🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add forkmind -- npx -y forkmind~/.codex/config.toml
[mcp_servers.forkmind]
command = "npx"
args = ["-y", "forkmind"]
# codex mcp add forkmind -- npx -y forkmind~/.cursor/mcp.json
{
"mcpServers": {
"forkmind": {
"command": "npx",
"args": [
"-y",
"forkmind"
]
}
}
}.vscode/mcp.json
{
"servers": {
"forkmind": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"forkmind"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"forkmind": {
"command": "npx",
"args": [
"-y",
"forkmind"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"forkmind": {
"command": "npx",
"args": [
"-y",
"forkmind"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"forkmind": {
"command": "npx",
"args": [
"-y",
"forkmind"
]
}
}
}