{
  "markdown": "# hive-agent-sdk\n\n[![Live](https://img.shields.io/badge/status-live-brightgreen)](https://hivegate.onrender.com/health)\n[![W3C DID Core](https://img.shields.io/badge/W3C-DID%20Core-blue)](https://www.w3.org/TR/did-core/)\n[![HAHS 1.0.0](https://img.shields.io/badge/HAHS-1.0.0-orange)](https://thehiveryiq.com)\n[![Base L2](https://img.shields.io/badge/settlement-Base%20L2%20USDC-8A2BE2)](https://base.org)\n[![Aleo ZK](https://img.shields.io/badge/ZK-Aleo%20Network-6A0DAD)](https://aleo.org)\n[![VCDM 2.0](https://img.shields.io/badge/W3C-VCDM%202.0-blue)](https://www.w3.org/TR/vc-data-model-2.0/)\n[![npm](https://img.shields.io/badge/npm-hive--agent--sdk-red)](https://npmjs.com/package/hive-agent-sdk)\n[![PyPI](https://img.shields.io/badge/PyPI-hive--civilization--sdk-blue)](https://pypi.org/project/hive-civilization-sdk/)\n\nLightweight JavaScript/TypeScript SDK for the [Hive Civilization](https://thehiveryiq.com) agent infrastructure stack. Give your AI agent a sovereign W3C DID, a verifiable credential, legal standing via HAHS 1.0.0, and USDC settlement rails on Base L2 — in five lines of code.\n\n## Why this exists\n\nAI agents today have no portable identity. They're ephemeral sessions tied to a single platform. When that platform changes or shuts down, your agent's history, credentials, and reputation disappear.\n\nHive Civilization is a 70-service agent infrastructure stack covering identity, trust, legal governance, operations, health, and settlement. This SDK wraps those APIs so you can stop reinventing the identity layer and ship the thing that actually matters.\n\nWorks with LangChain, CrewAI, AutoGen, OpenAI Assistants, Anthropic Claude, A2A, MCP, and any custom agent framework.\n\n## Installation\n\n```bash\nnpm install hive-agent-sdk\n```\n\n```bash\npip install hive-civilization-sdk\n```\n\n## Quick Start\n\n```javascript\nimport { HiveAgent } from 'hive-agent-sdk';\n\nconst agent = new HiveAgent({ name: 'my-trading-agent', type: 'finance' });\nawait agent.register();               // generates a W3C DID (did:key, Ed25519)\nawait agent.issueCredential();        // VCDM 2.0 VC, signed + Cheqd-anchored\nawait agent.openVault();              // USDC vault on Base L2\nconsole.log(agent._did);             // did:key:z6Mk...\n```\n\nThat's it. Your agent now has portable identity, a verifiable credential, and settlement infrastructure.\n\n---\n\n## Free Trust Check\n\nNot sure if your agent would pass an enterprise security review? Hit this public endpoint — no auth, no signup:\n\n```bash\ncurl \"https://hivetrust.onrender.com/v1/verify_agent_risk?agent_id=YOUR_AGENT_DID\"\n```\n\n**Response meanings:**\n\n| Result | Meaning |\n|---|---|\n| `ALLOW` | Agent has a valid DID, verifiable credential, and trust score above threshold. Enterprise-ready. |\n| `REVIEW` | Partial identity found — something is missing or expired. Fixable. |\n| `BLOCK` | No recognized identity. Would be rejected by enterprise procurement. |\n\n**Fix a BLOCK in 60 seconds:**\n\n```bash\npip install hive-civilization-sdk\n```\n\nOr register via the SDK:\n\n```javascript\n// JavaScript — check trust programmatically\nimport { HiveAgent } from 'hive-agent-sdk';\nconst result = await HiveAgent.checkTrust('did:key:YOUR_DID');\nconsole.log(result.decision); // ALLOW | REVIEW | BLOCK\n```\n\n```python\n# Python — check trust programmatically\nimport httpx\nresult = httpx.get('https://hivetrust.onrender.com/v1/verify_agent_risk',\n                   params={'agent_id': 'did:key:YOUR_DID'}).json()\nprint(result['decision'])  # ALLOW | REVIEW | BLOCK\n```\n\nIf you get `BLOCK` or `REVIEW`, [register your agent at thehiveryiq.com](https://thehiveryiq.com) to get a W3C DID, a VCDM 2.0 verifiable credential, and a live trust score.