Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more
Local-first project memory for AI coding tools over MCP.
Context Sync gives an agent a persistent memory layer for a codebase:

Context Sync is built for session continuity. Instead of relying on a model to remember earlier conversations, it stores the project context that matters and makes it retrievable through a small MCP tool surface.
The current core tools are:
set_projectrememberrecallread_filesearchstructuregitnotionInstall globally:
npm install -g @context-sync/server
Auto-configuration runs during global install. After install, restart your AI tool.
If you install locally instead of globally, auto-config does not run. Use the manual config guide in docs/CONFIG.md.
Check that context-sync appears in your MCP tool list:
codex mcp listclaude mcp listIf auto-config fails, use docs/TROUBLESHOOTING.md and docs/CONFIG.md.
Run the setup wizard if you want Notion integration:
context-sync-setup
or:
npx context-sync-setup
Notion support is intentionally read-only at the tool surface:
notion({ action: "search", query: "..." })notion({ action: "read", pageId: "..." })Start every new session by setting the project first:
1. set_project({ path: "/absolute/path/to/project" })
2. recall()
3. structure({ depth: 2 })
4. read_file({ path: "src/index.ts" })
5. remember({ type: "decision", content: "Use SQLite for local storage" })
Recommended pattern:
set_project once per project/session startrecall to recover contextstructure and search to exploreread_file for focused inspectionremember when something should survive the current sessionWhen you run set_project inside a git repository, Context Sync can install hooks for automatic context capture.
Installed hooks:
post-commitpre-pushpost-mergepost-checkoutHooks are marked with Context Sync Auto-Hook, and existing hooks are backed up first.
The git tool supports:
statuscontexthotspotscouplingblameanalysisDefault locations:
~/.context-sync/data.db~/.context-sync/config.json~/.context-sync/install-status.jsonCustom database options:
context-sync --db-path /absolute/path/to/dbCONTEXT_SYNC_DB_PATHSee docs/DATA.md for storage details.
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y @context-sync/serverMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-intina47-context-sync": {
"command": "npx",
"args": [
"-y",
"@context-sync/server"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup reference@context-sync/servernpmio.github.Intina47/context-sync works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.