Connect Kimi Code to your cross-tool memory through MCP, reusable skills, and local session import.

For your agent

Paste this into Kimi Code:

Read https://mem.nowledge.co/SKILL.md and follow the instructions to install or update Nowledge Mem for Kimi Code. Verify with nmem status and the Context Bundle or Working Memory check, then summarize what changed.

Kimi Code can use Nowledge Mem through MCP and skills. That gives Kimi Code access to your saved decisions, working context, thread search, and memory save tools. When you want older Kimi Code conversations searchable in Mem, nmem can import Kimi Code's local wire.jsonl sessions.

Before You Start

Nowledge Mem is running locally, or you have a reachable remote Mem server
Kimi Code is installed
nmem works on the same machine as Kimi Code

nmem status

If Kimi Code runs on a different machine from the desktop app, install the standalone CLI there first:

python3 -m pip install --user nmem-cli
nmem config client set url https://your-server
nmem config client set api-key your-key

Setup

Generate the MCP config for this machine:

nmem config mcp show --host kimi-code

Add the generated nowledge-mem server to Kimi Code's MCP configuration. Then import or copy the Nowledge Mem skills so Kimi Code has clear guidance for when to search, save, and check status.

Verify

Restart Kimi Code and ask:

Is Nowledge Mem connected? Read my current context.

Success means Kimi Code can call the Nowledge Mem MCP tools and return Context Bundle, Working Memory, or an empty-but-successful memory result.

Session Capture

Kimi Code stores local sessions under ~/.kimi-code/sessions. Import them with:

nmem t sync --from kimi-code --limit 20
nmem t sync --from kimi-code --apply

This works for local Mem and remote Mem because the nmem CLI reads the local Kimi Code transcript files and uploads normalized thread messages to your configured Mem server.

This is not a live hook package yet. New conversations are imported when you run the sync command. During a conversation, ask Kimi Code to save a handoff summary when you want a compact curated checkpoint immediately.

For your agent

Paste this into Kimi Code:

Read https://mem.nowledge.co/SKILL.md and follow the instructions to install or update Nowledge Mem for Kimi Code. Verify with nmem status and the Context Bundle or Working Memory check, then summarize what changed.

Before You Start

Nowledge Mem is running locally, or you have a reachable remote Mem server
Kimi Code is installed
nmem works on the same machine as Kimi Code

nmem status

If Kimi Code runs on a different machine from the desktop app, install the standalone CLI there first:

python3 -m pip install --user nmem-cli
nmem config client set url https://your-server
nmem config client set api-key your-key

Setup

Generate the MCP config for this machine:

nmem config mcp show --host kimi-code

Add the generated nowledge-mem server to Kimi Code's MCP configuration. Then import or copy the Nowledge Mem skills so Kimi Code has clear guidance for when to search, save, and check status.

Verify

Restart Kimi Code and ask:

Is Nowledge Mem connected? Read my current context.

Success means Kimi Code can call the Nowledge Mem MCP tools and return Context Bundle, Working Memory, or an empty-but-successful memory result.

Session Capture

Kimi Code stores local sessions under ~/.kimi-code/sessions. Import them with:

nmem t sync --from kimi-code --limit 20
nmem t sync --from kimi-code --apply

This works for local Mem and remote Mem because the nmem CLI reads the local Kimi Code transcript files and uploads normalized thread messages to your configured Mem server.

Kimi Code × Nowledge Mem

Before You Start

Setup

Verify

Session Capture

On this page

Kimi Code × Nowledge Mem

Before You Start

Setup

Verify

Session Capture

On this page