Shared, git-tracked memory for AI agents on the same codebase. What one Claude/Cursor/Cline learns, the next one picks up. No DB, no SaaS — just files in your repo. CLI + MCP server.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add repo-memory -- uvx repo-memory-mcp~/.codex/config.toml
[mcp_servers.repo-memory]
command = "uvx"
args = ["repo-memory-mcp"]
# codex mcp add repo-memory -- uvx repo-memory-mcp~/.cursor/mcp.json
{
"mcpServers": {
"repo-memory": {
"command": "uvx",
"args": [
"repo-memory-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"repo-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"repo-memory-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"repo-memory": {
"command": "uvx",
"args": [
"repo-memory-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"repo-memory": {
"command": "uvx",
"args": [
"repo-memory-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"repo-memory": {
"command": "uvx",
"args": [
"repo-memory-mcp"
]
}
}
}