cade-cli 0.15.9

Cade - The CLI Agent from Arcade.dev

Cade

The CLI agent from Arcade.dev. Coding, research, and everyday automation — driven from a terminal, a single shell pipe, or a long-lived daemon that replies over Telegram.

curl -fsSL https://arcadeagent.dev/install | sh   #  or:  uv tool install cade-cli  |  pip install cade-cli
cade login
cade

---

Highlights

• Three deployment modes from the same binary. Interactive chat (cade), one-shot or pipe (cade -m "…"), or a headless daemon that replies over messaging (cade serve).
• Tools from anywhere. Built-in local tools (filesystem / shell / git / search / tasks / memory), Arcade Cloud tools (Slack, GitHub, Gmail, calendars, …), and any MCP server you register — all unified under one tool surface.
• Bidirectional MCP. Tools can call context.ui.elicit(…) for structured input, context.log.* for live operator logs, and context.progress.report(…) for editable progress UI — routed end-to-end through whichever adapter is active (Telegram inline keyboard, terminal prompt).
• Agents + per-agent memory. Multiple agents, each with their own model, system prompt, tools, and an indexed memory store backed by agent-library.
• Extensibility surface. Hooks (lifecycle events), tasks (durable work), cron (scheduled prompts) — all available to the agent as Local_* tools and to you as cade <subcommand>.
• Bring your own LLM. OpenAI, Anthropic, or any OpenAI-compatible endpoint (Ollama, vLLM, Together, Groq, Fireworks, …). --local-only skips Arcade Cloud entirely.

---

Install

Source	Command
Install script (recommended)	curl -fsSL https://arcadeagent.dev/install | sh
uv	uv tool install cade-cli
pip	pip install cade-cli
From source	git clone https://github.com/arcadeai-labs/cade.git && cd cade && uv sync

The install script detects your OS/arch, downloads the matching prebuilt binary (macOS arm64, Linux x64), verifies its checksum, and drops cade in ~/.local/bin — no GitHub token required. Pin a version or install location:

CADE_VERSION=0.15.5 CADE_INSTALL_DIR=/usr/local/bin \
  sh -c "$(curl -fsSL https://arcadeagent.dev/install)"

On Linux the installer auto-picks a cpu or gpu build (GPU when nvidia-smi detects a card; the GPU build bundles the CUDA stack and is a much larger download). Force it with CADE_VARIANT=cpu or CADE_VARIANT=gpu.

(Windows: grab the .zip from the releases page, or pip install cade-cli.)

Prerequisites: Python 3.11+, an Arcade account (arcade.dev) for cloud tools, and an LLM provider key (OPENAI_API_KEY or ANTHROPIC_API_KEY). Skip the Arcade account with --local-only or CADE_LOCAL_ONLY=1.

The first run walks you through picking a model provider and key (stored in your OS keyring); re-run it any time with cade init.

cade init           # pick provider + model (runs automatically on first launch)
cade login          # Arcade Cloud OAuth (skip with --local-only)
cade --version

Full install and first-run docs: docs/install.md and docs/quickstart.md.

---

Quick start

cade                                       # interactive chat
cade -m "What changed in HEAD?"            # single message, then exit
cade -m "What went wrong?" < error.log     # prompt + file/stdin
cade resume                                # resume the most recent thread
cade resume "auth-rewrite"                 # resume a thread by name
cade use reviewer                          # switch the current agent
cade --voice                               # speak / hear (requires cade-cli[voice])

Top-level options

Flag	Description
-m, --message	Single-message mode; piped stdin is appended to the prompt
--voice	Voice mode; install cade-cli[voice] first
-v, --verbose	Debug logging
--version	Print version

In-chat slash commands

Command	Description
/help	List commands
/clear	Clear screen
/copy	Copy last response
/logs	Recent log entries
/thread, /history	Current thread info
/pin, /unpin	Pin reference material into the session
/tasks, /cron, /hooks, /notify	Coordination surfaces (mirrored as cade tasks / cade cron / cade hooks)
/usage	Context-window status and token usage
/cd, /pwd, /!	Shell shortcuts
Ctrl+C	Exit

---

Tools

Tools come from three sources and are addressed uniformly by their registered name:

• Local_* — built-in: filesystem (ReadFile, WriteFile, Edit, ListFiles), shell (Bash), Search, Git, Task*, AskUserQuestion, RetrieveToolResult, ToolSchema, PinContext, PushNotification, WebFetch, and WebSearch.
• Memory_* — agent-library backed, per-agent indexed knowledge store.
• Arcade Cloud + user MCP servers — anything you register.

cade tools list                         # all tools, all sources
cade tools list --source local          # filter by source
cade tools search "send slack"          # keyword search
cade tools info Local_ReadFile          # full schema + description

The full local tool surface (including the bidirectional MCP capabilities and cade serve integration) is documented in docs/mcp.md.

Custom MCP servers

cade mcp add my-server http://localhost:8080
cade mcp add my-server http://… --auth bearer -t <token>
cade mcp authorize my-server                      # OAuth flow (browser)
cade mcp list / status / test / enable / disable / rm

User MCP servers register on the agent's ~/.cade/config/agents/<name>.toml [[mcp]] list (with cade.toml [agent_defaults].mcp as the shared default). Servers with large catalogs are auto-deferred (parameter schemas stripped to keep tool-list bytes down) and fetched on demand via Local_ToolSchema.

