Other AI agents
Cursor, Copilot, Codex, Gemini, and any tool without native MCP.
Two modes
For non-Claude agents, larkx supports two integration patterns:
- Native MCP, if the agent supports MCP (Cursor, Continue, Cline)
- Instruction file + CLI context, the agent reads
larkx contextoutput instead of calling tools (Copilot, ChatGPT, Codex, Gemini)
Cursor
Cursor supports MCP natively. Add larkx in Settings → MCP:
{
"mcpServers": {
"larkx": {
"command": "larkx",
"args": ["mcp"]
}
}
}Then run larkx init in your project to create .cursorrules.
GitHub Copilot
Copilot doesn't expose tool-calling for arbitrary MCP servers, so it uses the instruction file pattern. larkx init creates .github/copilot-instructions.md with a directive to run larkx context at the start of any task.
OpenAI Codex
Codex reads AGENTS.md. Run larkx init and select OpenAI Codex. The generated AGENTS.md tells Codex to fetch larkx context before opening files.
Gemini CLI
Gemini reads GEMINI.md. Same flow, larkx init creates the file with the right instructions.
Check the CLI
larkx --version
# → larkx v0.1.0If the command is not found, make sure your Node global bin is on PATH.
Check the index
larkx statsShould print file counts, detected frameworks, and per-level token estimates.
If the index is empty, run larkx index first.
Check the context file
cat .larkx/context.mdThe file should exist and contain a compact project snapshot. If it is missing or empty, run larkx index.
Verify file-based integration
After running larkx index, confirm this file exists:
cat .larkx/context.mdThe file should contain a compact project map. If it is missing or empty, rerunlarkx index.
Then ask your non-MCP agent a question like:
- "What files contain authentication logic?"
- "Where is the login handler defined?"
The instruction file should direct the agent to read larkx context first before opening source files.
- If Copilot still dives into source files, confirm .github/copilot-instructions.md was created and includes larkx context.
- If Codex or Gemini ignores the context file, reopen the terminal or chat session so it reloads project instructions.
- For any agent, use larkx context --folder src/path or --level 1 to keep the prompt small.
- Run larkx stats to verify the index is built and the project is recognized.
Universal fallback
For any other tool, just pipe context output into your conversation:
larkx context > project-context.md
# then paste into ChatGPT / Claude.ai / wherever--folder src/auth to limit context to a subtree, or --level 1 for just file paths. Both work in any agent that can read text.