Built-in tools that the agent can call (via function/tool calling).
- Core tool toggles live in
preferences/runtime-config.json(dashboard: Settings). - Official integrations such as browser, Brave Search, Tavily Search, Firecrawl, Perplexity Sonar, weather, and mail are loaded through the plugin runtime and keep their own configuration under
preferences/plugins/<owner>/<plugin>.json. - File and shell access are sandboxed to the tool workspace (
bot.tools.*.workspace). - Destructive actions may require user confirmation when tool confirmations are enabled.
Core tools are controlled via runtime-config.json under tools and security:
{
"tools": {
"filesystemEnabled": true,
"shellEnabled": true,
"skillManagementEnabled": true,
"skillTransitionEnabled": true,
"tierEnabled": true,
"goalManagementEnabled": true,
"shellEnvironmentVariables": []
},
"security": {
"toolConfirmationEnabled": false,
"toolConfirmationTimeoutSeconds": 60
}
}Plugin-owned tool settings are stored separately, for example:
preferences/plugins/golemcore/browser.jsonpreferences/plugins/golemcore/brave-search.jsonpreferences/plugins/golemcore/tavily-search.jsonpreferences/plugins/golemcore/firecrawl.jsonpreferences/plugins/golemcore/perplexity-sonar.jsonpreferences/plugins/golemcore/weather.jsonpreferences/plugins/golemcore/mail.json
File and shell tools operate only inside the configured workspace:
bot.tools.filesystem.workspacebot.tools.shell.workspace
In Docker, set these via env and mount volumes:
docker run -d \
-e STORAGE_PATH=/app/workspace \
-e TOOLS_WORKSPACE=/app/sandbox \
-v golemcore-bot-data:/app/workspace \
-v golemcore-bot-sandbox:/app/sandbox \
-p 8080:8080 \
golemcore-bot:latestThe dashboard embedded IDE uses direct authenticated HTTP endpoints under /api/files.
This API is separate from the filesystem tool used by the agent tool loop.
- Dashboard IDE API (
/api/files) is deterministic UI/backend integration. filesystemtool is an LLM-callable tool with tool-loop semantics.
Both are sandboxed to the configured filesystem workspace root.
Sandboxed file operations (read/write/list/create/delete/send) under the tool workspace.
Operations:
read_file,write_file,list_directory,create_directory,delete,file_info,send_file
Sandboxed command execution under the tool workspace.
Input fields:
command(required)timeout(seconds; default/max enforced)workdir(relative to tool workspace)
Headless browsing (Playwright) to extract page text, html, or capture screenshot.
Provided by the official golemcore/browser plugin.
Input fields:
url(required)mode:text|html|screenshot
Web search via Brave Search API.
Provided by the official golemcore/brave-search plugin.
Configure it in Settings or preferences/plugins/golemcore/brave-search.json.
Web search via Tavily Search API with optional answer synthesis and advanced retrieval depth.
Provided by the official golemcore/tavily-search plugin.
Configure it in Settings or preferences/plugins/golemcore/tavily-search.json.
Remote webpage scraping via Firecrawl /v2/scrape.
Provided by the official golemcore/firecrawl plugin.
Configure it in Settings or preferences/plugins/golemcore/firecrawl.json.
Grounded synchronous completions via Perplexity Sonar with selectable search model.
Provided by the official golemcore/perplexity-sonar plugin.
Configure it in Settings or preferences/plugins/golemcore/perplexity-sonar.json.
Create/list/get/delete skills at runtime (writes under workspace/skills/ in the storage workspace).
Switch active skill/pipeline step.
Switch model tier mid-conversation (balanced, smart, coding, deep).
Auto Mode goal/task/diary management.
Plan-work tools for canonical plan drafting (SSOT).
- Advertised only when plan mode is active for the current session.
plan_getreturns the current canonical Markdown plan draft.plan_set_contentaccepts full Markdown inplan_markdown(optionaltitle) and requests finalization.- Persistence/finalization is handled by
PlanFinalizationSystem;plan_set_contentis a deterministic control signal. - Finalizing a draft makes the plan
READY, while plan work remains active until/plan doneor/plan off.
Structured memory operations for autonomous workflows.
Operations:
memory_search: search memory by querymemory_read: read specific items by id, fingerprint, or querymemory_expand_section: ask for more detail from a compact prompt section such as semantic facts or recent episodesmemory_add: write a semantic/procedural memory itemmemory_update: update an existing semantic/procedural memory itemmemory_promote: promote matching memories into a longer-lived layermemory_forget: forget matching memories by id, fingerprint, or query
This tool uses Memory V2 APIs (no direct filesystem assumptions for memory writes).
When progressive disclosure is enabled, memory_read and memory_expand_section are the main "show me more" operations.
Email tools.
Provided by the official golemcore/mail plugin.
Configured in Settings or preferences/plugins/golemcore/mail.json.
Synthesize and send voice responses (when voice is enabled and configured).
Built-in utility tool.
Weather lookup provided by the official golemcore/weather plugin.