Launching today

CodeYam CLI & Memory
Comprehensive memory management for Claude Code
78 followers
Comprehensive memory management for Claude Code
78 followers
We built CodeYam Memory because Claude Code kept repeating the same mistakes and our claude.md files got stale. CodeYam Memory uses a background agent to review your coding session transcripts, identifies confusion patterns, and generates targeted rules with proper scoping. This is a small first step towards our vision of exploring the ideal AI-native development experience, packaged as a lightweight CLI that you can use wherever you use Claude Code.
Products used by CodeYam CLI & Memory
Explore the tech stack and tools that power CodeYam CLI & Memory. See what products CodeYam CLI & Memory uses for development, design, marketing, analytics, and more.
Engineering & Development 1
Engineering & Development 1

Claude CodeAnthropic’s deep-context AI coder
5.0 (234 reviews)
Claude Code fits how I like to work. The CLI loop is fast, and it’s decently good at working through changes across a repo without needing constant prompting. My preferred format is Claude Code in the terminal or in my IDE (VS Code or Cursor, although I hope to try Zed soon). I have also tried the Claude Chrome extension and Desktop app, but find them too buggy to reliably use for anything but chat. Specifically for Claude Cowork, it often has cold start problems (can't get set up) and then often creates weird results and pushes me to IDEs or formats I don't use, like open a .md file in Windsurf (no thanks) or open a slide deck in PowerPoint (also no thanks). I hope that the Anthropic team gets Claude Cowork to a more stable, usable state as it has a ton of potential. I also hope they integrate more seamlessly with Google Workspace so I don't have to constantly download/upload/convert PowerPoint to Google Slides (for instance) to iterate and edit. Also please stop pushing me to Windsurf!
Productivity 2
Productivity 2

LinearThe product development system for teams and agents.
4.9 (364 reviews)
We run most of our planning and issue tracking in Linear. While we didn't need something this robust in our early days, as we speed towards launches (like our PH launch) Linear becomes essential for keeping our team aligned on highest priorities, todos, and who is working on what.
The Discord integration keeps things visible for the team and makes it easy to add bugs/issues or features as they're discussed, and the MCP server makes it easy to plug Linear into agent-based workflows. I use the Linear MCP with Claude (either Claude Cowork in the Desktop app if it works or, when it's buggy, in Claude Chat or Claude Code in the terminal directly). When Claude + Linear MCP works, it's magical. I feel like I can wave my magic wand and bippity-boppity-boop get a detailed roadmap with owners, priorities, timelines, milestones, which would have taken me hours in the past.

FigmaThe collaborative interface design tool
4.9 (1.4K reviews)
Figma’s Dev Mode MCP server makes it much easier to bring design context into AI coding workflows. Instead of copying specs manually or screenshotting, the agent can pull what it needs directly from the source. I use this with Claude Code in VS Code, and find it super effective from translating designs to code, especially if designs are more detailed or complex (e.g. too big to bring the frame into a vibe coding tool that allows Figma imports). While there's still a lot that can be improved for the Figma Dev Mode MCP (it's still in beta) it's well worth using.

Cursor
Windsurf