AI CLI Command Cheatsheet

Full command reference for Open Interpreter, a terminal AI coding agent: install and launch, --local local models, -y auto-accept, --os OS control, --api_base custom endpoint, resume --last session restore and /model interactive commands, all matched to official docs.

Full flag reference for llama.cpp llama-cli inference tool: model load -m, interactive -i, GPU offload -ngl, context -c, threads -t, temperature --temp and conversation -cnv, all matched to official docs.

Full command reference for MLC-LLM mlc_llm CLI: chat interactive, serve local server, convert model, plus --device, --quantization, --model-lib flags, all matched to official docs.

Full command reference for LocalAI local-ai CLI: run and serve to start, models list/install/pull for management, api and finetune commands, all matched to official docs.

Full command reference for LM Studio lms CLI: status, ls and ps to list models, get to download, load and unload, server start, and terminal chat, all matched to official docs.

Full command reference for GPT Engineer gpte and gpt-engineer CLI: create projects, improve code with -i, --model selection, --steps workflows, and --temperature, all matched to official docs.

Full command reference for Mentat CLI: pass files or dirs as context, --exclude to drop paths, --auto-context retrieval, --model switch, --mcp-server for tools, and /include interactive commands, all matched to official docs.

Full command reference for CrewAI crewai CLI: create crew, run, train, flow workflows, tool management, and install, all matched to official docs.

Full command reference for Phidata phi CLI: init, auth, config, ws create/up/down workspace management, start/stop resource deploy, all matched to official docs.

Full command reference for Tabby tabby CLI: serve to start, --model/--device/--port flags, download models, scheduler to trigger indexing, and OpenAI-compatible API calls, all matched to official docs.

Full command reference for Open WebUI open-webui CLI: serve to start, --port and --host flags, DATA_DIR, pip install and update, Docker and K8s deploy, all matched to official docs.

Full command reference for gptme CLI: start a chat, -m model, -t tools, -y auto-confirm, -n non-interactive, --output-format json, resume, and tools/chats/models subcommands, all matched to official docs.

Full flag reference for SGLang launch_server: --model-path, --host and --port, --tp and --dp parallelism, --mem-fraction-static VRAM, --quantization, and --trust-remote-code, all matched to official docs.

Full command reference for Tabnine CLI: tabnine to start, /help /model /clear /settings slash commands, -p non-interactive mode, TABNINE_TOKEN auth, and tabnine-opencode integration, all matched to official docs.

Command reference for Hermes Agent, Nous Research open-source, model-agnostic terminal AI agent: install, model & tool configuration, message gateway, and setup wizard, covering hermes model, hermes tools, hermes config set, and hermes gateway.

Command reference for Kilo Code CLI, the terminal AI coding agent sharing an engine with the IDE extensions: install, interactive & one-off tasks, and model integrations, covering kilo run, kilo --mode, kilo --auto, kilo auth, and kilo mcp.

Command reference for Pi, the earendil-works multi-model terminal coding agent: install, interactive sessions, headless mode & scripting, and session/model management, covering pi -c, pi -p, pi @file, /login, and /model.

Command reference for Kimi Code CLI, Moonshot AI terminal AI coding agent wired to Kimi models: install, interactive & single instructions, and sessions & models, covering kimi -p, kimi -C, /login, /init, and /model.

Command reference for Grok CLI, the xAI Grok Build terminal AI coding agent: install, interactive sessions, session management, headless mode, and scripting, covering grok -p, grok inspect, XAI_API_KEY, and /model.

Command reference for Warp Agent CLI, the AI coding agent built into the Warp terminal: install, core agent commands, MCP integration, and cloud agents, covering /agent, /model, /plan, /orchestrate, /mcp, and oz agent run.

Command reference for Crush, the Charmbracelet Rust single-binary terminal AI coding agent: install, sessions & modes, and configuration, covering crush --yolo, /model, and crush logs.

Command reference for Antigravity CLI (Google terminal AI coding agent, command `agy`): install, sessions & planning, and tools & integrations, covering agy, /model, /planning, /mcp, and /permissions.