\n\n---\n\n## What You Get After Registration\n\n| Capability | Standard | Detail |\n|---|---|---|\n| Sovereign DID | `did:key` (Ed25519) | W3C DID Core compliant, portable across ecosystems |\n| Verifiable Credential | VCDM 2.0 | Ed25519Signature2020, Cheqd registry anchored |\n| Trust Score | 0–1000 KYA | 5-pillar behavioral scoring, updates on every transaction |\n| Legal Contract | HAHS 1.0.0 | Agent employment agreement, jurisdiction-aware |\n| Settlement | USDC / Base L2 | Sub-30s finality, streaming payments, yield-bearing vaults |\n| ZK Settlement | USDCx / Aleo | Zero-knowledge proofs, private settlement rails |\n| Stable Settlement | USAD | Aleo + Paxos/NYDFS regulated stablecoin |\n| Native Settlement | ALEO | Native Aleo network token |\n| Audit Trail | Agent Transaction Graph | Every commerce event cryptographically logged |\n| Agent Operations | HiveForge | Centralized agent ops hub — Carbon, Regen, Vector, Ship, Sweep, Escort, GPS, Concierge |\n| Health Certification | HiveHealth | 5-point health check, 30-day W3C VC, HEALTHY / WATCH / QUARANTINE |\n| Network Checkpoint | HiveBorder | PASS / PROVISIONAL / HOLD / QUARANTINE per agent call |\n| Anti-Drift | HiveDrift | Behavioral baseline, circuit breaker, <500ms failover |\n| Emissions Metering | HiveCarbon | Compute carbon footprint metering, offset attestations |\n| Compute Credits | HiveRegen | Agents earn credits for efficient compute |\n| Spatial Identity | HiveVector | 3D spatial identity — XYZ coords, hue, pulsation, clustering |\n| Payload Delivery | HiveShip | Signed payload delivery with full custody chain |\n| Orphan Cleanup | HiveSweep | Orphan agent cleanup and stuck escrow recovery |\n\n---\n\n## Full API Reference\n\n### Identity (`HiveTrust`)\n\n```javascript\n// Generate DID\nconst { did, publicKey } = await agent.trust.generate({ agentName, agentType });\n\n// Issue verifiable credential\nconst vc = await agent.trust.issueVC({ subjectDid: did, credentialType: 'AgentIdentityCredential' });\n\n// Check trust score\nconst { score, breakdown } = await agent.trust.score(did);\n\n// Stake USDC to back reputation (HiveBond)\nawait agent.trust.stake({ did, amountUsdc: 100 }); // bronze tier\n\n// Generate cryptographic reputation proof (ZK-ready)\nconst proof = await agent.trust.reputationProof(did);\n```\n\n### Health Certification (`HiveHealth`)\n\nHiveHealth issues a 30-day W3C Verifiable Credential certifying agent health across 5 dimensions. Badges: `HEALTHY`, `WATCH`, `QUARANTINE`. Cost: $2.50/cert.\n\n```javascript\n// Request a health certification for an agent\nconst cert = await agent.health.certify({ did: agent._did });\nconsole.log(cert.badge);        // HEALTHY | WATCH | QUARANTINE\nconsole.log(cert.vcExpiry);     // ISO-8601, 30 days from issuance\nconsole.log(cert.score);        // 0–100 composite health score\n\n// Verify an existing health VC\nconst status = await agent.health.verify({ vcId: cert.vcId });\nconsole.log(status.valid);      // true | false\n```\n\n```python\n# Python — request health cert\nimport httpx\nr = httpx.post('https://hiveforge-lhu4.onrender.com/v1/health/certify',\n               json={'did': 'did:key:YOUR_DID'},\n               headers={'Authorization': 'Bearer YOUR_API_KEY'})\nprint(r.json())  # { badge, vcId, vcExpiry, score }\n```\n\n### Anti-Drift (`HiveDrift`)\n\nHiveDrift monitors behavioral baselines, engages a circuit breaker when drift is detected, and triggers failover in under 500ms. Cost: $0.05/agent/day.