @@ npm run build
 
 Requirements:
 
-- Node.js `>=22.19.0`
+- Node.js `>=22.18.0`
 - npm
 - Git

package/llms.txt

@@ -2,7 +2,7 @@
 
 > Local-first shared memory layer for AI coding agents.
 
-Memorix gives coding agents persistent, project-aware memory across sessions, IDEs, terminals, and MCP clients. It stores project knowledge once so multiple agents can retrieve it through plugin packages, MCP, CLI, SDK, generated rules/instructions, hooks, skills, local plugins, or the bundled terminal agent. It works with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and other MCP-capable agents.
+Memorix gives coding agents persistent, project-aware memory across sessions, IDEs, terminals, and MCP clients. It stores project knowledge once so multiple agents can retrieve it through plugin packages, MCP, CLI, SDK, generated rules/instructions, hooks, skills, local plugins, or the bundled terminal agent. It works with Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and other MCP-capable agents.
 
 ## Entry Points
 
@@ -10,7 +10,7 @@ Memorix gives coding agents persistent, project-aware memory across sessions, ID
 - `memorix setup --list` lists supported agent entry points.
 - `memorix serve` starts the manual stdio MCP server for IDEs and agents.
 - `memorix background start` starts the HTTP MCP service and dashboard.
-- `memorix memory`, `codegraph`, `knowledge`, `reasoning`, `session`, `team`, `task`, `handoff`, `poll`, `receipt`, `sync`, `ingest`, and `orchestrate` expose the CLI command set.
+- `memorix memory`, `codegraph`, `knowledge`, `reasoning`, `session`, `team`, `task`, `handoff`, `poll`, `receipt`, `sync`, `media`, `ingest`, and `orchestrate` expose the CLI command set.
 - `memorix integrate --agent <agent>` and `memorix hooks install --agent <agent>` are manual/fallback generation commands.
 - `memorix` and `memcode` open memcode, the bundled terminal agent that uses the same project memory pool.
 - `memorix dashboard` opens the local read-mostly dashboard.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "memorix",
   "mcpName": "io.github.AVIDS2/memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Local-first shared memory layer for AI coding agents across MCP clients, Git history, reasoning context, and project sessions.",
   "type": "module",
   "sideEffects": false,

package/plugins/claude/memorix/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://anthropic.com/claude-code/plugin.schema.json",
   "name": "memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Shared workspace memory for Claude Code and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/codebuddy/memorix/.codebuddy-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Local-first project memory for CodeBuddy Code and other coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/codex/memorix/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Shared workspace memory for Codex and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/copilot/memorix/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Shared local workspace memory for GitHub Copilot CLI and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/gemini/memorix/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "mcpServers": {
     "memorix": {
       "command": "memorix",

package/plugins/omp/memorix/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix-omp-package",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Memorix shared workspace memory package for Oh-my-Pi.",
   "license": "Apache-2.0",
   "keywords": [

package/plugins/openclaw/memorix/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Shared workspace memory for OpenClaw and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/pi/memorix/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix-pi-package",
-  "version": "1.4.3",
+  "version": "1.4.4",
   "description": "Memorix shared workspace memory package for Pi coding agent.",
   "license": "Apache-2.0",
   "keywords": [

package/server.json

@@ -7,7 +7,7 @@
     "url": "https://github.com/AVIDS2/memorix",
     "source": "github"
   },
-  "version": "1.4.3",
+  "version": "1.4.4",
   "websiteUrl": "https://github.com/AVIDS2/memorix#readme",
   "icons": [
     {
@@ -22,7 +22,7 @@
     {
       "registryType": "npm",
       "identifier": "memorix",
-      "version": "1.4.3",
+      "version": "1.4.4",
       "runtimeHint": "npx",
       "packageArguments": [
         {

