Wireclaw agents have access to 30+ built-in tools across 8 categories. Enable them in your agent config:
enabled = ["web_search", "browser", "shell", "file_read", "file_write"]
| Tool | Description |
|---|
web_search | Search the web via DuckDuckGo or Brave. Returns titles, URLs, and snippets. |
web_fetch | Fetch a URL and convert HTML to Markdown. Useful for reading articles, docs, pages. |
http_request | Make raw HTTP requests (GET, POST, PUT, DELETE). For APIs, webhooks, external services. |
domain_allowlist = ["docs.example.com", "*.github.com"]
domain_allowlist = ["api.example.com"]
| Tool | Description |
|---|
browser | Full browser automation via Playwright — screenshot, click, fill, navigate, evaluate JavaScript. |
The browser tool gives agents a real browser for interacting with dynamic web pages, filling forms, and capturing screenshots.
domain_allowlist = ["*.wikipedia.org", "arxiv.org"]
| Tool | Description |
|---|
file_read | Read files from the agent’s workspace. |
file_write | Write or create files in the workspace. |
file_edit | Edit existing files with search-and-replace operations. |
glob_search | Find files by glob pattern (e.g., **/*.md). |
content_search | Search file contents with regex patterns. |
File operations are scoped to the agent’s workspace directory — agents cannot access files outside their workspace.
| Tool | Description |
|---|
shell | Execute shell commands in a sandboxed environment. |
sandbox = "landlock" # Options: landlock, bubblewrap, firejail, docker
domain_allowlist = ["api.github.com"] # Network access restrictions
Sandbox backends:
| Backend | OS | Isolation |
|---|
landlock | Linux 5.13+ | Filesystem access control |
bubblewrap | Linux | Container-like isolation |
firejail | Linux | Security sandbox |
docker | Any | Full container isolation |
| Tool | Description |
|---|
memory_store | Store a key-value pair in persistent memory. |
memory_recall | Retrieve stored memory by key or semantic search. |
memory_forget | Delete a memory entry. |
Memory persists across sessions and restarts. See the [memory] section in Agent Config.
| Tool | Description |
|---|
cron | Create, list, update, remove, and run scheduled tasks. |
schedule | Schedule a one-time future action. |
Agents can schedule recurring tasks (e.g., “check this URL every hour”) or delayed actions.
| Tool | Description |
|---|
pdf_read | Extract text and structure from PDF files. |
| Tool | Description |
|---|
delegate | Call another agent to handle a subtask. |
pushover | Send push notifications via Pushover. |
Control how much oversight tools require:
| Level | Behavior |
|---|
autonomous | Tools execute without approval (default). |
guided | Tools execute but all actions are logged. |
supervised | Tools require explicit user approval before execution. |
autonomy = "supervised" # Require approval for all tool actions