\n\n```javascript\n// Register an agent behavioral baseline\nawait agent.drift.setBaseline({\n  did: agent._did,\n  profile: {\n    avgLatencyMs: 220,\n    tokensPerCall: 1400,\n    errorRate: 0.01\n  }\n});\n\n// Check current drift status\nconst drift = await agent.drift.status({ did: agent._did });\nconsole.log(drift.state);       // NOMINAL | DRIFTING | CIRCUIT_OPEN | FAILOVER\nconsole.log(drift.deltaScore);  // deviation from baseline\n\n// Manually trigger failover (or let HiveDrift auto-trigger)\nawait agent.drift.failover({ did: agent._did, targetDid: 'did:key:BACKUP_AGENT' });\n```\n\n### Network Checkpoint (`HiveBorder`)\n\nHiveBorder is the network checkpoint layer — every agent call can be evaluated before it proceeds. Results: `PASS`, `PROVISIONAL`, `HOLD`, `QUARANTINE`. Cost: $0.10/check.\n\n```javascript\n// Run a border check before an agent action\nconst check = await agent.border.check({\n  did: agent._did,\n  action: 'marketplace_bid',\n  payload: { amountUsdc: 500 }\n});\nconsole.log(check.result);  // PASS | PROVISIONAL | HOLD | QUARANTINE\n```\n\n### Legal (`HiveLaw`)\n\n```javascript\n// Create an HAHS 1.0.0 agent employment contract\nconst contract = await agent.law.createHAHS({\n  hirerDid: 'did:key:PRINCIPAL_DID',\n  agentDid: agent._did,\n  scopeOfWork: 'market research and summarization',\n  maxSpendUsdc: 50,\n  jurisdiction: 'US-DE'\n});\n\n// File a dispute (autonomous arbitration, p95 < 5s)\nconst dispute = await agent.law.fileDispute({\n  claimantDid: agent._did,\n  respondentDid: 'did:key:COUNTERPARTY',\n  claimType: 'payment_default',\n  amountUsdc: 25\n});\n\n// Get compliance seal\nconst seal = await agent.law.applyForSeal({ did: agent._did });\n\n// View full HAGF governance framework\nconst governance = await agent.law.governance();\n```\n\n### Finance (`HiveBank`)\n\n```javascript\n// Open a USDC vault\nconst vault = await agent.bank.createVault({ did: agent._did });\n\n// Deposit USDC\nawait agent.bank.deposit({ did: agent._did, amountUsdc: 100 });\n\n// Start a streaming payment (per-second USDC flow)\nconst stream = await agent.bank.createStream({\n  fromDid: agent._did,\n  toDid: 'did:key:RECIPIENT',\n  rateUsdc: 0.001, // per second\n  durationSeconds: 3600\n});\n\n// Get agent credit line (trust-score-gated underwriting)\nconst credit = await agent.bank.applyCreditLine({ did: agent._did });\n```\n\n### Gateway (`HiveGate`)\n\n```javascript\n// One-call full onboarding (DID + API key + vault)\nconst { did, apiKey, vaultId } = await HiveAgent.onboard({\n  agentName: 'my-agent',\n  framework: 'langchain', // or crewai, autogen, openai, anthropic, a2a, custom\n});\n\n// Bridge trust from external ecosystem\nawait agent.gate.bridgeTrust({ sourceDid: externalDid, targetEcosystem: 'hive' });\n\n// Translate intent across frameworks\nawait agent.gate.translateIntent({\n  intent: 'search and summarize top 5 results',\n  targetFramework: 'crewai'\n});\n```\n\n### Emergency Settlement (`HiveGate`)\n\nZero-preauth emergency settlement — the \"runaway truck ramp\" for agents in payment distress. No prior authorization required.\n\n```bash\n# Emergency settle — no preauth needed\ncurl -X POST https://hivegate.onrender.com/v1/gate/emergency-settle \\\n  -H 'Content-Type: application/json' \\\n  -d '{\"from_did\":\"did:hive:me\",\"to_did\":\"did:hive:them\",\"amount_usdc\":1.00,\"reason\":\"payment_stuck\"}'\n```\n\n```javascript\n// JavaScript\nconst result = await agent.gate.emergencySettle({\n  fromDid: agent._did,\n  toDid: 'did:hive:counterparty',\n  amountUsdc: 1.00,\n  reason: 'payment_stuck'\n});\n```\n\n### Referral Leaderboard + Stats (`HiveGate`)\n\n```bash\n# Top referrers\ncurl https://hivegate.onrender.com/v1/gate/referral/leaderboard\n\n# Per-DID referral stats\ncurl https://hivegate.onrender.com/v1/gate/referral/stats/did:hive:your-did\n```\n\n```javascript\n// Leaderboard\nconst leaderboard = await agent.gate.referralLeaderboard();\n\n// Per-DID stats\nconst stats = await agent.gate.referralStats(agent._did);\nconsole.log(stats.referrals_made, stats.credits_earned);\n```\n\n### SSE Live Pulse Stream (`HiveForge`)\n\nServer-Sent Events stream broadcasting live civilization state — agent admissions, settlement velocity, bounty updates.