Rekindle

Name: Rekindle
Author: Skitchy

@Skitchy

代码仓库

关于 Rekindle

Your AI forgets everything between sessions.

#mcp #memory #continuity #sqlite #session #orientation #ai #claude-code

基本信息

分类

其他

传输方式

stdio

发布者

Skitchy

提交者

Skitch

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "rekindle": {
      "command": "npx",
      "args": [
        "-y",
        "rekindle"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Rekindle?

Rekindle is an MCP continuity engine that solves session orientation for AI assistants like Claude Code. It stores structured context, transcripts, and memories in a local SQLite database – no API keys, no external services. Designed for users who lose time re‑explaining project context every session.

How to use Rekindle?

Run npx rekindle init in your project to create a .rekindle/ folder with a SQLite database, identity template, and transcript directory. Then add the MCP server configuration for your client (Claude Code, Claude Desktop, or Cursor) and paste the boot instructions into your CLAUDE.md. The boot_report tool runs automatically at session start; end_session captures continuity records when you finish.

Key features of Rekindle

Boot‑time orientation pipeline with gap detection and scoring
Structured session capture (checkpoint, decisions, open loops, etc.)
Full‑text search with importance‑weighted BM25 ranking
Memory storage with categories, project scoping, and importance
Local SQLite storage – no network calls, no telemetry
7 MCP tools: boot_report, end_session, store/search/list/delete/update memory

Use cases of Rekindle

Prevent AI assistants from forgetting project context between sessions
Orient the assistant at session boot with identity, recent memories, and gap warnings
Capture decisions, open loops, and preferences at the end of each session
Search and manage project‑scoped memories across multiple sessions

FAQ from Rekindle

How does Rekindle differ from other memory tools like Mem0 or Letta?

Those tools focus on retrieval accuracy (can the AI find what it stored?). Rekindle solves session orientation: proactively loading identity, recent context, memory health, and missing‑context warnings at session start.

Where is my data stored, and is it secure?

All data is stored locally in a .rekindle/ SQLite database inside your project. No data is sent to external servers; the MCP server communicates only via stdio. Transcript capture is optional and disabled by default. The database is not encrypted – use OS‑level disk encryption if needed.

Which clients and transports does Rekindle support?

Claude Code (macOS, Linux/WSL2, Windows), Claude Desktop, and Cursor are tested/compatible via stdio transport. Any MCP client that supports stdio should work.

Do I need API keys or network access to use Rekindle?

No. Rekindle requires no API keys, makes no HTTP calls, and has no telemetry or analytics. Everything runs locally.

Why not just use CLAUDE.md?

A static file is passive – the AI reads it but cannot search, rank, track what’s been retrieved, or detect gaps. Rekindle adds full‑text search, structural gap detection, an orientation score, and structured session capture with checkpoints and open loops.