MoonshotAI / MoonshotAI/kimi-cli

Plugin Showcase: kimi-mneme — Persistent Memory for Kimi Code CLI

Open
#2,161 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
11.4k
Forks
1.3k
Avg merge
9h 47m
Merged PRs (30d)
2

Description

Overview
I'd like to showcase kimi-mneme — a community plugin that adds persistent cross-session memory to Kimi Code CLI. It so
lves the "blank slate" problem where context is lost between sessions.
What is kimi-mneme?
Mneme (Greek: Μνήμη — goddess of memory) captures, compresses, and retrieves coding session context across restarts, d
ays, or weeks of inactivity.
Key Features
Feature Description
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🧠 Persistent Memory Context survives across sessions, restarts, reboots
🤖 AI Structuring Raw tool outputs → structured observations via Kimi API
⚡ Heuristic Fallback Works without API key — rule-based structuring
🔍 Smart Search Full-text (FTS5) + semantic (sqlite-vec) hybrid search
📊 Progressive Disclosure 3-layer retrieval: index → timeline → full details
🖥️ Web Viewer Real-time memory stream at http://localhost:37777
🔌 Plugin Tools mneme_search, mneme_timeline, mneme_get — AI queries its own memory
🖇️ MCP Server Claude Desktop, Cursor, Goose integration
🔒 Privacy-First Local SQLite storage, no cloud dependencies
💰 Token Economics Tracks token savings from context reuse
Architecture

Image

Integration Points
kimi-mneme integrates cleanly with Kimi CLI's existing plugin system:
• Hooks: Uses all 13 lifecycle events (SessionStart, UserPromptSubmit, PostToolUse, PreCompact, PostCompact, SessionEn
etc.)
• Plugin Tools: Exposes 3 AI-callable tools (mneme_search, mneme_timeline, mneme_get)
• OAuth Reuse: Reads ~/.kimi/credentials/kimi-code.json — no separate API key needed
• No Core Patching: Pure plugin architecture, zero modifications to Kimi CLI
Quick Start

Install

uv tool install git+https://github.com/barrelc/kimi-mneme.git

Setup

mneme bootstrap

Use

kimi
Why This Matters for Kimi CLI

  1. User Retention: Developers hate re-explaining context. Persistent memory = happier users.
  2. Token Efficiency: Reusing structured context costs fewer tokens than re-explaining from scratch.
  3. Ecosystem Growth: Shows Kimi CLI's plugin system is powerful enough for complex extensions.
  4. Privacy Story: Local-first storage aligns with developer concerns about cloud AI.
    Request
    Would love to see kimi-mneme mentioned in:
    • Official plugin documentation/examples
    • Community plugins list
    • Or even considered for future native integration
    Happy to collaborate on documentation, testing, or integration improvements!
    ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
    Repository: https://github.com/barrelc/kimi-mneme
    PyPI: https://pypi.org/project/kimi-mneme/
    Version: 2.0.7
    License: AGPL-3.0
    ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
    Labels: enhancement, documentation

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no repository file, test, or documentation entry point and proposes several possible locations. Start by locating the official plugin documentation/examples and community plugins list, then confirm which location maintainers want. Done means kimi-mneme is documented in an accepted location with its repository and setup details.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, sqlite
Domain
cli, documentation
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.