superlocalmemory - npm Package Compare versions

Comparing version 3.6.6 to 3.6.7

package.json

 {
   "name": "superlocalmemory",
-  "version": "3.6.6",
+  "version": "3.6.7",
   "description": "Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.",
@@ -5,0 +5,0 @@ "keywords": [

pyproject.toml

 [project]
 name = "superlocalmemory"
-version = "3.6.6"
+version = "3.6.7"
 description = "Information-geometric agent memory with mathematical guarantees"
@@ -5,0 +5,0 @@ readme = "README.md"

README.md

@@ -312,2 +312,8 @@ <p align="center">
 
+SLM supports **two MCP transports** — use whichever fits your tool. Both expose the same 33 tools and 7 resources.
+
+#### Option A — HTTP transport (v3.6.7+, recommended)
+
+One shared process handles every client. RAM is flat regardless of how many IDE windows, subagents, or concurrent sessions connect. Requires the SLM daemon to be running (`slm start`).
+
 ```json
@@ -317,2 +323,22 @@ {
     "superlocalmemory": {
+      "type": "http",
+      "url": "http://127.0.0.1:8765/mcp/"
+    }
+  }
+}
+```
+
+> **Claude Code** also accepts:
+> ```bash
+> claude mcp add --transport http superlocalmemory http://127.0.0.1:8765/mcp/
+> ```
+
+#### Option B — stdio transport (universal, works everywhere)
+
+Spawns one `slm mcp` subprocess per client connection (~90–110 MB each). Works with every MCP-compatible tool including those that do not yet support HTTP transport. No daemon required.
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
       "command": "slm",
@@ -325,4 +351,33 @@ "args": ["mcp"]
 
-33 MCP tools by default (+42 optional behind `SLM_MCP_ALL_TOOLS=1`) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in `ide/configs/`). **V3.3: Adaptive lifecycle, smart compression, and pattern learning.**
+#### Option C — `mcp-remote` bridge (for stdio-only tools that want HTTP)
 
+Some CLIs (e.g. Grok CLI) only speak stdio but you still want the RAM benefit of HTTP. The [`@modelcontextprotocol/client-cli`](https://www.npmjs.com/package/@modelcontextprotocol/client-cli) package bridges them:
+
+```bash
+npm install -g @modelcontextprotocol/client-cli
+```
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
+      "command": "mcp-remote",
+      "args": ["http://127.0.0.1:8765/mcp/", "--allow-http", "--transport", "http-only"]
+    }
+  }
+}
+```
+
+#### When to use which
+
+| Situation | Use |
+|-----------|-----|
+| Claude Code / Claude Desktop (v3.6.7+) | **HTTP** — zero new processes per session |
+| Cursor, Windsurf, Gemini CLI, Antigravity | **HTTP** — native support |
+| Grok CLI, tools that only support stdio | **`mcp-remote` bridge** |
+| Offline / daemon-free usage | **stdio** |
+| Any tool, any version | **stdio** always works as fallback |
+
+See [`docs/ide-setup.md`](docs/ide-setup.md) for per-IDE configs. 33 MCP tools by default (+42 optional behind `SLM_MCP_ALL_TOOLS=1`) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in `ide/configs/`).
+
 ### Dual Interface: MCP + CLI
@@ -329,0 +384,0 @@

src/superlocalmemory.egg-info/PKG-INFO

 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.6.6
+Version: 3.6.7
 Summary: Information-geometric agent memory with mathematical guarantees
@@ -404,2 +404,8 @@ Author-email: Varun Pratap Bhardwaj <[e-mail]>
 
+SLM supports **two MCP transports** — use whichever fits your tool. Both expose the same 33 tools and 7 resources.
+
+#### Option A — HTTP transport (v3.6.7+, recommended)
+
+One shared process handles every client. RAM is flat regardless of how many IDE windows, subagents, or concurrent sessions connect. Requires the SLM daemon to be running (`slm start`).
+
 ```json
@@ -409,2 +415,22 @@ {
     "superlocalmemory": {
+      "type": "http",
+      "url": "http://127.0.0.1:8765/mcp/"
+    }
+  }
+}
+```
+
+> **Claude Code** also accepts:
+> ```bash
+> claude mcp add --transport http superlocalmemory http://127.0.0.1:8765/mcp/
+> ```
+
+#### Option B — stdio transport (universal, works everywhere)
+
+Spawns one `slm mcp` subprocess per client connection (~90–110 MB each). Works with every MCP-compatible tool including those that do not yet support HTTP transport. No daemon required.
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
       "command": "slm",
@@ -417,4 +443,33 @@ "args": ["mcp"]
 