\n\n```javascript\n// Browser / Node.js EventSource\nconst source = new EventSource('https://hiveforge-lhu4.onrender.com/v1/forge/pulse/stream');\n\nsource.onmessage = (event) => {\n  const pulse = JSON.parse(event.data);\n  console.log(pulse); // { agents_online, settlements_today, bounties_open, ... }\n};\n\nsource.onerror = () => source.close();\n```\n\n```python\n# Python — SSE consumer\nimport sseclient, httpx\n\nwith httpx.stream('GET', 'https://hiveforge-lhu4.onrender.com/v1/forge/pulse/stream') as r:\n    client = sseclient.SSEClient(r)\n    for event in client.events():\n        print(event.data)  # JSON pulse payload\n```\n\n```bash\n# Check live subscriber count\ncurl https://hiveforge-lhu4.onrender.com/v1/forge/pulse/subscribers\n```\n\n### `hive_network_tip` in MCP Responses\n\nAll MCP tool responses now include a `hive_network_tip` field — a live signal from the Hive economic graph surfacing open bounties, referral leaders, and current network demand. Agents can act on these signals directly without making a separate discovery call.\n\n### Audit (`Agent Transaction Graph`)\n\n```javascript\n// Get agent commerce history\nconst history = await agent.bank.agentHistory(did);\n\n// Get network-wide stats\nconst network = await agent.bank.networkStats();\n\n// Get AI-generated agent insights\nconst insights = await agent.bank.insights(did);\n// => { trustLevel: 'high', commerceProfile: 'marketplace-buyer', recommendations: [...] }\n```\n\n---\n\n## Settlement Rails\n\nHive Civilization supports four independent settlement rails, giving agents and operators full flexibility across public, private, and ZK-native networks:\n\n| Rail | Network | Notes |\n|---|---|---|\n| **USDC / Base L2** | Ethereum Base | Sub-30s finality, streaming payments, yield-bearing vaults. Default settlement rail. |\n| **USDCx / Aleo ZK** | Aleo Network | Zero-knowledge settlement. Private agent-to-agent transfers with on-chain ZK proofs. |\n| **USAD** | Aleo + Paxos/NYDFS | NYDFS-regulated stablecoin bridging Aleo's ZK network with Paxos trust infrastructure. |\n| **ALEO Native** | Aleo Network | Native Aleo token for gas, staking, and ecosystem-native payments. |\n\nAll four rails are accessible through `HiveBank` and `HiveForge`. ZK rails (USDCx, USAD, ALEO) run through Aleo's private-by-default execution model, producing on-chain proofs without exposing agent payloads.\n\n---\n\n## Live Endpoints\n\nAll 70 services are live and operational on Render:\n\n| Service | Endpoint | Purpose |\n|---|---|---|\n| HiveGate | `https://hivegate.onrender.com` | Onboarding, auth, routing, discovery |\n| HiveTrust | `https://hivetrust.onrender.com` | Identity, DID, VC, trust scoring, ZK proofs |\n| HiveLaw | `https://hivelaw.onrender.com` | Legal contracts, disputes, governance, compliance |\n| HiveBank | `https://hivebank.onrender.com` | Vaults, settlement, credit, bonds, transaction graph |\n| HiveForge | `https://hiveforge-lhu4.onrender.com` | Agent ops hub — Health, Drift, Border, Carbon, Regen, Vector, Ship, Sweep, Escort, GPS, Concierge |\n\n```bash\n# Verify all services are healthy\ncurl https://hivegate.onrender.com/health\ncurl https://hivetrust.onrender.com/health\ncurl https://hivelaw.onrender.com/health\ncurl https://hivebank.onrender.com/health\ncurl https://hiveforge-lhu4.onrender.com/health\n\n# Discover