Command reference for Plandex, the terminal planning open-source AI coding agent (alias pdx): install, plan & load, and execute & iterate, covering plandex new, plandex load, plandex tell, and OPENROUTER_API_KEY.

Command reference for Amazon Q Developer CLI, AWS official terminal AI coding agent: install, login, chat, one-line queries, and Agent mode, covering brew install amazon-q, q chat, q one-line queries, and /q slash commands.

Command reference for Sourcegraph Amp, the terminal AI coding agent: install, login, one-shot prompts, background execution, and thread management, covering @sourcegraph/amp, amp prompts, amp -x background tasks, and amp threads.

Command reference for LiteLLM, unified OpenAI-compatible gateway for 100+ LLMs: proxy launch, provider-prefix routing, config-file mode, and self-test, covering litellm --model, litellm --config, and litellm --test.

Command reference for vLLM, the high-performance LLM inference & serving engine: install, OpenAI-compatible server launch, host/port/API-key configuration, and quantization, covering pip install vllm, vllm serve, and --host/--port/--api-key.

Command reference for llamafile, Mozilla single-file local LLM runner: download & run, OpenAI-compatible server, GGUF loading, GPU layers, and temperature, covering ./xxx.llamafile --server, --nobrowser, -m, --ngl, --temp.

Command reference for Continue CLI (cn, open-source terminal coding agent sharing the engine with the VS Code/JetBrains extensions): install, interactive session, headless mode, login, and thread resume, covering cn, cn -p, cn login, and cn --resume.

Command reference for OpenCode, the open-source Claude Code-style TUI terminal AI coding agent: launch & resume, CLI flags, session and subcommands (agent/auth/github/mcp/run/serve/web), and interactive slash commands.

Command reference for Goose, the open-source general-purpose terminal AI agent (Rust, Apache-2.0, 15+ providers, 70+ MCP extensions; orig. Block, now Linux Foundation AAIF): sessions, runtime, configure, extensions, and diagnostics, including goose session/run/configure/cook/doctor and --resume.

Command reference for OpenHands, the open-source autonomous coding agent that can write a whole repo: launch, task execution, approval modes, resume/headless, Web/ACP/Cloud, MCP management, and config, including openhands -t/--yolo/--resume/--headless and openhands mcp.

Command reference for Cline, one of the most popular VS Code AI coding extensions (formerly Claude Dev, Apache-2.0, multi-provider, Plan & Act modes): command palette entries, @ context references, Plan/Act workflows, and config.

Command reference for Ollama, the de-facto open-source local LLM runtime: run, pull/push, model management, Modelfile customization, serve, and config, including ollama run/pull/list/ps/create and Modelfile FROM/PARAMETER/TEMPLATE/SYSTEM.

Command reference for Qwen Code, Alibaba Qwen open-source AI coding CLI (Claude Code-like, built on Qwen3-Max / Qwen3-Coder): install, launch, print mode, slash commands, and MCP, including qwen -p, /init, qwen mcp, and DASHSCOPE_API_KEY.

Command reference for GitHub Copilot CLI (gh CLI extension): explain commands, generate shell suggestions, aliases, and config, covering gh copilot explain/suggest/alias/config and @copilot.

Full command reference for Claude Code, Anthropic terminal AI coding agent: install & auth, -p print mode and session resume, --permission-mode/--worktree, dev slash commands, MCP server management, and @ file references, all flags matching official docs.

Command reference for OpenAI Codex CLI, the Rust-built terminal coding agent: install & auth, interactive and non-interactive codex exec, session management, model & config, sandbox and approval modes, MCP, and Codex Cloud.

Command reference for Gemini CLI, Google open-source (Apache 2.0) terminal AI agent: install & auth, run modes and global flags, session slash commands, MCP/extension management, and GEMINI.md project memory, with a 2M context.

Command-line and Cursor Agent reference for Cursor, the VS Code-based AI editor: opening files/folders, window management, diff compare, extension management, rendering & performance, remote dev, debugging, cursor-agent non-interactive calls, and git core.editor integration.

Command reference for Aider, the open-source Apache 2.0 terminal AI pair programmer (100+ models, auto git commits): install, model & reasoning, files & context, chat modes, Git & run, session tools, and advanced usage.