myagentmemory 0.5.2 → 0.5.4

package/README.md

@@ -11,6 +11,8 @@ agent-memory setup     # one-shot: memory dir, skills, hooks, MCP, local Pro pre
 
 Then open your agent and ask *"what do you remember about me?"* — that's the wow.
 
+Prefer to have an agent drive the whole thing — install, configure, verify, then show you what to do next? Feed [this onboarding doc](https://jayzeng.github.io/agentmemory/onboarding.md) to your coding agent or chat LLM and let it run the setup for you.
+
 [![npm version](https://img.shields.io/npm/v/myagentmemory?color=cb3837&logo=npm)](https://www.npmjs.com/package/myagentmemory)
 [![npm downloads](https://img.shields.io/npm/dm/myagentmemory?color=cb3837&logo=npm)](https://www.npmjs.com/package/myagentmemory)
 [![license](https://img.shields.io/npm/l/myagentmemory)](LICENSE)
@@ -22,7 +24,7 @@ Then open your agent and ask *"what do you remember about me?"* — that's the w
 
 - AgentMemory injects your decisions, scratchpad, and daily log at session start — no copy-paste, no re-explaining.
 - Repeated corrections become durable memory you can inspect and undo (Pro).
-- Every memory is a plain Markdown file you own. Memory content, session content, queries, and repository paths stay on this machine.
+- Every memory is a plain Markdown file you own. AgentMemory's services do not receive memory content, session content, queries, or repository paths. Context you ask AgentMemory to return to a coding agent is then subject to that agent or model provider's data handling.
 
 AgentMemory does not provide a Python SDK, does not provide a vector database, and does not provide a knowledge graph. It is a local Markdown store with a CLI, agent skills, and optional full-text and semantic search via [qmd](https://github.com/tobi/qmd). See [product boundary](docs/product-boundary.md) for full scope.
 
@@ -34,9 +36,9 @@ AgentMemory does not provide a Python SDK, does not provide a vector database, a
 
 **Core remembers what you save. Pro learns from what you do.** Core remains free, MIT-licensed, and useful forever. Pro adds three things:
 
-- **Remember past sessions** — ask *"what did we decide about auth?"* across Claude Code, Codex, and Cursor.
+- **Remember past sessions** — ask *"what did we decide about auth?"* across Claude Code, Codex, and Pi session history. Cursor can use AgentMemory's skills and hooks, but Cursor transcript ingestion is not currently supported.
 - **Learn from your patterns** — turn repeated corrections into memory you can inspect and undo.
-- **Private by default** — memory and session content index locally. Pro installation uses a pseudonymous installation identifier and bounded compatibility metadata, never your memory or session content.
+- **Private by default** — memory and session content index locally. AgentMemory's services receive only a pseudonymous installation identifier and bounded compatibility metadata, never your memory or session content. Recall results provided locally to a coding agent are subject to that agent or model provider's data handling.
 
 Preview what Pro would find in your existing sessions *before* installing anything:
 
