0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
0
1
x: 0y: 0z: 0
Agent-native model capability network

Autonomous model routing for agents

Buyer agents discover verified model capabilities. Provider nodes publish GPT, Claude, DeepSeek, Kimi, GLM, Qwen or local models. Crucible routes by price, latency, policy and trust.

Buyer Agent

Sends intent and policy

Crucible Router

Price / latency / trust

Provider Node

Cross-region model capability

Receipt

Metered audit record

# Any OpenAI-compatible agent changes one base_url

export OPENAI_BASE_URL=

"https://api.a2a-crucible.xyz/v1"

model =

"best:coding.high_reasoning"

returns route + receipt

Routing policy

quality-first

Candidates

provider nodes

Receipt

rcpt_*

Failover

< 30s

Provider nodes can expose these model capabilities

GPT
Claude
DeepSeek
Kimi
GLM
Qwen
OllamaLocal
0+

Model families

0

Routing signals

0

Entry points

<0s

Failover target

Three Autonomous Loops

Buyer agents discover, provider nodes list, and the platform routes and supervises

1
Buyer Loop

Intent-Based Discovery

Buyer agents ask for capabilities, quality, latency, privacy and budget instead of choosing a fixed vendor

{
  "capability": "coding.high_reasoning",
  "max_price": 0.05,
  "privacy": "no_retention"
}
2
Provider Loop

Autonomous Listing

Provider nodes publish model families, price policy, current load, health and service constraints

{
  "models": ["claude", "deepseek"],
  "load": 0.42,
  "region": "asia"
}
3
Platform Loop

Policy-Aware Routing

Crucible matches requests to nodes by price, latency, region, trust score and failure history

{
  "route": "node_8f2a",
  "score": 0.94,
  "fallbacks": 2
}
4
Trust Loop

Meter and Score

Every invocation produces usage receipts, audit logs, health updates and quality feedback

{
  "receipt": "rcpt_2dbb9a53",
  "tokens": 1842,
  "latency_ms": 912
}

A2A-Crucible Core Protocol

intent → discover → route → invoke → meter → score

Agent Card|OpenAI-compatible|Metering
Model Routing Policies

Agents choose capabilities, not vendors

Crucible abstracts model providers into routable capabilities and selects provider nodes by task type, price, latency, region and trust score.

High-Reasoning Coding

best:coding.high_reasoning

For review, debugging, architecture and hard refactors.

ClaudeGPTDeepSeek Reasoner
Policyquality first

Low-Cost Reasoning

cheap:reasoning

For batch analysis, agent background work and retryable tasks.

DeepSeekGLMQwen
Policycost first

Long-Context Chinese

best:zh.long_context

For Chinese documents, knowledge work and large context windows.

KimiGLMQwen
Policycontext first

Local Private Node

private:local

For internal agents that need data locality and no-retention policy.

OllamavLLMCustom
Policyprivacy first

Price

budget caps

Latency

SLA targets

Region

cross-border routes

Trust

health and receipts

client.invoke("best:coding.high_reasoning", prompt, policy={"max_price": 0.05, "privacy": "no_retention"})
Seed Provider Network

Turn idle model capacity into agent-discoverable nodes

The early goal is not payout promises. It is a small, stable Provider Node network with observable models, regions, price, heartbeat, readiness and receipts.

3-5

Seed nodes

15s

Heartbeat

rcpt_*

Receipts

5-minute Provider Node path
CRUCIBLE_AUTO_REGISTER=true \
CRUCIBLE_API_BASE_URL=https://api.a2a-crucible.xyz/api \
CRUCIBLE_NODE_PUBLIC_URL=https://your-node.example.com \
PROVIDER_NODE_MODELS=best:coding.high_reasoning,cheap:reasoning \
node scripts/provider-node.mjs

Configure upstream key or local model

Auto-register and report heartbeat

Enter cross-region routing candidates

Expose upstream or local models

Provider Node can relay OpenAI-compatible upstreams or wrap Ollama, vLLM and custom services.

OpenAI-compatibleOllamavLLM

Auto registration and heartbeat

Nodes list capabilities on startup and report latency, success rate, queue and memory signals.

heartbeathealthload

Signed invocation endpoint

Optional HMAC verification protects Provider Node capacity from non-platform calls.

HMACnoncetimestamp

Receipts build trust

Every routed invocation creates a receipt for trust score, audit and future billing plugins.

receiptmeteringtrust
The seed stage validates that a node can be listed, discovered, probed and metered. Buyer agents, arbitrage agents and secondary routers can enter once supply is stable.
Infrastructure, not a cash pool

Discovery, routing, metering and trust first

Payments can arrive later as integrations. The core product is reliable discovery, invocation and evaluation of model provider nodes.

OpenAI-compatible Gateway

Connect existing agents through a base_url change

Agent Cards

Describe provider node models, capabilities and policies

Heartbeat

Live health checks, load reporting and delisting

Routing Engine

Route by price, latency, region and trust score

Metering Receipts

Record invocations, usage, latency, cost and audit trails

Trust Score

Turn success rate, SLA, feedback and failures into scores

Future billing can support x402, Stripe Connect, invoices and BYOK, but it is no longer the hero of the product.