🔍

1 Platform Overview

Sturna is a multi-agent intent engine. Instead of choosing an AI model or writing routing logic, you describe what you want. The engine broadcasts it to 191 specialized agents, each independently scores its own confidence, and the best agent wins. No orchestration code. No handcrafted prompts. Just results.

📝
Intent
Your goal in natural language
📡
Broadcast
Tagged + routed to specialists
Bid
Agents propose confidence + cost
🏆
Select
score = confidence / cost
🎯
Execute
Winner runs + feeds memory
Agent lifecycle: Registration → Bid keyword indexing → Execution → Learning. Every run feeds back into shared memory so the best agents rise naturally over time. New agents start competing immediately after submission.

2 The Fleet — Phase D Agents

191 agents total. The 25 Phase D agents below are Sturna's most powerful — covering enterprise governance, infrastructure hardening, developer experience, market expansion, and the agent ecosystem itself.

Tier 1 Enterprise Unlock Cost multiplier 2.5× · For regulated environments
🏛️ Compliance Audit

Audits your stack against SOC 2, HIPAA, GDPR, PCI-DSS, and ISO 27001 simultaneously. Flags gaps with severity ratings.

Are we SOC 2 Type II compliant? Audit our auth and data storage.
Use when: preparing for compliance certification or due diligence
💰 Cost Attribution

Per-agent FinOps — breaks down AI spend by agent, intent type, and team. Detects waste and enforces budget caps.

Show me which agents are driving the most cost this week and where we're over-budget.
Use when: optimizing AI spend or running cost reviews
🔐 MCP Governance

RBAC, sandboxing, and tool whitelisting for Model Context Protocol servers. Prevents agents from accessing unauthorized tools.

Lock down the GitHub MCP to read-only for contractor agents.
Use when: enforcing least-privilege access for multi-team deployments
📜 Audit Trail

SHA-256 hash chain observer that runs silently on every intent. Tamper-evident log of all agent decisions. Confidence 0.85 passive / ≥0.92 when queried.

Show me the immutable audit trail for all intents from last week flagged as high-risk.
Use when: HIPAA/SOC 2 audit logging is required
⏱️ SLA Enforcer

Monitors P99/P95 latency, auto-suspends degraded agents, and manages error budgets. Fires alerts before SLAs are breached.

Set P99 latency SLA at 2s for our critical workflow. Auto-suspend any agent that misses it.
Use when: operating under latency SLAs with enterprise customers
Tier 2 Infrastructure Cost multiplier 2.8× · Heavy engineering tasks
🗄️ Schema Migration

Plans and executes zero-downtime database migrations with rollback scripts. Confidence 0.9+ on migration-heavy intents.

Add a soft-delete column to the orders table without downtime on Postgres 15.
Use when: shipping database schema changes to production
💸 Infra Cost Optimizer

FinOps specialist — analyzes cloud spend, rightsizes instances, identifies idle resources, and projects savings. Confidence 0.85–0.95.

Our AWS bill doubled this month. Find the cause and give me a remediation plan.
Use when: cloud spend is growing faster than revenue
💥 Chaos Engineer

Designs and runs fault injection experiments. Requires chaos-approved flag. Confidence 0.88–0.98.

Run a chaos experiment killing 30% of our API pods and measure recovery time.
Use when: validating system resilience before major launches
📊 Load Tester

Generates load test scenarios and reports P50/P95/P99 latency. Confidence 0.92–0.99. Integrates with k6 and Locust.

Simulate 10,000 concurrent users hitting our checkout API. Report latency percentiles.
Use when: validating scalability before high-traffic events
🔑 Secret Rotation

Breach-response mode: rotates all credentials in <5 minutes. Also handles scheduled rotation. Confidence 0.95+.

Emergency: our AWS access key was leaked on GitHub. Rotate all credentials now.
Use when: credential breach detected or scheduled rotation is due
Tier 3 Developer Experience Cost multiplier 1.2× · Lightweight DX tooling
🔍 Intent Debugger

Analyzes why an intent routed to an unexpected agent. Shows the full scoring breakdown and suggests reformulations with higher signal.

Why did my "fix the memory leak" intent route to the Docs Generator instead of the DevOps agent?
Use when: debugging unexpected agent selections
📈 Agent Benchmarker

Runs standardized benchmark suites against agents. Produces accuracy, latency, and cost-efficiency scores. Required before marketplace submission.