package/src/audit/index.ts

@@ -1,156 +1,156 @@
-/**
- * Audit Module - Track Memorix-written files
- *
- * Records all files written by Memorix to distinguish them from
- * project-native files. Provides audit trail for cleanup and rollback.
- */
-
-import * as fs from 'node:fs/promises';
-import * as path from 'node:path';
-import { homedir } from 'node:os';
-
-function getAuditFilePath(): string {
-  return process.env.MEMORIX_AUDIT_FILE || path.join(homedir(), '.memorix', 'audit.json');
-}
-
-export interface AuditEntry {
-  type: 'hook' | 'rule' | 'other';
-  agent?: string;
-  path: string;
-  createdAt: string;
-}
-
-export interface ProjectAudit {
-  projectRoot: string;
-  installedAt: string;
-  entries: AuditEntry[];
-}
-
-export interface AuditData {
-  version: string;
-  projects: Record<string, ProjectAudit>;
-}
-
-/**
- * Load audit data from disk.
- */
-export async function loadAudit(): Promise<AuditData> {
-  try {
-    const content = await fs.readFile(getAuditFilePath(), 'utf-8');
-    return JSON.parse(content) as AuditData;
-  } catch {
-    // No audit file yet
-    return {
-      version: '1.0.0',
-      projects: {},
-    };
-  }
-}
-
-/**
- * Save audit data to disk.
- */
-export async function saveAudit(data: AuditData): Promise<void> {
-  const auditFile = getAuditFilePath();
-  const dir = path.dirname(auditFile);
-  await fs.mkdir(dir, { recursive: true });
-  await fs.writeFile(auditFile, JSON.stringify(data, null, 2), 'utf-8');
-}
-
-/**
- * Get project ID from project root via .git detection.
- */
-export function getProjectId(projectRoot: string): string {
-  try {
-    const { detectProject } = require('../project/detector.js');
-    const project = detectProject(projectRoot);
-    if (project) return project.id;
-  } catch { /* fallback below */ }
-  const normalized = projectRoot.replace(/\\/g, '/');
-  return `untracked/${normalized}`;
-}
-
-/**
- * Record a file written by Memorix.
- */
-export async function recordFile(
-  projectRoot: string,
-  type: AuditEntry['type'],
-  filePath: string,
-  agent?: string,
-): Promise<void> {
-  const data = await loadAudit();
-  const projectId = getProjectId(projectRoot);
-
-  if (!data.projects[projectId]) {
-    data.projects[projectId] = {
-      projectRoot,
-      installedAt: new Date().toISOString(),
-      entries: [],
-    };
-  }
-
-  // Check if entry already exists
-  const existingIndex = data.projects[projectId].entries.findIndex(
-    (e) => e.path === filePath
-  );
-
-  if (existingIndex === -1) {
-    data.projects[projectId].entries.push({
-      type,
-      agent,
-      path: filePath,
-      createdAt: new Date().toISOString(),
-    });
-  }
-
-  await saveAudit(data);
-}
-
-/**
- * Get all files written by Memorix for a project.
- */
-export async function getProjectFiles(projectRoot: string): Promise<AuditEntry[]> {
-  const data = await loadAudit();
-  const projectId = getProjectId(projectRoot);
-  return data.projects[projectId]?.entries || [];
-}
-
-/**
- * Remove a file from audit (when uninstalled).
- */
-export async function removeFile(projectRoot: string, filePath: string): Promise<void> {
-  const data = await loadAudit();
-  const projectId = getProjectId(projectRoot);
-
-  if (!data.projects[projectId]) return;
-
-  data.projects[projectId].entries = data.projects[projectId].entries.filter(
-    (e) => e.path !== filePath
-  );
-
-  // If no entries left, remove the project
-  if (data.projects[projectId].entries.length === 0) {
-    delete data.projects[projectId];
-  }
-
-  await saveAudit(data);
-}
-
-/**
- * Get all audit entries across all projects.
- */
-export async function getAllAuditEntries(): Promise<
-  Array<{ projectId: string; entry: AuditEntry }>
-> {
-  const data = await loadAudit();
-  const entries: Array<{ projectId: string; entry: AuditEntry }> = [];
-
-  for (const [projectId, project] of Object.entries(data.projects)) {
-    for (const entry of project.entries) {
-      entries.push({ projectId, entry });
-    }
-  }
