TheStack-ai/waypath
by Various
Open-source memory CLI for Claude Code, Codex & MCP — local-first SQLite, graph-aware recall, review gate. npm i -g waypath
MCP
TheStack-ai/waypath
Added 1 June 2026
Overview
Waypath is an open-source CLI that provides persistent memory for AI coding assistants including Claude Code, Codex, and MCP-compatible tools. It stores data locally in SQLite, uses graph relationships for context-aware recall, and includes a review gate to filter memory entries. Installation is via npm with the command npm i -g waypath.
Best for
Best for
Developers using Claude Code or Codex who need persistent, local memory across sessions
Use cases
- Persist conversation context across Claude Code sessions
- Share memory between Codex and MCP-based tools
- Review and approve memory entries before they are stored
How to use
Install
npm install -g waypath Tools exposed
Local-first
Tested with
Claude Code, Cursor
Notes
Waypath is an open-source CLI that provides persistent memory for AI coding assistants including Claude Code, Codex, and MCP-compatible tools. It stores data locally in SQLite, uses graph relationships for context-aware recall, and includes a review gate to filter memory entries. Installation is via npm with the command npm i -g waypath.
3 stars on GitHub. Last updated 2026-04-28. Licensed MIT.
Use cases
- Persist conversation context across Claude Code sessions
- Share memory between Codex and MCP-based tools
- Review and approve memory entries before they are stored
Pros
- Local-first design keeps data private and offline-capable
- Graph-aware recall surfaces relevant context automatically
- Open-source and npm installable with no dependency on cloud services
Cons
- Very early-stage project with only 3 GitHub stars and limited community support
- Requires command-line comfort and manual setup with each AI tool
- Graph recall quality depends on how users structure their memory entries
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Local-first design keeps data private and offline-capable
- Graph-aware recall surfaces relevant context automatically
- Open-source and npm installable with no dependency on cloud services
Cons
- Very early-stage project with only 3 GitHub stars and limited community support
- Requires command-line comfort and manual setup with each AI tool
- Graph recall quality depends on how users structure their memory entries
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
oraios/serena
Various
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
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.
