Long-term memory MCP server for OpenCode and other harnesses — stores preferences, lessons, and usage history in a single local SQLite file (100% local, no external API) so the AI can "remember and adapt" to the user through context-based learning.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add th-memory -- npx -y th-memory-mcp~/.codex/config.toml
[mcp_servers.th-memory]
command = "npx"
args = ["-y", "th-memory-mcp"]
# codex mcp add th-memory -- npx -y th-memory-mcp~/.cursor/mcp.json
{
"mcpServers": {
"th-memory": {
"command": "npx",
"args": [
"-y",
"th-memory-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"th-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"th-memory-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"th-memory": {
"command": "npx",
"args": [
"-y",
"th-memory-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"th-memory": {
"command": "npx",
"args": [
"-y",
"th-memory-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"th-memory": {
"command": "npx",
"args": [
"-y",
"th-memory-mcp"
]
}
}
}