Nowledge Mem seamlessly integrates with your existing AI tools and workflows, enabling you to capture insights and access memories without disrupting your flow.

Model Context Protocol (MCP)

MCP (Model Context Protocol) is the primary integration method for AI agents to interact with Nowledge Mem.

MCP-connected agents can act autonomously or respond to your manual triggers to work with your knowledge base.

Capabilities

Search memories: memory_search
Add memories: memory_add
Update memories: memory_update
List memory labels: list_memory_labels
Save/Import threads: thread_persist
Prompts:
- sum: summarize the current session and add it to memory
- save: checkpoint current conversation as a thread
- In Codex CLI: /prompts:distill (sum), /prompts:save_session (save)

Triggers: Manual and Autonomous

Manual and autonomous triggers at a glance:

Mode	How to invoke	Examples	Notes
Manual	- User explicitly asks - Slash commands	ChatWise: "Save our key findings to Nowledge Mem" Cursor/Claude Desktop: `/` + `sum` Claude Code: `/` + `save`, `/` + `sum`; Codex: `/` + `save`, `/` + `distill`	Claude Code slash commands are available after installing the plugin Codex slash commands are available after installing Custom Commands (Level 2)
Autonomous	Agent decides during tasks	- Cursor Rules/ AGENT(S).md/ CLAUDE.md - Claude Code plugin(Skills/Actions)	Tell the agent when/how to autonomously save/ update/ search insights/ state/ progress to Nowledge Mem

Setup Guides

Below are setup guides for integrating Nowledge Mem with popular AI tools via MCP.

Claude Code & Codex CLI

Claude Code — Plugin + MCP. See Claude Code.

Codex CLI — MCP (Level 1), Custom Commands (Level 2). See Codex CLI.

Nowledge Mem MCP Server

Server Endpoint

http://localhost:14242/mcp

Configuration Guide and Examples

For clients like Cursor, use this JSON snippet in their settings.

{
  "mcpServers": {
    "nowledge-mem": {
      "url": "http://localhost:14242/mcp",
      "type": "streamableHttp",
      "headers": {
        "APP": "Cursor"
      }
    }
  }
}

MCP Supported Services

Cursor

ChatWise

Claude Desktop

Claude Code

Github Copilot

Trae

Codex

Gemini Cli

Qwen Code

+ any agent that supports MCP

Browser Extension

For web-based AI chat services, you can import entire conversations into Nowledge Mem with a single click.

With this method, the conversation is first imported as a thread, then you can trigger Memory Distillation from within the app to extract individual memories from the conversation.

Nowledge Mem comes with a browser extension: Nowledge Mem Exchange. When you are in a supported AI chat page, click on the Nowledge Mem icon to parse & import the conversation.

Browser Extension Supported Services

ChatGPT

Gemini

Claude

Perplexitycoming soon

Poecoming soon

Qwencoming soon

+ many more

Download Extension

Chrome

Browser extension to capture conversations from Web AI chat services.

Firefox

Browser extension to capture conversations from Web AI chat services.

Edge

Browser extension to capture conversations from Web AI chat services.

Arc

Browser extension to capture conversations from Web AI chat services.

Thread File Import

Similar to the browser extension, you can import conversations from your favorite AI tools by uploading exported conversation files directly into Nowledge Mem.

File based Conversation Import

Bring your existing knowledge from other apps into Nowledge Mem by importing conversation files.

How It Works

Navigate to Threads

Go to the 'Threads' section from the main sidebar.

Start the Import

Click the 'Import Thread' button to open the file.

Select & Preview

Choose your exported file & select messages to import.

Supported Formats

Cursor Exports

Cursor .md exported conversation files.

ChatWise Exports

ChatWise .html exported conversation files.

Generic Markdown

Following the format of Cursor exported file.

Grow with Us

We are working hard to support more import sources. For any tools you'd love to see integrated, please let us know.