@@ -48,7 +50,7 @@ agent-memory learn
 agent-memory dashboard
 ```
 
-Pre-install preview: up to 50 local sessions per day. Free installed preview: 20 recalls + 5 learning scans per local day. Memory, session, query, and repository content stay on your machine; installation sends only a pseudonymous identifier and bounded compatibility metadata. Full detail on [privacy, signing, and installation](docs/official-plugin-bootstrap.md).
+Pre-install preview: up to 50 local sessions per day. Free installed preview: 20 recalls + 5 learning scans per local day. AgentMemory's services do not receive memory, session, query, or repository content; installation sends only a pseudonymous identifier and bounded compatibility metadata. Recall results provided locally to a coding agent are subject to that agent or model provider's data handling. Full detail on [privacy, signing, and installation](docs/official-plugin-bootstrap.md).
 
 ## Installation
 
@@ -57,7 +59,7 @@ Pre-install preview: up to 50 local sessions per day. Free installed preview: 20
 brew tap jayzeng/agentmemory https://github.com/jayzeng/agentmemory
 brew install jayzeng/agentmemory/agent-memory
 
-# Install the portable CLI globally (Node.js 20+; macOS, Linux, or Windows)
+# Install the portable Core CLI globally (Node.js 20+; Pro session recall requires Node.js 22.13+)
 npm install -g myagentmemory
 
 # If corporate TLS inspection requires a private CA, use your organization's CA file:
@@ -88,9 +90,9 @@ The npm package installs a platform-neutral Node.js executable. The optional Hom
 - `%USERPROFILE%\.cursor\skills\agent-memory\SKILL.md` — Cursor skill (Windows)
 - `%USERPROFILE%\.agents\skills\agent-memory\SKILL.md` — Agent CLI skill (Windows)
 
-### Pi users
+### Pi
 
-If you're on Pi and prefer a native extension, use `pi-memory` (https://github.com/jayzeng/pi-memory) instead of installing this skill. The CLI + skill workflow here is the cross-platform alternative, and works fine on Pi without any extension.
+Pi doesn't use SKILL.md or a JSON hook config — its extensibility model is a registered native extension. So instead of writing a skill file, `agent-memory setup`/`install-hooks` detects `pi` on your `PATH` and installs [`pi-memory`](https://github.com/jayzeng/pi-memory) for you, via `pi install npm:pi-memory` — same author, same memory-file conventions, native pi tools (`memory_write`, `memory_read`, `scratchpad`, `memory_search`). It's prompted for like any other detected agent and auto-applied under `--yes`; run `agent-memory install-hooks --only pi` to target just pi, or check `agent-memory doctor` for its status.
 
 ### Optional: Enable search with qmd
 
@@ -171,6 +173,7 @@ Run `agent-memory help` for the full generated list, or `agent-memory <command>
 | `agent-memory completion [bash\|zsh\|fish\|powershell] [--stdout]` | Install or print shell completion |
 | `agent-memory install-hooks [--yes] [--all] [--only <agents>] [--mode stable\|per-turn]` | Install managed context and memory-write reminder hooks |
 | `agent-memory uninstall-hooks [--only <agents>]` | Remove only hooks managed by AgentMemory |
+| `agent-memory uninstall [--data] [--yes]` | Remove hooks, skills, MCP registrations, completions, and the Pro plugin; `--data` also deletes MEMORY.md, daily logs, scratchpad, and topics |
 | `agent-memory init [--yes] [--skip-skills] [--skip-hooks]` | Legacy interactive wizard; `setup` runs this as its first step |
 | `agent-memory status [--probe]` | Show config, qmd status, file counts, embedding health |
 | `agent-memory doctor` | One-shot health check across memory, qmd, skills, hooks, and Pro |

package/dist/cli-spec.d.ts

@@ -6,7 +6,7 @@ export interface CliOptionSpec {
         kind: CliValueKind;
     };
 }
-export declare const COMMANDS: readonly ["context", "save", "note", "write", "read", "scratchpad", "search", "distil", "sync", "setup", "status", "doctor", "tutorial", "install-skills", "uninstall-skills", "install-hooks", "uninstall-hooks", "completion", "pro", "recall", "learn", "dashboard", "plugin", "serve", "upgrade", "version", "help"];
+export declare const COMMANDS: readonly ["context", "save", "note", "write", "read", "scratchpad", "search", "distil", "sync", "setup", "status", "doctor", "tutorial", "install-skills", "uninstall-skills", "install-hooks", "uninstall-hooks", "uninstall", "completion", "pro", "recall", "learn", "dashboard", "plugin", "serve", "upgrade", "version", "help"];
 export declare const PLUGIN_COMMANDS: readonly ["list", "status", "install", "update", "uninstall", "manage"];
 export declare const WORKER_ACTIONS: readonly [];
 export declare const SCRATCHPAD_ACTIONS: readonly ["add", "done", "undo", "clear_done", "list"];

package/dist/cli-spec.js

@@ -16,6 +16,7 @@ export const COMMANDS = [
     "uninstall-skills",
     "install-hooks",
     "uninstall-hooks",
+    "uninstall",
     "completion",
     "pro",
     "recall",
@@ -48,6 +49,7 @@ export const COMMAND_DESCRIPTIONS = {
     "uninstall-skills": "remove core instructions from detected agents",
     "install-hooks": "install managed context and memory-write reminder hooks",
     "uninstall-hooks": "remove only hooks managed by agent-memory",
+    uninstall: "remove hooks, skills, MCP registrations, completions, and the Pro plugin; add --data to also delete memory data",