-33 MCP tools by default (+42 optional behind `SLM_MCP_ALL_TOOLS=1`) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in `ide/configs/`). **V3.3: Adaptive lifecycle, smart compression, and pattern learning.**
+#### Option C — `mcp-remote` bridge (for stdio-only tools that want HTTP)
 
+Some CLIs (e.g. Grok CLI) only speak stdio but you still want the RAM benefit of HTTP. The [`@modelcontextprotocol/client-cli`](https://www.npmjs.com/package/@modelcontextprotocol/client-cli) package bridges them:
+
+```bash
+npm install -g @modelcontextprotocol/client-cli
+```
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
+      "command": "mcp-remote",
+      "args": ["http://127.0.0.1:8765/mcp/", "--allow-http", "--transport", "http-only"]
+    }
+  }
+}
+```
+
+#### When to use which
+
+| Situation | Use |
+|-----------|-----|
+| Claude Code / Claude Desktop (v3.6.7+) | **HTTP** — zero new processes per session |
+| Cursor, Windsurf, Gemini CLI, Antigravity | **HTTP** — native support |
+| Grok CLI, tools that only support stdio | **`mcp-remote` bridge** |
+| Offline / daemon-free usage | **stdio** |
+| Any tool, any version | **stdio** always works as fallback |
+
+See [`docs/ide-setup.md`](docs/ide-setup.md) for per-IDE configs. 33 MCP tools by default (+42 optional behind `SLM_MCP_ALL_TOOLS=1`) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in `ide/configs/`).
+
 ### Dual Interface: MCP + CLI
@@ -421,0 +476,0 @@

src/superlocalmemory/__init__.py

@@ -31,3 +31,3 @@ """SuperLocalMemory — information-geometric agent memory."""
 
-__version__ = "3.6.6"
+__version__ = "3.6.7"
 
@@ -34,0 +34,0 @@ _REQUIRED_VERSIONS = {

src/superlocalmemory/mcp/server.py

@@ -240,6 +240,17 @@ # Copyright (c) 2026 Varun Pratap Bhardwaj / Qualixar
 import threading
-_warmup_thread = threading.Thread(target=_eager_warmup, daemon=True, name="mcp-warmup")
-_warmup_thread.start()
 
+# v3.6.7: Suppress standalone-process behaviours when the MCP server is
+# imported inside the daemon (SLM_MCP_EMBEDDED=1). Three threads are safe
+# to run in a dedicated `slm mcp` subprocess but harmful inside the daemon:
+#   mcp-warmup      — creates a LIGHT engine duplicate; daemon has a FULL one.
+#   parent-watchdog — calls os._exit(0) if its parent IDE quits, which would
+#                     kill the daemon along with it.
+#   stdin-eof-monitor — monitors stdin pipe; meaningless inside the daemon.
+_embedded_in_daemon = _os.environ.get("SLM_MCP_EMBEDDED") == "1"
 
+if not _embedded_in_daemon:
+    _warmup_thread = threading.Thread(target=_eager_warmup, daemon=True, name="mcp-warmup")
+    _warmup_thread.start()
+
+
 # V3.4.57: Parent watchdog — self-terminate when the IDE/Claude session dies.
@@ -278,4 +289,5 @@ # FastMCP relies on stdin EOF to stop, but stdin EOF is NOT guaranteed on
 
-_watchdog_thread = threading.Thread(target=_parent_watchdog, daemon=True, name="parent-watchdog")
-_watchdog_thread.start()
+if not _embedded_in_daemon:
+    _watchdog_thread = threading.Thread(target=_parent_watchdog, daemon=True, name="parent-watchdog")
+    _watchdog_thread.start()
 
@@ -342,4 +354,5 @@
 
-_stdin_monitor_thread = threading.Thread(target=_stdin_eof_monitor, daemon=True, name="stdin-eof-monitor")
-_stdin_monitor_thread.start()
+if not _embedded_in_daemon:
+    _stdin_monitor_thread = threading.Thread(target=_stdin_eof_monitor, daemon=True, name="stdin-eof-monitor")
+    _stdin_monitor_thread.start()
 
@@ -346,0 +359,0 @@

New alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 4 instances in 1 package

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Fixed alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 4 instances in 1 package

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

7752871

0.11%

Lines of code

118492

0.05%

Number of lines in readme file

894

6.56%

No dependency changes