Skip to main content

​
What Are Tools?

Tools are how an ArgentOS agent takes action. When the agent needs to run a command, search the web, recall a memory, or manage a task, it invokes a tool. Each tool is defined as a JSON schema, validated at runtime, and governed by the agent’s intent policies and sandbox mode. The agent selects tools automatically based on conversational context. You do not need to tell it which tool to use — ask for what you need and the agent routes to the right capability.

​
Tool Catalog

File & Code

read, write, edit, bash, glob, grep — full filesystem and shell access

Web & Research

browser, web_search, web_fetch, firecrawl — browse, search, scrape

Memory

memory_store, memory_recall, memory_timeline — persistent agent memory

Tasks

tasks — 15+ actions for full task lifecycle management

Knowledge & Library

knowledge_search, knowledge_ingest, knowledge_collections — RAG library with ACL

Communication

outbound_message, channel_send — multi-channel delivery

Media & Display

sag, image_gen, doc_panel, canvas — speech, images, document panels

System & Config

os_docs, health, config, gateway, backup — system operations

Marketplace

marketplace_search, marketplace_install, marketplace_publish — package management

​
File & Code

​
Web & Research

​
Memory

​
Tasks

​
Knowledge & Library

​
Communication & Channels

​
Media & Display

​
System & Configuration

​
Marketplace

​
Automation & Scheduling

​
Project Management

​
How Tools Activate

Tools are selected by the LLM based on context. The flow:
1

LLM returns a tool call

The LLM returns a tool_use block with the tool name and input parameters.
2

Schema validation

The agent runtime validates input against the tool’s JSON schema.
3

Policy and sandbox check

Intent policies and sandbox mode are checked.
4

Tool executes

The tool handler executes and returns a result.
5

Result feeds back

The result feeds back to the LLM as a tool_result block.
You can guide tool selection by being specific (“search my memory for…” or “create a task to…”), but explicit tool names are never required.

​
Tool Governance

The Intent System controls which tools an agent can use. Intent policies define allowedActions and requiresHumanApproval lists that restrict tool access at three levels:
  • Global — baseline restrictions for all agents
  • Department — narrowed per department (e.g., Support agents cannot use bash)
  • Agent — per-agent overrides (most restrictive wins)
Policies are monotonic: child levels can only tighten constraints, never loosen them. If Global allows a tool but the Department policy removes it, no agent in that department can use it.

​
Sandbox Modes

Tool execution is gated by the agent’s security mode: See Sandboxing for configuration details.

​
Extending Tools

Plugins can register new tools at startup. See Plugins. Skills bundle tools with prompts into loadable capability packages. See Skills.