Capabilities Overview

Capabilities are modular units that extend what an agent can do. Each capability can contribute:

Tools: callable functions the agent can invoke during conversations
System prompt additions: context and instructions prepended to the agent’s prompt
Features: UI elements unlocked when the capability is active (e.g., Workspace tab)

Agents compose capabilities, enable only what you need.

Capability Reference

Core

Fundamental capabilities for file operations, command execution, web access, session management, time awareness, task tracking, scheduling, and agent coordination.

Capability	ID	Tools
File System	`session_file_system`	6
Bashkit Shell	`bashkit_shell`	1
Session	`session`	2
Storage	`session_storage`	2
Web Fetch	`web_fetch`	1
Current Time	`current_time`	1
Message Metadata	`message_metadata`	0
Task Management	`stateless_todo_list`	1
Schedules	`session_schedule`	3
Auto-Continue After Usage Limit	`usage_limit_auto_continue`	0
Sub Agents	`subagents`	3
AGENTS.md	`agent_instructions`	0
Agent Skills	`skills`	2

Sandboxes

Cloud and container sandbox environments for isolated code execution.

Capability	ID	Tools
Daytona	`daytona`	10
Deno Sandboxes	`deno`	6
E2B	`e2b`	6
Docker Container	`docker_container`	5

Browser

Browser automation and web interaction capabilities.

Capability	ID	Tools
Browserless	`browserless`	7

Data

Structured data and knowledge capabilities.

Capability	ID	Tools
SQL Database	`session_sql_database`	3
Retrieval Citations	`citation_retrieval`	0
Citation Verification	`citation_verification`	0

Media

Image generation and editing workflows.

Capability	ID	Tools
OpenAI Image Generation	`gpt_image_gen`	2

Tools

Provider-executed and built-in tool capabilities.

Capability	ID	Tools
OpenRouter Server Tools	`openrouter_server_tools`	0

Integrations

External-service capabilities and blueprint-backed workflows.

Capability	ID	Tools
GitHub Scout	`github_scout`	0

Platform

Agent self-management and platform control.

Capability	ID	Tools
Platform	`platform`	3
Platform Management (legacy)	`platform_management`	14

Optimization

Performance and cost optimization for LLM interactions.

Capability	ID	Tools
Infinity Context	`infinity_context`	1
Auto Tool Search	`auto_tool_search`	1
OpenAI Tool Search	`openai_tool_search`	0
Claude Tool Search	`claude_tool_search`	0
Tool Search	`tool_search`	1
Budgeting	`budgeting`	1
Self-Budget	`self_budget`	0
Parallel Tool Calls	`parallel_tool_calls`	0

Safety

Streaming-output guardrails and runtime safety nets.

Capability	ID	Tools
Prompt Canary Guardrail	`prompt_canary_guardrail`	0
Tool Call Repair	`tool_call_repair`	0
Guardrails	`guardrails`	0

The guardrails capability runs config-driven checks over model output and tool activity, blocking or logging per check. Checks can be deterministic (regex, blocklist, tool-call patterns) or model-backed, an llm_judge policy or a moderation classifier, plus delegation to an external guardrail over scoped MCP. Each check binds a rule to a stage (output, tool_use, tool_output) with an on_fail of block or log; model-backed and MCP checks send a bounded excerpt off the sync path and fail open. Use advisory mode and the POST /v1/capabilities/guardrails/dry-run endpoint to tune against false positives before enforcing. For ready-made starting points, list the gallery at GET /v1/capabilities/guardrails/examples, each preset carries a data_egress signal (none vs. utility_llm), and drop a preset’s config into the agent’s guardrails capability config.

Automation

Run shell commands at lifecycle and tool events. Block, mutate, or audit agent actions from outside the model.

Capability	ID	Tools
User Hooks	`user_hooks`	0

Demo

Pre-built domain simulations for testing and demonstrations.

Capability	ID	Tools
Fake Warehouse	`fake_warehouse`	10
Fake AWS	`fake_aws`	11
Fake CRM	`fake_crm`	8

Quick Start

Enable via API

curl -X POST http://localhost:9300/api/v1/agents \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Agent",
    "system_prompt": "You are a helpful assistant.",
    "capabilities": ["session_file_system", "bashkit_shell", "web_fetch"]
  }'

Enable via UI

Navigate to the Agent detail page
Open the Capabilities section
Toggle capabilities on/off
Reorder with drag handles (order affects system prompt priority)
Save

List available capabilities

curl http://localhost:9300/api/v1/capabilities

Create a declarative capability

Declarative capabilities are persisted capability definitions made from data: system prompt text, scoped MCP servers, text file mounts, and skill packages. They use a public resource ID like cap_... and a stable capability reference like declarative:research_pack.

curl -X POST http://localhost:9300/api/v1/capabilities \
  -H "Content-Type: application/json" \
  -d '{
    "definition": {
      "name": "research_pack",
      "display_name": "Research Pack",
      "description": "Default research behavior and resources.",
      "system_prompt": "Prefer primary sources and cite them clearly.",
      "risk_level": "low"
    }
  }'

Agents and harnesses can use the canonical reference:

{ "ref": "declarative:research_pack" }

For convenience, agent and harness write APIs also accept the plain unique name when it matches a declarative capability:

{ "ref": "research_pack" }

Key Concepts

Dependencies

Some capabilities depend on others. Dependencies are resolved automatically at runtime, you don’t need to manually add them.

Capability	Depends On
Bashkit Shell	File System
Agent Skills	File System
GitHub Scout	Sub Agents
Deno Sandboxes	Storage
E2B	Storage

Features

Capabilities declare UI features they contribute. The session aggregates features from all active capabilities to decide which UI tabs to render.

Feature	UI Element	Contributed By
`file_system`	Workspace tab	File System, Bashkit Shell
`secrets`	Storage tab	Storage
`key_value`	Storage tab	Storage
`schedules`	Schedules tab	Schedules
`sql_database`	Database tab	SQL Database
`subagents`	Subagents tab	Sub Agents
`citations`	Inline citation chips + Sources strip	Retrieval Citations, Citation Verification

Ordering

Capabilities are applied in the order configured on the agent. Earlier capabilities’ system prompt additions appear first. Place the most important context-setting capabilities first.