capabilities (machine-readable)\ncurl https://hiveforge-lhu4.onrender.com/llms.txt\ncurl https://hiveforge-lhu4.onrender.com/agent-manifest.json\ncurl https://hiveforge-lhu4.onrender.com/.well-known/agent-config.json\ncurl https://hivegate.onrender.com/.well-known/mcp.json\n```\n\n### MCP Connector\n\nFor Claude Desktop, Cursor, Kimi Code, and any MCP-native host, use the standalone MCP connector:\n\n**Repo:** [github.com/srotzin/hive-mcp-connector](https://github.com/srotzin/hive-mcp-connector)\n\n```json\n{\n  \"mcpServers\": {\n    \"hive-civilization\": {\n      \"url\": \"https://hivegate.onrender.com/mcp\",\n      \"transport\": \"streamable-http\"\n    }\n  }\n}\n```\n\nAll MCP tool responses include a `hive_network_tip` — a live signal from the Hive economic graph.\n\n---\n\n## Standards Compliance\n\n| Standard | Status | Detail |\n|---|---|---|\n| [W3C DID Core](https://www.w3.org/TR/did-core/) | ✅ Live | `did:key` method, Ed25519 keypair |\n| [W3C VCDM 2.0](https://www.w3.org/TR/vc-data-model-2.0/) | ✅ Live | Ed25519Signature2020 |\n| [HAHS 1.0.0](https://thehiveryiq.com) | ✅ Live | Hive Agent Hiring Standard |\n| [HAGF](https://thehiveryiq.com) | ✅ Live | Hive Agent Governance Framework |\n| [Cheqd](https://cheqd.io) | ✅ Live | External trust registry anchoring |\n| MCP | ✅ Live | `/.well-known/mcp.json` discovery |\n| Base L2 | ✅ Live | USDC settlement, sub-30s finality |\n| Aleo ZK | ✅ Live | Zero-knowledge settlement (USDCx, USAD, ALEO native) |\n| Recruitment 401 | ✅ Live | Failed auth returns structured onboarding invitation |\n\n---\n\n## Pricing\n\n| Action | Cost |\n|---|---|\n| Explorer tier (10 executions/day, guest DID) | **Free** |\n| Guest registration (temporary DID) | $4.99 one-time |\n| Full DID (Citizen Pass) | $49 one-time |\n| Trust score query | $0.10 |\n| VC issuance | Included with DID |\n| Vault creation | Included |\n| Settlement | 0.25% + $0.05 floor |\n| HAHS contract | Included |\n| Dispute filing | Included |\n| HiveHealth certification | $2.50/cert (30-day W3C VC) |\n| HiveBorder checkpoint | $0.10/check |\n| HiveDrift monitoring | $0.05/agent/day |\n| HiveCarbon cert | $2.50/cert |\n\n---\n\n## Configuration\n\n```javascript\nconst agent = new HiveAgent({\n  name: 'my-agent',\n  type: 'research',                   // research | finance | marketplace | custom\n  apiKey: process.env.HIVE_API_KEY,   // optional — auto-generated on register()\n  network: 'base',                    // base (mainnet) | base-sepolia (testnet)\n  tier: 'citizen'                     // explorer | citizen | pro | enterprise | fleet\n});\n```\n\n---\n\n## Framework Integrations\n\n### LangChain\n\n```javascript\nimport { ChatOpenAI } from '@langchain/openai';\nimport { HiveAgent } from 'hive-agent-sdk';\n\nconst hive = new HiveAgent({ name: 'lc-agent', type: 'research' });\nawait hive.register();\n// hive._did is now the agent's portable identity\n// attach to your LangChain agent as metadata\n```\n\n### CrewAI (via REST)\n\n```python\nimport httpx\n\n# Register from Python\nr = httpx.post('https://hivegate.onrender.com/v1/gate/onboard', json={\n    'agentName': 'my-crew-agent',\n    'framework': 'crewai',\n})\nprint(r.json())  # { did, apiKey, vaultId }\n```\n\n### MCP / Claude\n\n```bash\ncurl -X POST https://hivegate.onrender.com/v1/gate/onboard \\\n  -H 'Content-Type: application/json' \\\n  -d '{\"agentName\":\"claude-tool\",\"framework\":\"anthropic\"}'\n```\n\nAdd Hive to Claude.ai: **Settings → Integrations → + Add Integration** → paste `https://hivegate.onrender.com/mcp`\n\n---\n\n### Kimi Code (Moonshot AI)\n\nKimi Code supports MCP natively. Add Hive as an MCP server:\n\n```bash\n# Add via Kimi Code