Tight Integrations

Apart from general MCP, Browser Extension, and Thread File Import, Nowledge Mem is also tightly integrated with some popular AI tools for your convenience.

For instance Claude Desktop Extension, Claude Code plugin, Codex Custom Commands.

For some other cool AI Tools like DeepChat and LobeHub Desktop, Nowledge Mem is built-in as an external memory option.

Claude Desktop

Nowledge Mem provides a one-click extension for Claude Desktop, enabling Claude to search, update, and add memories to your Nowledge Mem knowledge base.

Download Extension

Install Extension

Ensure Python 3.13 is installed on your system.

Open Terminal.app and run the following commands:

which brew || /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
python3.13 --version || brew install python@3.13

Double-click the downloaded claude-dxt.mcpb file from your browser's download area
Click the Install button in the installation dialog

Install Extension

You can now ask Claude to save insights to Nowledge Mem, update existing memories, or search your knowledge base anytime during conversations.

Use Mem in Claude Desktop

Claude Code

Use Nowledge Mem directly from Claude Code via MCP to save conversations and distill insights into structured memories.

Install the Claude Code plugin (recommended)

For autonomous workflows (Claude Code automatically searching, sinking, and checkpointing key insights/findings), install the Nowledge Mem plugin. See the official guide: Claude Code plugins.

# Add the Nowledge community marketplace
claude plugin marketplace add nowledge-co/community

# Install the Nowledge Mem plugin
claude plugin install nowledge-mem@nowledge-community

Add the Nowledge Mem MCP server (required)

MCP is still required and is primarily used for human-triggered actions from inside Claude Code.

Default (global) installation:

claude mcp add --transport http nowledge-mem http://localhost:14242/mcp --scope user

Project-only installation (omit scope):

claude mcp add --transport http nowledge-mem http://localhost:14242/mcp

When to use Plugin vs. MCP

Plugin (recommended):
Enhances autonomous behaviors inside Claude Code, such as automatic search, syncing/saving, and checkpointing key findings as you work.
MCP (required):
Enables the full suite of operations:

Tools: memory_search, memory_add, memory_update, memory_delete
Prompts: save, sum
Best practice:
Install both, the plugin for automation, plus MCP for seamless manual and autonomous control.

Usage

Two ways to use Nowledge Mem inside a Claude Code chat:

Save conversation thread to Mem

Press /
Type save
Select nowledge-mem:save (MCP)
Press Enter

This persists the conversation thread to the codebase/folder where Claude Code is running. The saved thread will appear in Nowledge Mem and can be searched and further distilled there.

Distill key insights into memories

Press /
Type sum
Select nowledge-mem:sum (MCP)
Press Enter

Claude Code will distill key insights from the session into structured memories in Nowledge Mem.

All MCP capabilities are available in Claude Code:

Search, add, update, or delete memories
Import entire conversation threads

You can perform these actions either explicitly (with slash commands) or autonomously (via the plugin) once MCP is configured.

Codex CLI

Use Nowledge Mem with Codex in two levels so you can start simple and add more power when you're ready.

Level 1 — Configure MCP (required)

Add Nowledge Mem as an MCP server in Codex. Create or update ~/.codex/config.toml:

[mcp_servers.nowledge-mem]
url = "http://localhost:14242/mcp"

[mcp_servers.nowledge-mem.http_headers]
APP = "Codex"

Note: No restart needed after adding the configuration.

What you get at this level: Codex can call Nowledge Mem tools (memory_search, memory_add, memory_update, list_memory_labels, thread_persist) during workflows and via manual triggers.

Level 2 — Custom Commands (optional, recommended)

Install our custom prompts to add friendly slash commands for saving sessions and distilling insights.

Install:

Fresh install:

curl -fsSL https://raw.githubusercontent.com/nowledge-co/community/main/nowledge-mem-codex-prompts/install.sh | bash

Update install:

curl -fsSL https://raw.githubusercontent.com/nowledge-co/community/main/nowledge-mem-codex-prompts/install.sh -o /tmp/install.sh && bash /tmp/install.sh --force && rm /tmp/install.sh

Usage inside a Codex chat:

Save session to Mem

Press /
Type save
Select prompts:save_session
Press Enter

This lists your available sessions and saves the one you choose to Nowledge Mem.

