Hey everyone! I built SupraCortex because I kept running into the same problem with coding agents: every time I switched tools or started a new session, useful project context was lost. I didn't want another giant chat history or a pile of Markdown files. I wanted one local place to keep the decisions, constraints, and lessons that actually matter. So I built SupraCortex. It gives Claude Code, Codex, OpenCode, and other MCP clients access to the same project memory. It also tracks where memories came from, flags outdated information, and helps carry work between sessions. It's open source, MIT licensed, and still early. I'd really like to hear from developers using multiple coding agents. What would you want your agents to remember automatically, and what should require your approval? GitHub: https://github.com/Xelson431/sup... Thanks for checking it out!

SupraCortex

One shared project memory for coding agents Copy

One shared project memory for coding agents Copy