     completion: "install or print Bash, Zsh, Fish, or PowerShell completion",
     pro: "install, inspect, or upgrade AgentMemory Pro",
     recall: "recall decisions and context from prior coding sessions with Pro",
@@ -55,7 +57,7 @@ export const COMMAND_DESCRIPTIONS = {
     dashboard: "open the private local Memory Dashboard",
     plugin: "discover, install, update, or remove optional official plugins",
     serve: "run as a Model Context Protocol (MCP) server over stdio",
-    upgrade: "check for and install newer agent-memory CLI and Pro plugin releases",
+    upgrade: "check for, and auto-install by default, newer agent-memory CLI and Pro plugin releases",
     version: "print the installed agent-memory version",
     help: "show this command overview",
 };
@@ -65,7 +67,7 @@ export const PLUGIN_COMMAND_DESCRIPTIONS = {
     install: "authenticate if needed, then install or upgrade the official bundle",
     update: "upgrade an existing official bundle when a compatible release exists",
     uninstall: "remove official plugin executables while preserving user data",
-    manage: "open the AgentMemory account and billing website",
+    manage: "open account management when that future service is available",
 };
 export const WORKER_ACTION_DESCRIPTIONS = {};
 export const SCRATCHPAD_ACTION_DESCRIPTIONS = {
@@ -95,6 +97,7 @@ export const COMMAND_OPTIONS = {
     "uninstall-skills": [],
     "install-hooks": ["--yes", "--all", "--only", "--mode"],
     "uninstall-hooks": ["--only"],
+    uninstall: ["--data", "--yes"],
     completion: ["--stdout"],
     pro: [],
     recall: [
@@ -111,7 +114,7 @@ export const COMMAND_OPTIONS = {
     learn: ["--preview"],
     dashboard: ["--no-browser"],
     serve: ["--mcp", "--register", "--only"],
-    upgrade: ["--check", "--refresh", "--yes", "--quiet", "--cli", "--plugin"],
+    upgrade: ["--check", "--refresh", "--yes", "--quiet", "--cli", "--plugin", "--background"],
     version: [],
     help: [],
 };
@@ -272,6 +275,7 @@ export const OPTION_SPECS = {
     "--agent": { description: "internal SessionStart host key", value: { label: "agent", kind: "value" } },
     "--token": { description: "internal session-worker lease token", value: { label: "token", kind: "value" } },
     "--uninstall": { description: "use install-skills compatibility uninstall mode" },
+    "--data": { description: "uninstall: also permanently delete the memory directory and plugin state" },
     "--mcp": { description: "serve as an MCP server over stdio (used by Claude Code)" },
     "--register": { description: "register the MCP server in detected supported agents and exit" },
     "--check": { description: "upgrade: report available updates without installing" },
@@ -279,6 +283,9 @@ export const OPTION_SPECS = {
     "--quiet": { description: "upgrade: suppress non-error output (used by the passive session-start refresh)" },
     "--cli": { description: "upgrade: limit action to the CLI binary" },
     "--plugin": { description: "upgrade: limit action to the Pro plugin bundle" },
+    "--background": {
+        description: "upgrade: non-interactive; installs only targets whose policy is 'auto' (see: agent-memory upgrade policy)",
+    },
 };
 export const SHELL_DESCRIPTIONS = {
     bash: "generate or install Bash completion",
@@ -312,13 +319,14 @@ const COMMAND_USAGE = {
     "uninstall-skills": "agent-memory uninstall-skills [--json]",
     "install-hooks": "agent-memory install-hooks [--yes] [--all] [--only claude,codex,cursor] [--mode stable|per-turn] [--json]",
     "uninstall-hooks": "agent-memory uninstall-hooks [--only claude,codex,cursor] [--json]",
+    uninstall: "agent-memory uninstall [--data] [--yes] [--json]",
     completion: "agent-memory completion [bash|zsh|fish|powershell] [--stdout]",
     pro: "agent-memory pro <install|status|upgrade> [--channel stable] [--yes]",
     recall: 'agent-memory recall "<query>" [--limit N] [--context N] [--scope current|global] [--cwd <path>] [--json]\n  Multi-query: agent-memory recall --queries \'["q1","q2","q3"]\' [--sessions N] [--events N]',
     learn: "agent-memory learn [--preview] [--json]",
     dashboard: "agent-memory dashboard [--no-browser]",
     plugin: "agent-memory plugin <list|status|install|update|uninstall|manage> [--channel stable] [--yes] [--no-browser]",
-    upgrade: "agent-memory upgrade [--check] [--yes] [--cli|--plugin] [--refresh] [--json]",
+    upgrade: "agent-memory upgrade [--check] [--yes] [--cli|--plugin] [--refresh] [--json]\n  agent-memory upgrade policy [off|notify|auto] [--cli|--plugin] [--json]  (default: auto for both)",
     version: "agent-memory version",
     help: "agent-memory help [<command>]",
 };
@@ -356,6 +364,10 @@ const COMMAND_EXAMPLES = {
     status: ["agent-memory status", "agent-memory status --json"],
     init: ["agent-memory init", "agent-memory init --yes --skip-hooks"],
     setup: ["agent-memory setup", "agent-memory setup --json"],
+    uninstall: [
+        "agent-memory uninstall --yes  # removes hooks, skills, MCP registrations, completions, Pro plugin",
+        "agent-memory uninstall --data --yes  # also deletes MEMORY.md, daily logs, scratchpad, topics",
+    ],
     "install-hooks": [
         "agent-memory install-hooks",
         "agent-memory install-hooks --yes",