Distill key insights into memories

Press /
Type distill
Select prompts:distill
Press Enter

Codex will analyze the conversation and create structured memory entries in Nowledge Mem.

Troubleshooting

"MCP server not found" → Check your Codex MCP configuration
Sessions not listing → Ensure you're in the correct project directory

DeepChat

DeepChat comes with built-in Nowledge Mem integration, allowing one-click switch on memory saving and searching over Nowledge Mem.

Enable MCP in DeepChat

Toggle on the switch under Settings > MCP Settings

Enable Nowledge Mem

Toggle on the nowledge-mem switch under Custom Servers

DeepChat Toggle Highlight

LobeHub(working in progress)

LobeHub(formerly LobeChat) comes with built-in Nowledge Mem integration, allowing one-click switch on memory saving and searching over Nowledge Mem.

Coming Soon...

We are still working with LobeHub Team to submitting the Nowledge Mem configuration via Lobhub MCP Marketplace.

One-Click Installation

Install Nowledge Mem directly in LobeHub using the one-click installation feature:

Install to LobeHub Beta

Install to LobeHub

Click the Install button to install Nowledge Mem LobeHub plugin.

LobeHub Installation Demo

API Integration

Nowledge Mem provides RESTful APIs for you to leverage your knowledge freely.

API Reference

Full documentation for Nowledge Mem's RESTful APIs.

OpenAPI Specification

Download the Spec File for Nowledge Mem.

Showcase Your Integration!

Have you built something cool with the Nowledge Mem API?

We'd love to know! Share it on Github Issues, Discord, or Email.

We're always excited to highlight community integrations—standout projects may receive Pro Licenses and special gifts!

Next Steps

Having trouble with your setup? Check the troubleshooting guide:

Troubleshooting - Common issues and solutions
Advanced Features - Explore knowledge graph capabilities

Nowledge Mem seamlessly integrates with your existing AI tools and workflows, enabling you to capture insights and access memories without disrupting your flow.

Model Context Protocol (MCP)

MCP (Model Context Protocol) is the primary integration method for AI agents to interact with Nowledge Mem.

MCP-connected agents can act autonomously or respond to your manual triggers to work with your knowledge base.

Capabilities

Search memories: memory_search
Add memories: memory_add
Update memories: memory_update
List memory labels: list_memory_labels
Save/Import threads: thread_persist
Prompts:
- sum: summarize the current session and add it to memory
- save: checkpoint current conversation as a thread
- In Codex CLI: /prompts:distill (sum), /prompts:save_session (save)

Triggers: Manual and Autonomous

Manual and autonomous triggers at a glance:

Mode	How to invoke	Examples	Notes
Manual	- User explicitly asks - Slash commands	ChatWise: "Save our key findings to Nowledge Mem" Cursor/Claude Desktop: `/` + `sum` Claude Code: `/` + `save`, `/` + `sum`; Codex: `/` + `save`, `/` + `distill`	Claude Code slash commands are available after installing the plugin Codex slash commands are available after installing Custom Commands (Level 2)
Autonomous	Agent decides during tasks	- Cursor Rules/ AGENT(S).md/ CLAUDE.md - Claude Code plugin(Skills/Actions)	Tell the agent when/how to autonomously save/ update/ search insights/ state/ progress to Nowledge Mem

Setup Guides

Below are setup guides for integrating Nowledge Mem with popular AI tools via MCP.

Claude Code & Codex CLI

Claude Code — Plugin + MCP. See Claude Code.

Codex CLI — MCP (Level 1), Custom Commands (Level 2). See Codex CLI.

Nowledge Mem MCP Server

Server Endpoint

http://localhost:14242/mcp

Configuration Guide and Examples

For clients like Cursor, use this JSON snippet in their settings.