---

Agents + memory

Each agent bundles a model, system prompt, tools, and memory. The current agent is ambient — most commands act on it.

cade new reviewer --prompt "You are a meticulous code reviewer."  # create + switch
cade list                                     # all agents
cade use reviewer                             # switch the current agent
cade info / cade edit reviewer                # inspect / change config

cade mem                                      # the current agent's memory (status)
cade mem add ~/notes                          # index a directory
cade mem search "auth design"                 # semantic search
cade mem warm                                 # pre-load the semantic memory model

Memory is per-agent — each agent has its own ~/.cade/data/agents/<id>/memory/.librarian/ index, so a reviewer agent's notes never leak into another. Cade advertises Memory_* tools without starting the memory server; the first actual memory call starts it and keeps it warm for later calls. Use cade mem warm when you want to pay that semantic-search warmup before a conversation.

---

Headless daemon: cade serve

Run Cade as a long-lived daemon that replies through adapters. Telegram is supported for personal bot workflows, and Desktop exposes a local WebSocket for native clients. Each conversation gets its own persistent thread — model, memory, and tools carry across messages.

cade serve init                          # wizard: bot token, allowed senders
cade serve                               # foreground (current agent)
cade serve --agent ops                   # serve a specific agent (one daemon per agent)
cade serve list                          # agents with a running daemon
cade serve --install launchd             # macOS LaunchAgent (or --install systemd)
cade serve status / stop                 # health, uptime; SIGTERM running daemon

Each agent's serve config lives in ~/.cade/config/agents/<name>.toml [serve]. Edit and kill -HUP $(cat ~/.cade/run/agents/<name>/serve.pid) to reload without restart.

Security defaults are fail-closed: allowed_senders = [] blocks everyone; tools are default-deny against [serve.tools].allow (globs / regex / pipe lists supported); deny always wins.

The MCP transport is fully bidirectional, so tools running inside the daemon can elicit structured input, stream live progress, and emit logs through whichever adapter is active. See docs/adapters/ for adapter details, docs/mcp.md for protocol details, and docs/configuration.md for the full daemon config reference.

---

Extensibility: hooks, tasks, cron

Three primitives the agent uses directly (as Local_* tools) and you can drive from the CLI:

Surface	What it is	CLI
Hooks	Lifecycle event handlers (pre/post tool, user prompt submit)	cade hooks list / add / remove / test
Tasks	Durable work units that survive turn boundaries	cade tasks list / get / create / update / delete
Cron	Scheduled prompts the agent runs on a timer	cade cron list / add / remove / enable / disable / run-now

Cross-agent messaging is set up with cade link / cade channel (an agent can only reach another it's been linked to). Hooks and tasks/cron details live in their respective cade <subcommand> --help outputs.

---

Bring your own LLM

Cade works with any OpenAI-compatible endpoint. Three ways to wire one in (CLI flag → env → config, first match wins):

# CLI flag for Ollama. Use a model from `ollama list`.
cade chat -L --endpoint http://localhost:11434 --model qwen3:4b

# Or create a dedicated agent for the local model
cade new local-qwen --model qwen3:4b
cade use local-qwen
export OLLAMA_BASE_URL="http://localhost:11434"
CADE_LOCAL_ONLY=1 cade -m "hello from a local model"

# Config — ~/.cade/config/cade.toml
[model_settings]
host = "http://localhost:8000/v1"
api_key = "ollama"

Skip Arcade Cloud authentication entirely with --local-only or CADE_LOCAL_ONLY=1 when running against local LLMs.

---

Configuration

All state lives under ~/.cade/. Override the location with CADE_HOME=/path/to/alt.

File	Purpose
config/cade.toml	Global settings + [agent_defaults] (model, provider, UI, …)
config/agents/<name>.toml	Per-agent config (model, prompt, [[mcp]], [serve], hooks)
data/agents/<id>/	Per-agent state: threads/ memory/ tasks/ inbox/
run/agents/<name>/	Per-agent daemon runtime: serve.pid, mcp-services, cron lease
logs/cade.log	Rotating log file

Full layout, env vars, and TOML schema in docs/configuration.md.

Common env vars

Variable	Purpose
OPENAI_API_KEY / ANTHROPIC_API_KEY	LLM provider keys
OPENAI_BASE_URL	Custom OpenAI-compatible endpoint
ARCADE_API_KEY, ARCADE_BASE_URL	Arcade Cloud (alternative to OAuth)
CADE_LOCAL_ONLY=1	Skip remote tools entirely
CADE_HOME	Override config directory
CADE_PROJECT_ROOT	Sandbox Local_* filesystem tools to this root

---

Contributing

git clone https://github.com/arcadeai-labs/cade.git
cd cade
uv sync --extra dev
uv run pytest
uv run ruff check src/ tests/

Style: Python 3.11+ with modern type hints (dict, list, | None); ruff for lint + format; pytest with asyncio_mode = "auto". Public functions and classes get docstrings.

Build/release docs live in docs/development.md. PRs welcome — open an issue first for anything substantial.

---

Resources

• arcade.dev — product
• docs.arcade.dev — API and tool catalog
• docs/ — quickstart, examples, install, config, MCP, channels, voice, development, and adapters
• Issues · Releases

License

MIT