AWS's spec-driven agentic IDE, CLI and web workspace: prompts become requirements, design docs and tracked tasks before any code is written.
Memwyre
Summary
Memwyre is a memory layer for AI assistants. It stores context in one place and makes it available across ChatGPT, Claude and other tools through a Chrome extension and MCP.
Screenshots
Description
Memwyre is a personal knowledge base and memory layer for AI assistants. Most assistants forget you between chats, and each keeps its own separate memory. Memwyre keeps one persistent vault of your context and makes it available across Claude, ChatGPT, Gemini, Copilot and other tools.
How it works
- Browser extension: save memories from any AI chat and recall them while you work in the browser.
- MCP server: connect the same vault to Claude Desktop, Cursor and other MCP-compatible clients and coding agents, with tools to search, save, update and manage memories.
- Document ingestion: bring in PDFs, text files, YouTube links and web pages, then search them semantically.
- Organisation and export: group memories into projects, tag them, and export to Markdown, JSON or PDF.
It is aimed at developers and heavy AI users who are tired of re-explaining their context every time they switch tools. A REST API with an OpenAPI spec is available for custom integrations.
Reviews
Similar App Suggestions
8-29 MB automation models that run on phones, wearables and microcontrollers — tool calling, structured extraction and embeddings, fully offline.
JetBrains' agent platform: run Claude Agent, Codex, Junie or Copilot in the cloud, then review every diff inside your IDE.
One backend for AI and SaaS products: authentication, merchant-of-record payments, a customer database and AI analytics, with no webhook plumbing to write.
Vercel Labs' tiny open-source coding agent: a ~6MB Zig binary that cold-starts in microseconds and embeds anywhere.