{
  "mcpServers": {
    "nowledge-mem": {
      "url": "http://localhost:14242/mcp",
      "type": "streamableHttp",
      "headers": {
        "APP": "Cursor"
      }
    }
  }
}

MCP Supported Services

Cursor

ChatWise

Claude Desktop

Claude Code

Github Copilot

Trae

Codex

Gemini Cli

Qwen Code

+ any agent that supports MCP

Browser Extension

For web-based AI chat services, you can import entire conversations into Nowledge Mem with a single click.

With this method, the conversation is first imported as a thread, then you can trigger Memory Distillation from within the app to extract individual memories from the conversation.

Nowledge Mem comes with a browser extension: Nowledge Mem Exchange. When you are in a supported AI chat page, click on the Nowledge Mem icon to parse & import the conversation.

Browser Extension Supported Services

ChatGPT

Gemini

Claude

Perplexitycoming soon

Poecoming soon

Qwencoming soon

+ many more

Download Extension

Chrome

Browser extension to capture conversations from Web AI chat services.

Firefox

Browser extension to capture conversations from Web AI chat services.

Edge

Browser extension to capture conversations from Web AI chat services.

Arc

Browser extension to capture conversations from Web AI chat services.

Thread File Import

Similar to the browser extension, you can import conversations from your favorite AI tools by uploading exported conversation files directly into Nowledge Mem.

File based Conversation Import

Bring your existing knowledge from other apps into Nowledge Mem by importing conversation files.

How It Works

Navigate to Threads

Go to the 'Threads' section from the main sidebar.

Start the Import

Click the 'Import Thread' button to open the file.

Select & Preview

Choose your exported file & select messages to import.

Supported Formats

Cursor Exports

Cursor .md exported conversation files.

ChatWise Exports

ChatWise .html exported conversation files.

Generic Markdown

Following the format of Cursor exported file.

Grow with Us

We are working hard to support more import sources. For any tools you'd love to see integrated, please let us know.

Tight Integrations

Apart from general MCP, Browser Extension, and Thread File Import, Nowledge Mem is also tightly integrated with some popular AI tools for your convenience.

For instance Claude Desktop Extension, Claude Code plugin, Codex Custom Commands.

For some other cool AI Tools like DeepChat and LobeHub Desktop, Nowledge Mem is built-in as an external memory option.

Claude Desktop

Nowledge Mem provides a one-click extension for Claude Desktop, enabling Claude to search, update, and add memories to your Nowledge Mem knowledge base.

Download Extension

Install Extension

Ensure Python 3.13 is installed on your system.

Open Terminal.app and run the following commands:

which brew || /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
python3.13 --version || brew install python@3.13

Double-click the downloaded claude-dxt.mcpb file from your browser's download area
Click the Install button in the installation dialog

Install Extension

You can now ask Claude to save insights to Nowledge Mem, update existing memories, or search your knowledge base anytime during conversations.

Use Mem in Claude Desktop

Claude Code

Use Nowledge Mem directly from Claude Code via MCP to save conversations and distill insights into structured memories.

Install the Claude Code plugin (recommended)

For autonomous workflows (Claude Code automatically searching, sinking, and checkpointing key insights/findings), install the Nowledge Mem plugin. See the official guide: Claude Code plugins.

# Add the Nowledge community marketplace
claude plugin marketplace add nowledge-co/community

# Install the Nowledge Mem plugin
claude plugin install nowledge-mem@nowledge-community

Add the Nowledge Mem MCP server (required)

MCP is still required and is primarily used for human-triggered actions from inside Claude Code.