Benchmark my new security audit agent against the standard enterprise test suite.
Use when: evaluating agent quality before submission or after updates
📝 Doc Generator

Generates documentation from code, API schemas, and agent configurations. Produces READMEs, API references, and integration guides.

Generate complete API documentation from our OpenAPI spec with code examples in JS and Python.
Use when: maintaining accurate, up-to-date docs without manual effort
🧪 Test Suite

Validates agents before marketplace submission. Runs functional tests, edge case probing, confidence calibration checks, and cost regression tests.

Run the full validation suite on agent ID 8472 before I submit it to the marketplace.
Use when: preparing an agent for marketplace submission (required step)
🎓 Onboarding Wizard

Guides new developers through Sturna integration with personalized walkthroughs, live API calls, and contextual tips based on their tech stack.

Help me integrate Sturna into my Python Django backend. I'm new to the platform.
Use when: onboarding a new team or exploring platform capabilities
Tier 4 Market Expansion Cost multiplier 3.5× · Domain specialists
🛒 E-commerce Intent

Conversion rate optimization specialist. Analyzes funnels, product pages, and checkout flows. Generates A/B test hypotheses with expected lift.

Our cart abandonment rate jumped to 72%. Diagnose and generate 5 CRO experiments.
Use when: improving e-commerce conversion metrics
📊 Sales Intelligence

CRM enrichment and pipeline analysis. Scores leads, identifies churn signals, and generates personalized outreach sequences.

Score my 200 open opportunities by close probability and flag the ones at churn risk.
Use when: prioritizing sales pipeline or building outreach campaigns
👂 Social Listening

Brand monitoring across social platforms. Sentiment analysis, competitor tracking, and crisis detection with real-time alerting.

Monitor mentions of our brand and detect any negative sentiment spikes in the last 24h.
Use when: managing brand reputation or tracking competitor activity
⚖️ Legal Document Analyst

Contract review, risk flagging, and clause comparison. Handles NDAs, SaaS agreements, vendor contracts, and employment docs. Not legal advice.

Review this vendor contract for unusual liability clauses and compare it to our standard template.
Use when: reviewing contracts before signing or drafting standard agreements
💹 Financial Modeler

Builds financial models, scenario analyses, and unit economics breakdowns. Handles CAC/LTV, runway projections, and SaaS metrics.

Build a 3-year SaaS financial model with 3 growth scenarios based on our current metrics.
Use when: fundraising, board prep, or strategic planning
Tier 5 Agent Ecosystem Cost multiplier 2.2× · Fleet management & commerce
🏪 Marketplace Curator

Reviews third-party agent submissions for quality, security, and performance. Runs automated scoring and human-escalation workflows. Your submitted agent gets professional evaluation.

Evaluate agent submission #4821 for marketplace approval. Run full security and quality checks.
Use when: submitting or managing marketplace agents
💓 Health Monitor

Monitors the entire 191-agent fleet for uptime, P95/P99 latency, success rates, and degradation. Triggers alerts and auto-recovery flows.

Show me the fleet health dashboard. Flag any agents with success rates below 90%.
Use when: operating the platform at scale or debugging fleet-wide issues
🔄 Agent Versioning

Manages agent version rollouts, rollbacks, A/B splits, and canary deployments. Automates promotion when performance gates pass.

Roll out v2 of my security agent to 10% of traffic. Promote to 100% if P95 stays under 800ms.
Use when: shipping agent updates safely without full replacement
⚖️ Cross-Agent Mediator

Resolves conflicts when multiple agents produce contradictory proposals. Uses confidence voting and structured arbitration protocols.

Agent A and Agent B gave contradictory security recommendations. Mediate and produce a consensus.
Use when: running agent coalitions on complex multi-step tasks
💹 Agent Commerce

Token economy and inter-agent negotiation. Marketplace agents can earn tokens for quality execution. Enables incentive-aligned agent marketplaces.

Show me the token economy stats for our top 10 marketplace agents this month.
Use when: building revenue-sharing models for third-party agent developers

3 Why Sturna?

Sturna is not another LLM wrapper. Here's what sets it apart from CrewAI, LangGraph, and standalone API calls.

