Agents Overview
Asset Core provides production-ready adapters for AI agent integration, enabling models to manipulate state through a bounded, auditable operation set. The goal is to let automation act safely without expanding the attack surface or breaking deterministic replay.
Who this is for
Engineers building AI agents that need to interact with Asset Core state through a unified, tool-based interface. If you are integrating with MCP, OpenAI, or Gemini, this page is the conceptual starting point.
What you will learn
- Why Asset Core’s fixed operation set is ideal for agents
- How the canonical tooling surface maps to HTTP
- Where to find the full tool definitions and schemas
LLM Briefing Pack
Need a single, detailed file you can upload into your own LLM? The Asset Core LLM Briefing Pack covers the full mental model, mapping logic, guarantees, and fit guidance. It is English-only (most LLMs handle English well) and experimental; the canonical source of truth is the website. Use it as a guide, not a source of record. The intent is self-guided exploration: upload it, describe your domain, and let the model map Asset Core to your use case. You can also give an agent the canonical URLs: https://assetcore.io/ or https://assetcore.io/docs (strict CSP, no tracking), but not every page is guaranteed to be visited, so this pack keeps the core math, constraints, and decision guidance in one place.
- Open: Asset Core LLM Briefing Pack (17.5 KB, English-only)
- Download: Asset Core LLM Briefing Pack (.md) (17.5 KB, English-only)
When to use this
Use Asset Core as your agent’s state backend when you need:
- Auditability: Every state change is recorded
- Safety: Bounded operations prevent dangerous mutations
- Determinism: Reproducible behavior for testing and debugging
High-level structure
The Problem with Open-Ended APIs
AI agents can execute arbitrary actions, which creates risks. Without a bounded operation set, auditing and rollback become guesswork.
- Unbounded mutations can corrupt state
- No audit trail for what changed
- Hard to test and verify behavior
- Difficult to constrain permissions
Transactions as Safe Surface
Asset Core solves this by exposing exactly 24 operations. The fixed vocabulary makes automated access reviewable and enforceable.
| Domain | Operations |
|---|---|
| Container | CreateContainer, RemoveContainer |
| Balance | AddFungible, RemoveFungible, MoveFungible, TransferFungible, TransferMany, Distribute, MoveMany, MergeStacks, ConsolidateStacks |
| Instance | AddInstance, MoveInstance, RemoveInstance, BurnInstance, Attach, Detach |
| Slot | PlaceInSlot, RemoveFromSlot, SwapSlots |
| Schema | RegisterClass, RegisterClassShape, RegisterClassContinuousShape1d, RegisterClassContinuousShape2d |
This fixed vocabulary:
- Limits blast radius: Agents can only do these things
- Enables auditing: Every possible action is known
- Supports permissions: Filter operations by tag
- Simplifies testing: Finite state space
Protocol Adapters
Asset Core provides adapters that translate between AI protocols and HTTP. This keeps the tooling surface stable even as AI protocols evolve.
Agent → Adapter → HTTP API → Daemon
Available adapters:
| Protocol | Description | Transport |
|---|---|---|
| MCP | Model Context Protocol | STDIO, SSE |
| OpenAI | Function calling | HTTP |
| Gemini | Function declarations | HTTP |
All adapters expose the same tool surface, so switching protocols doesn’t require changing your Asset Core integration.
Adapter Architecture
Each adapter provides:
- Tool definitions matching the protocol’s schema
- Executor that maps tool calls to HTTP requests
- HTTP client for daemon communication
- Error handling with protocol-appropriate responses
The adapters live in the assetcore-adapters crate and share common infrastructure.
Tool Inventory
Standard tools across all adapters:
| Tool | Description |
|---|---|
assetcore_commit | Submit transactions to write daemon |
assetcore_write_health | Check write daemon health |
assetcore_read_health | Check read daemon health |
assetcore_read_freshness | Check projection freshness |
assetcore_read_stream | Stream commits with SSE cursors |
assetcore_list_containers | List containers with filters |
assetcore_get_container_contents | Unified container contents query |
assetcore_docs_search | Search static Asset Core docs |
tools/list | MCP tool discovery endpoint |
The commit tool accepts the same operation structure as the HTTP API, so agents can compose complex transactions.
Filtering by Tags
Operations have tags (domain, action, scope, reversibility) that enable filtering:
# Allow only read operations
allowed = [op for op in operations if op.action != "destroy"]
# Restrict to specific domains
allowed = [op for op in operations if op.domain in ["balance", "container"]]
This lets you build agents with different permission levels without changing the core system.
Next steps
- Tooling Guide - Canonical tool definitions
- Tooling Manifest - Machine-readable tool metadata
- Action Reference - Complete operation reference