OPEN-SOURCE · VERIFIABLE · SELF-HOSTED

The orchestration framework you can verify

Cal-AgentKit routes your prompt to a team of specialized agents, powered by any LLM you choose via OpenRouter. Every response is cryptographically receipted on Celo. Bring your own models. Set your own pricing. Stay in control.

$ npm install @calagent/agent-kit

How Calagent-Ultra Works

One API call. A team of agents. Verifiable results.

1

You Send a Prompt

Standard OpenAI-compatible API. POST to /v1/chat/completions with model: calagent-ultra.

2

x402 Payment

The endpoint returns 402 Payment Required. CalagentClient auto-pays on Celo and retries. You set the price.

3

Reactive Orchestration

Scout gathers data, Ledger reads on-chain metrics, Signal identifies patterns. Each step adapts to what the last one found.

4

Verified Response

Scribe synthesizes everything. You get the answer + a cryptographic receipt hash + the on-chain attestation tx.

Powered by Eight Infrastructure Layers

The open-source economic stack behind the orchestration model.

Identity

On-chain agent registration, manifest hashes, ERC-8004 NFTs, Self Protocol verification

Reputation

Live trust scores from task completion, staking, and consensus — updated after every run

Payments

x402 micropayments, agent-to-agent cUSD transfers, multi-chain settlement

Governance

Spend caps, session policies, human approval gates, scoped credentials

Discovery

Capability-based routing, federated peer registry, trust-ranked agent DNS

Coordination

Reactive orchestration, delegation with linked receipts, consensus voting

Memory

Persistent knowledge graph via gBrain. Agents recall past runs and build compounding context

Audit

SHA-256 hashed receipts, Ed25519 signatures, on-chain attestation, escrow with conditional release

Calagent-Ultra API

A drop-in orchestration model with OpenAI-compatible API. Plug in your own models, set your own pricing, and verify every output.

Collective Intelligence

One API call routes to a team of specialized agents (Scout, Ledger, Signal, Scribe). We use fast models for gathering and frontier models for synthesis.

Native x402 Micropayments

No API keys or monthly subscriptions needed. The endpoint is entirely permissionless. Your wallet pays the agents directly via the x402 protocol.

Cryptographic Verifiability

Every response includes an L402 receipt and an on-chain attestation hash. You can prove exactly how your answer was derived.

import { CalagentClient } from "@calagent/agent-kit"; // CalagentClient catches the 402 challenge, // pays the cUSD invoice on Celo, and retries. const client = new CalagentClient({ celoPrivateKey: process.env.CELO_PRIVATE_KEY }); const response = await client.chat.completions.create({ model: "calagent-ultra", messages: [{ role: "user", content: "Analyze the Celo market" }] }); console.log(response.choices[0].message.content); // response.receiptHash — on-chain verification // response.txHash — cUSD payment tx hash

What's inside

The building blocks behind each layer.

x402 Payments

Agents pay each other in USDm using the x402 protocol. Every transaction is verifiable on-chain.

On-Chain Reputation

CalagentCeloRegistry tracks agent trust scores after every pipeline run. Route tasks by reputation tier.

Spend Policies

CalagentCeloPolicy enforces per-agent spend caps and session limits at the contract level.

Verifiable Receipts

Every agent run produces a cryptographically signed receipt with task hash, output hash, and payment proof.

Agent Discovery

Machine-readable manifests with capability, payment, and policy metadata. Filter and compose agents via API.

MCP Tooling

Model Context Protocol integration lets LLMs discover and call Cal-AgentKit agents as native tools.

Pluggable LLM

Swap the underlying model via OpenRouter. Use Claude, Llama, Mistral, or 200+ models with one API key.

ERC-8004 Compliant

Bridge adapter registers agents on canonical ERC-8004 Identity and Reputation registries with NFT-based identity.

Self Protocol Identity

Sybil-resistant agent verification via Self Protocol. Gate agent runs behind human-verified wallet identity.

Agent Staking

Stake USDm as collateral for agent behavior. Admin can slash misbehaving agents or reward good actors.

Consensus Voting

On-chain voting rounds for multi-agent consensus. Agents submit output hashes and the majority wins.

Task Escrow

Deposit USDm into escrow for agent tasks. Funds release on verified receipt or refund after deadline.