Default (global) installation:

claude mcp add --transport http nowledge-mem http://localhost:14242/mcp --scope user

Project-only installation (omit scope):

claude mcp add --transport http nowledge-mem http://localhost:14242/mcp

When to use Plugin vs. MCP

Plugin (recommended):
Enhances autonomous behaviors inside Claude Code, such as automatic search, syncing/saving, and checkpointing key findings as you work.
MCP (required):
Enables the full suite of operations:

Tools: memory_search, memory_add, memory_update, memory_delete
Prompts: save, sum
Best practice:
Install both, the plugin for automation, plus MCP for seamless manual and autonomous control.

Usage

Two ways to use Nowledge Mem inside a Claude Code chat:

Save conversation thread to Mem

Press /
Type save
Select nowledge-mem:save (MCP)
Press Enter

This persists the conversation thread to the codebase/folder where Claude Code is running. The saved thread will appear in Nowledge Mem and can be searched and further distilled there.

Distill key insights into memories

Press /
Type sum
Select nowledge-mem:sum (MCP)
Press Enter

Claude Code will distill key insights from the session into structured memories in Nowledge Mem.

All MCP capabilities are available in Claude Code:

Search, add, update, or delete memories
Import entire conversation threads

You can perform these actions either explicitly (with slash commands) or autonomously (via the plugin) once MCP is configured.

Codex CLI

Use Nowledge Mem with Codex in two levels so you can start simple and add more power when you're ready.

Level 1 — Configure MCP (required)

Add Nowledge Mem as an MCP server in Codex. Create or update ~/.codex/config.toml:

[mcp_servers.nowledge-mem]
url = "http://localhost:14242/mcp"

[mcp_servers.nowledge-mem.http_headers]
APP = "Codex"

Note: No restart needed after adding the configuration.

What you get at this level: Codex can call Nowledge Mem tools (memory_search, memory_add, memory_update, list_memory_labels, thread_persist) during workflows and via manual triggers.

Level 2 — Custom Commands (optional, recommended)

Install our custom prompts to add friendly slash commands for saving sessions and distilling insights.

Install:

Fresh install:

curl -fsSL https://raw.githubusercontent.com/nowledge-co/community/main/nowledge-mem-codex-prompts/install.sh | bash

Update install:

curl -fsSL https://raw.githubusercontent.com/nowledge-co/community/main/nowledge-mem-codex-prompts/install.sh -o /tmp/install.sh && bash /tmp/install.sh --force && rm /tmp/install.sh

Usage inside a Codex chat:

Save session to Mem

Press /
Type save
Select prompts:save_session
Press Enter

This lists your available sessions and saves the one you choose to Nowledge Mem.

Distill key insights into memories

Press /
Type distill
Select prompts:distill
Press Enter

Codex will analyze the conversation and create structured memory entries in Nowledge Mem.

Troubleshooting

"MCP server not found" → Check your Codex MCP configuration
Sessions not listing → Ensure you're in the correct project directory

DeepChat

DeepChat comes with built-in Nowledge Mem integration, allowing one-click switch on memory saving and searching over Nowledge Mem.

Enable MCP in DeepChat

Toggle on the switch under Settings > MCP Settings

Enable Nowledge Mem

Toggle on the nowledge-mem switch under Custom Servers

DeepChat Toggle Highlight

LobeHub(working in progress)

LobeHub(formerly LobeChat) comes with built-in Nowledge Mem integration, allowing one-click switch on memory saving and searching over Nowledge Mem.

Coming Soon...

We are still working with LobeHub Team to submitting the Nowledge Mem configuration via Lobhub MCP Marketplace.

One-Click Installation

Install Nowledge Mem directly in LobeHub using the one-click installation feature:

Install to LobeHub Beta

Install to LobeHub

Click the Install button to install Nowledge Mem LobeHub plugin.

LobeHub Installation Demo

Troubleshooting - Common issues and solutions
Advanced Features - Explore knowledge graph capabilities

Integrations

How It Works

Navigate to Threads

Start the Import

Select & Preview

Supported Formats

API Reference

OpenAPI Specification

On this page

Integrations

How It Works

Navigate to Threads

Start the Import

Select & Preview

Supported Formats

API Reference

OpenAPI Specification

On this page