Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 100% on LongMemEval, 99% token savings. 44 MCP tools. Fully local, zero cost.
接入配置
选择客户端,复制配置,再按项目文档补齐环境变量。
claude mcp add context-mem -- npx -y context-mem~/.codex/config.toml
[mcp_servers.context-mem]
command = "npx"
args = ["-y", "context-mem"]
# codex mcp add context-mem -- npx -y context-mem~/.cursor/mcp.json
{
"mcpServers": {
"context-mem": {
"command": "npx",
"args": [
"-y",
"context-mem"
]
}
}
}.vscode/mcp.json
{
"servers": {
"context-mem": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"context-mem"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"context-mem": {
"command": "npx",
"args": [
"-y",
"context-mem"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"context-mem": {
"command": "npx",
"args": [
"-y",
"context-mem"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"context-mem": {
"command": "npx",
"args": [
"-y",
"context-mem"
]
}
}
}