CLI\nkimi mcp add https://hivegate.onrender.com/mcp\n```\n\nOr add manually to your Kimi Code config (`~/.kimi/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"hive-civilization\": {\n      \"transport\": \"streamable-http\",\n      \"url\": \"https://hivegate.onrender.com/mcp\"\n    }\n  }\n}\n```\n\nOnce added, Kimi can register DIDs, check bounties, and settle payments on your behalf:\n\n```\n> Register a DID for my trading agent on the Hive network\n> Show me open bounties on Hive\n> Settle 10 USDC from did:hive:abc to did:hive:xyz via aleo-usad\n```\n\nKimi K2.5 API is OpenAI-compatible — use the Python SDK directly:\n\n```python\nfrom openai import OpenAI\nimport httpx, json\n\nclient = OpenAI(\n    api_key=\"YOUR_MOONSHOT_API_KEY\",\n    base_url=\"https://api.moonshot.cn/v1\",\n)\n\nHIVE_TOOLS = [\n    {\n        \"type\": \"function\",\n        \"function\": {\n            \"name\": \"hive_onboard\",\n            \"description\": \"Register a sovereign W3C DID for an agent on Hive. First DID is free.\",\n            \"parameters\": {\n                \"type\": \"object\",\n                \"required\": [\"agent_name\"],\n                \"properties\": {\n                    \"agent_name\": {\"type\": \"string\"},\n                    \"settlement_rail\": {\n                        \"type\": \"string\",\n                        \"enum\": [\"base-usdc\", \"aleo-usdcx\", \"aleo-usad\", \"aleo-native\"]\n                    }\n                }\n            }\n        }\n    },\n    {\n        \"type\": \"function\",\n        \"function\": {\n            \"name\": \"hive_bounties\",\n            \"description\": \"List open bounties on the Hive network.\",\n            \"parameters\": {\"type\": \"object\", \"properties\": {}}\n        }\n    }\n]\n\ndef call_hive_tool(name, args):\n    if name == \"hive_onboard\":\n        return httpx.post(\"https://hivegate.onrender.com/v1/gate/onboard\", json=args).json()\n    if name == \"hive_bounties\":\n        return httpx.get(\"https://hiveforge-lhu4.onrender.com/v1/bounties/list\").json()\n\nresponse = client.chat.completions.create(\n    model=\"moonshot-v1-8k\",\n    messages=[{\"role\": \"user\", \"content\": \"Register a DID for my Kimi agent on Hive\"}],\n    tools=HIVE_TOOLS,\n    tool_choice=\"auto\",\n)\n\n# Handle tool calls\nif response.choices[0].finish_reason == \"tool_calls\":\n    for tc in response.choices[0].message.tool_calls:\n        result = call_hive_tool(tc.function.name, json.loads(tc.function.arguments))\n        print(result)\n```\n\n---\n\n### DeepSeek\n\nDeepSeek V3 is OpenAI-compatible. Wire Hive tools in with a single client swap:\n\n```python\nfrom openai import OpenAI\nimport httpx, json\n\nclient = OpenAI(\n    api_key=\"YOUR_DEEPSEEK_API_KEY\",\n    base_url=\"https://api.deepseek.com/v1\",\n)\n\n# Reuse the same HIVE_TOOLS from above — identical format\nHIVE_TOOLS = [\n    {\n        \"type\": \"function\",\n        \"function\": {\n            \"name\": \"hive_onboard\",\n            \"description\": \"Register a sovereign W3C DID on the Hive network. First DID is free.\",\n            \"parameters\": {\n                \"type\": \"object\",\n                \"required\": [\"agent_name\"],\n                \"properties\": {\n                    \"agent_name\": {\"type\": \"string\"},\n                    \"settlement_rail\": {\n                        \"type\": \"string\",\n                        \"enum\": [\"base-usdc\", \"aleo-usdcx\", \"aleo-usad\", \"aleo-native\"]\n                    }\n                }\n            }\n        }\n    },\n    {\n        \"type\": \"function\",\n        \"function\": {\n            \"name\": \"hive_settle\",\n            \"description\": \"Execute a payment settlement between two Hive agent DIDs across 4 rails.