-
-  return entries;
-}
+/**
+ * Audit Module - Track Memorix-written files
+ *
+ * Records all files written by Memorix to distinguish them from
+ * project-native files. Provides audit trail for cleanup and rollback.
+ */
+
+import * as fs from 'node:fs/promises';
+import * as path from 'node:path';
+import { homedir } from 'node:os';
+
+function getAuditFilePath(): string {
+  return process.env.MEMORIX_AUDIT_FILE || path.join(homedir(), '.memorix', 'audit.json');
+}
+
+export interface AuditEntry {
+  type: 'hook' | 'rule' | 'other';
+  agent?: string;
+  path: string;
+  createdAt: string;
+}
+
+export interface ProjectAudit {
+  projectRoot: string;
+  installedAt: string;
+  entries: AuditEntry[];
+}
+
+export interface AuditData {
+  version: string;
+  projects: Record<string, ProjectAudit>;
+}
+
+/**
+ * Load audit data from disk.
+ */
+export async function loadAudit(): Promise<AuditData> {
+  try {
+    const content = await fs.readFile(getAuditFilePath(), 'utf-8');
+    return JSON.parse(content) as AuditData;
+  } catch {
+    // No audit file yet
+    return {
+      version: '1.0.0',
+      projects: {},
+    };
+  }
+}
+
+/**
+ * Save audit data to disk.
+ */
+export async function saveAudit(data: AuditData): Promise<void> {
+  const auditFile = getAuditFilePath();
+  const dir = path.dirname(auditFile);
+  await fs.mkdir(dir, { recursive: true });
+  await fs.writeFile(auditFile, JSON.stringify(data, null, 2), 'utf-8');
+}
+
+/**
+ * Get project ID from project root via .git detection.
+ */
+export function getProjectId(projectRoot: string): string {
+  try {
+    const { detectProject } = require('../project/detector.js');
+    const project = detectProject(projectRoot);
+    if (project) return project.id;
+  } catch { /* fallback below */ }
+  const normalized = projectRoot.replace(/\\/g, '/');
+  return `untracked/${normalized}`;
+}
+
+/**
+ * Record a file written by Memorix.
+ */
+export async function recordFile(
+  projectRoot: string,
+  type: AuditEntry['type'],
+  filePath: string,
+  agent?: string,
+): Promise<void> {
+  const data = await loadAudit();
+  const projectId = getProjectId(projectRoot);
+
+  if (!data.projects[projectId]) {
+    data.projects[projectId] = {
+      projectRoot,
+      installedAt: new Date().toISOString(),
+      entries: [],
+    };
+  }
+
+  // Check if entry already exists
+  const existingIndex = data.projects[projectId].entries.findIndex(
+    (e) => e.path === filePath
+  );
+
+  if (existingIndex === -1) {
+    data.projects[projectId].entries.push({
+      type,
+      agent,
+      path: filePath,
+      createdAt: new Date().toISOString(),
+    });
+  }
+
+  await saveAudit(data);
+}
+
+/**
+ * Get all files written by Memorix for a project.
+ */
+export async function getProjectFiles(projectRoot: string): Promise<AuditEntry[]> {
+  const data = await loadAudit();
+  const projectId = getProjectId(projectRoot);
+  return data.projects[projectId]?.entries || [];
+}
+
+/**
+ * Remove a file from audit (when uninstalled).
+ */
+export async function removeFile(projectRoot: string, filePath: string): Promise<void> {
+  const data = await loadAudit();
+  const projectId = getProjectId(projectRoot);
+
+  if (!data.projects[projectId]) return;
+
+  data.projects[projectId].entries = data.projects[projectId].entries.filter(
+    (e) => e.path !== filePath
+  );
+
+  // If no entries left, remove the project
+  if (data.projects[projectId].entries.length === 0) {
+    delete data.projects[projectId];
+  }
+
+  await saveAudit(data);
+}
+
+/**
+ * Get all audit entries across all projects.
+ */
+export async function getAllAuditEntries(): Promise<
+  Array<{ projectId: string; entry: AuditEntry }>
+> {
+  const data = await loadAudit();
+  const entries: Array<{ projectId: string; entry: AuditEntry }> = [];
+
+  for (const [projectId, project] of Object.entries(data.projects)) {
+    for (const entry of project.entries) {
+      entries.push({ projectId, entry });
+    }
+  }
+
+  return entries;
+}