A cross-client markdown memory that syncs context between Claude, ChatGPT, Cursor, and Claude Code through a single MCP endpoint. The server stores memories as plain markdown with YAML frontmatter, mirrored locally so you can edit files directly or open them in Obsidian. It exposes lexical search across your memory and read/write operations that let any connected AI recall decisions or constraints set in another tool. Reach for this when you're tired of re-pasting architecture notes every time you switch from Claude to Cursor, or when you want your AI context to survive past the next vendor memory wipe. Files stay on your machine and in your region, with EU hosting and zero lock-in.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent