| claude |
ai-agent |
YES |
Claude Code command-line agent: reads, edits and runs commands in a project directory with the permissions of the user who started it, filtered by the session's permission mode. |
| codex |
ai-agent |
YES |
OpenAI's Codex CLI agent: a native binary that edits files and runs commands in your repository under two settings, the sandbox mode that the operating system enforces and the approval policy that decides when it asks you. |
| gemini |
ai-agent |
YES |
Google's Gemini CLI agent: a Node.js process that reads, edits and runs commands in the current project with your user's permissions, approving tools by its approval mode. |
| ollama |
ai-agent |
RESTART INSTEAD |
Local LLM server: ollama serve loads models on demand and answers an unauthenticated HTTP API on 127.0.0.1:11434 by default; whoever can reach that port can run models, and read or feed them anything. |
| openclaw-gateway |
ai-agent |
RESTART INSTEAD |
The OpenClaw Gateway: a Node.js daemon that serves the Control UI, the WebSocket and HTTP API (/v1/*, /tools/invoke, /api/channels/*) on one port, 18789 by default, and runs the agent's tools, terminal and browser control behind it. |