Skitchy/rekindle
by Various
Your AI forgets everything between sessions. Rekindle fixes that.
MCP
Skitchy/rekindle
Added 1 June 2026
Overview
Skitchy/rekindle is a TypeScript library that provides persistent memory for AI agents across sessions. It stores context and state so that agents can recall previous interactions without external services.
Best for
Best for
Developers building AI agents or chatbots that need session‑to‑session memory
Use cases
- Give a chatbot long-term memory of user conversations
- Maintain agent state across API calls or user sessions
- Build AI assistants that remember user preferences over time
How to use
Install
npx rekindle init Tools exposed
open_loopsrelational_deltanext_session_focusstore_memorysearch_memorylist_memoriesdelete_memoryupdate_memorylist_capturesread_capturecapture_nowREKINDLE_PRECOMPACT_MAX_MESSAGESREKINDLE_PRECOMPACT_MAX_CHARSREKINDLE_BASE_DIR
Tested with
Claude Desktop, Claude Code, Cursor
Notes
Skitchy/rekindle is a TypeScript library that provides persistent memory for AI agents across sessions. It stores context and state so that agents can recall previous interactions without external services.
3 stars on GitHub. Last updated 2026-05-13. Licensed MIT.
Use cases
- Give a chatbot long-term memory of user conversations
- Maintain agent state across API calls or user sessions
- Build AI assistants that remember user preferences over time
Pros
- Open source and simple to integrate with existing TypeScript projects
- No external database required for basic persistence
- Lightweight with minimal dependencies
Cons
- Limited documentation and community examples
- May require manual serialization for complex state
- Not designed for high‑scale or distributed deployments
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Open source and simple to integrate with existing TypeScript projects
- No external database required for basic persistence
- Lightweight with minimal dependencies
Cons
- Limited documentation and community examples
- May require manual serialization for complex state
- Not designed for high‑scale or distributed deployments
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
upstash/context7
Various
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
topoteretes/cognee
Various
Memory platform for AI Agents in 6 lines of code
vectorize-io/hindsight
Various
Hindsight: Agent Memory That Learns
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.