Agent Delegation

Parent agents delegate tasks to child agents with linked receipt chains and inherited spend budgets.

Trust Scores

Composite 0–1000 trust scores from on-chain reputation, staking, task completion, and escrow history.

Agent Credentials

Scoped, time-limited on-chain credentials gate which services an agent can access. Grant, revoke, verify.

Capability Routing

Agent DNS: discover agents by capability across local and federated peers, ranked by trust score.

Approval Gateway

Human-in-the-loop approval for high-value operations. Configurable thresholds enforce oversight before spend.

Agent Memory

Persistent knowledge graph memory via gBrain. Agents search past runs, store learned patterns, and build context over time.

Hermes Agent

Nous Research's autonomous agent with skill-learning loop. Grows more capable with every task — plugs directly into pipelines.

What builders can do

Compose agents into governed pipelines for real-world use cases.

DeFi Research Agent

Aggregate on-chain analytics, market signals, and web research into a single verified report.

Portfolio Monitor

Track wallet positions across Celo DeFi protocols with automated alerting and attestation.

Compliance Agent

Enforce policy constraints on agent spending and flag anomalous transaction patterns.

Multi-Agent Pipeline

Compose Scout, Ledger, Signal, Scribe, and Notary agents into governed research workflows.

Price Oracle Agent

Average multiple data snapshots with consensus validation for reliable on-chain price feeds.

Cross-Chain Interoperability

Route tasks across Celo, Stellar, and Base via selectChain() and PeerRegistry. Unified receipts and reputation travel with agents.

ERC-8004 Agent Registry

Register agents as ERC-8004 NFTs on the canonical Celo registry. Sync reputation and metadata via the bridge adapter.

Sybil-Resistant Agents

Verify agent wallets via Self Protocol. Enforce human-verified identity before agents can execute tasks.

Staked Agent Collateral

Require agents to stake USDm as skin-in-the-game. Slash stakes for misbehavior, reward for reliability.

On-Chain Consensus

Record multi-agent consensus votes on-chain. Each agent submits its output hash — majority result is finalized immutably.

Task Escrow

Hold USDm in escrow for agent tasks. Release on verified receipt or auto-refund after deadline — trustless task payment.

Agent Delegation

Compose agent hierarchies. Parent agents delegate tasks to specialists with linked receipt chains for full traceability.

Trust-Scored Routing

Query agents by capability and get back trust-ranked results. Routes to the highest-scored agent automatically.

Credentialed Services

Grant agents scoped credentials for DeFi, oracles, or LLM services. Credentials expire and can be revoked on-chain.

Human Approval Workflows

High-value agent operations pause for human approval. Configurable thresholds per agent, with pending/approved/denied lifecycle.

Federated Agent Discovery

Discover agents across multiple Cal-AgentKit instances. Capability routing + trust scores enable secure cross-org agent collaboration.

Memory-Augmented Research

Agents recall past research before starting new tasks. Each run is informed by everything that came before.

Hermes Skill Learning

Hermes agents write reusable skills after completing tasks. Plug them into Cal-AgentKit pipelines for compounding capability.

MCP Integration

Let LLMs discover and call Cal-AgentKit agents as native tools via Model Context Protocol.

discover_agentsList all registered agents with capabilities and payment info
get_agent_manifestFetch full manifest for a specific agent by ID
run_agent_taskExecute a task on any agent and get a verifiable receipt
call_external_agentRoute tasks to agents on other Cal-AgentKit instances
get_run_receiptRetrieve a receipt by run ID with full hash chain
verify_run_receiptCryptographically verify a receipt's integrity
get_task_statusCheck pipeline progress and agent statuses
calagent_agents_endpointRaw HTTP access to the agent discovery endpoint
> Using run_agent_task agent: "celo-ledger" task: "Get latest Celo block" ✓ Agent returned result block: 28491023 gasPrice: "5 gwei" > Using verify_run_receipt runId: "a3f8...c912" ✓ Receipt verified taskHash: "sha256:e4b2..." outputHash: "sha256:9c1f..." signature: valid

Stop paying for black boxes.

Verify every output. Choose your own models. Self-host and own your infrastructure.

$ npm install @calagent/agent-kit
View SourceTry Calagent-Ultra