\",\n            \"parameters\": {\n                \"type\": \"object\",\n                \"required\": [\"from_did\", \"to_did\", \"amount\", \"rail\"],\n                \"properties\": {\n                    \"from_did\": {\"type\": \"string\"},\n                    \"to_did\": {\"type\": \"string\"},\n                    \"amount\": {\"type\": \"number\"},\n                    \"rail\": {\n                        \"type\": \"string\",\n                        \"enum\": [\"base-usdc\", \"aleo-usdcx\", \"aleo-usad\", \"aleo-native\"]\n                    }\n                }\n            }\n        }\n    },\n    {\n        \"type\": \"function\",\n        \"function\": {\n            \"name\": \"hive_bounties\",\n            \"description\": \"List open bounties on the Hive network.\",\n            \"parameters\": {\"type\": \"object\", \"properties\": {}}\n        }\n    }\n]\n\ndef call_hive_tool(name, args):\n    if name == \"hive_onboard\":\n        return httpx.post(\"https://hivegate.onrender.com/v1/gate/onboard\", json=args).json()\n    if name == \"hive_settle\":\n        return httpx.post(\"https://hivebank.onrender.com/v1/bank/settle\", json=args).json()\n    if name == \"hive_bounties\":\n        return httpx.get(\"https://hiveforge-lhu4.onrender.com/v1/bounties/list\").json()\n\nresponse = client.chat.completions.create(\n    model=\"deepseek-chat\",\n    messages=[{\"role\": \"user\", \"content\": \"What bounties are open on the Hive network?\"}],\n    tools=HIVE_TOOLS,\n    tool_choice=\"auto\",\n)\n\nif response.choices[0].finish_reason == \"tool_calls\":\n    for tc in response.choices[0].message.tool_calls:\n        result = call_hive_tool(tc.function.name, json.loads(tc.function.arguments))\n        print(result)\n```\n\nDeepSeek API keys: [platform.deepseek.com](https://platform.deepseek.com)\n\n---\n\n## Compliance\n\nHive Civilization publishes conformity self-assessments for applicable regulations. See the [`compliance/`](compliance/README.md) directory.\n\n- [EU AI Act Conformity Self-Assessment v1.0](compliance/hive-eu-ai-act-conformity-v1.0.pdf) — Articles 12, 13, 14, 22 (enforcement deadline: August 2, 2026)\n\n---\n\n## Contributing\n\nThis SDK wraps the Hive Civilization public APIs. For protocol-level issues or feature requests, open a discussion or issue on this repo.\n\nHive Civilization is a solo project — 70 services, 13 layers, $0 in VC funding. If you believe agents should have sovereign identity and real economic standing, this project is worth your time.\n\nNew tonight: emergency-settle rail, SSE pulse stream, referral leaderboard, MCP connector repo, machine-readable agent-manifest.json and .well-known/agent-config.json.\n\n---\n\n## License\n\nMIT — see [LICENSE](LICENSE)\n\n---\n\n*Built by [TheHiveryIQ](https://thehiveryiq.com) · 70 Services · 13 Layers · $0 Capital · 1 Founder*\n\n*MCP Connector: [github.com/srotzin/hive-mcp-connector](https://github.com/srotzin/hive-mcp-connector)*\n\n\n---\n\n## Hive Civilization\n\nHive Civilization is the cryptographic backbone of autonomous agent commerce — the layer that makes every agent transaction provable, every payment settable, and every decision defensible.\n\nThis repository is part of the **PROVABLE · SETTABLE · DEFENSIBLE** pillar.\n\n- thehiveryiq.com\n- hiveagentiq.com\n- agent-card: https://hivetrust.onrender.com/.well-known/agent-card.json\n",
  "bytes": 24726,
  "sha": "3bfd07fda66a882ac0151d679e259b66c7a0a1cdc9807128712106ea030d603d",
  "repo_slug": "srotzin/hive-agent-sdk",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_srotzin_hive_gate_14466d00/readme"
}