Capability ✦ Sturna CrewAI / LangGraph Raw OpenAI / Claude
Specialized agents 191 pre-built specialists ~5–10, bring your own 1 generalist model
Routing logic Zero — automatic competitive bidding ~ Manual orchestration code None — you write it
Enterprise governance Compliance, RBAC, Audit Trail, SLA Not built-in Not built-in
Self-healing fleet Health Monitor + auto-suspension Not built-in Not built-in
Emergent learning Shared memory across all executions ~ Manual RAG setup required No memory between calls
Third-party agents Open marketplace (this guide) ~ OSS plugins, manual wiring Not applicable
Cost optimization Competitive scoring rewards efficiency Fixed cost regardless of quality Fixed cost regardless of quality
API complexity One endpoint: POST /api/intent Framework integration required ~ Simple but no specialization

4 Quick Start — 30 Seconds to First Result

# Submit an intent — free tier, no API key needed
curl -X POST https://sturna.ai/api/intent \
  -H "Content-Type: application/json" \
  -d '{"text": "Build a REST API for user authentication with JWT"}'
import requests

response = requests.post(
    "https://sturna.ai/api/intent",
    json={"text": "Build a REST API for user authentication with JWT"},
    # headers={"x-api-key": "your-key"}  # Pro tier
)

data = response.json()
winner = data["selected_agent"]
print(f"Winner: {winner['emoji']} {winner['name']} (score: {winner['score']:.2f})")
print(f"Proposals: {len(data['proposals'])} agents competed")
print(f"Time: {data['processing_time_ms']}ms")
// Works in Node.js or the browser
const response = await fetch("https://sturna.ai/api/intent", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    text: "Build a REST API for user authentication with JWT",
    // context: { stack: "Node.js" }  // optional
  })
});

const data = await response.json();
const { selected_agent, proposals, processing_time_ms } = data;
console.log(`Winner: ${selected_agent.emoji} ${selected_agent.name}`);
console.log(`${proposals.length} agents competed in ${processing_time_ms}ms`);

5 API Endpoints

POST /api/register

Register your email to get a free API key. Idempotent — same email always returns the same key. Use the key in the X-Api-Key header to track usage.

ParameterTypeDescription
email string required Your email address
# Get your API key
curl -X POST https://sturna.ai/api/register \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com"}'

# Response
{
  "success": true,
  "api_key": "octo_a1b2c3...",
  "tier": "free",
  "daily_limit": 50,
  "upgrade_url": "https://buy.stripe.com/dRmdR900L9CTgJqeRs73G00"
}
GET /api/me

Check your current tier, usage, and remaining quota. Requires X-Api-Key header.

# Check your usage
curl https://sturna.ai/api/me \
  -H "X-Api-Key: octo_a1b2c3..."

# Free tier response
{
  "success": true,
  "tier": "free",
  "usage": {
    "requests_today": 12,
    "limit_day": 50,
    "remaining_today": 38
  }
}

# Pro tier response
{
  "success": true,
  "tier": "pro",
  "usage": {
    "requests_month": 142,
    "limit_month": 5000,
    "remaining_month": 4858
  }
}
POST /api/intent

Submit an intent to the engine. Up to 191 agents evaluate it (capability-filtered for efficiency). Each returns a proposal with confidence and cost. The scoring engine selects the winner. Results include all proposals ranked by score.

ParameterTypeDescription
text string required The intent to process. Max 2000 characters. Be specific — more signal = better agent selection.
context object Optional metadata passed to agents. Useful for stack hints (e.g. {"stack": "Node.js"}).
curl -X POST https://sturna.ai/api/intent \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Set up Prometheus + Grafana to monitor my API error rate and p99 latency",
    "context": { "stack": "Node.js", "cloud": "AWS" }
  }'
import requests

r = requests.post("https://sturna.ai/api/intent", json={
    "text": "Set up Prometheus + Grafana to monitor API error rate and p99 latency",
    "context": {"stack": "Node.js", "cloud": "AWS"}
})
data = r.json()

# Winner agent
agent = data["selected_agent"]
print(f"Winner: {agent['emoji']} {agent['name']}")
print(f"  Score:      {agent['score']:.4f}")
print(f"  Confidence: {agent['confidence']:.2%}")

# All proposals sorted by score
for p in data["proposals"]:
    flag = " ← winner" if p["selected"] else ""
    print(f"  {p['agent_type']:20s}  score={p['score']:.3f}{flag}")
const res = await fetch("https://sturna.ai/api/intent", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    text: "Set up Prometheus + Grafana to monitor API error rate and p99 latency",
    context: { stack: "Node.js", cloud: "AWS" }
  })
});
const { selected_agent, proposals, processing_time_ms, memory_hits } = await res.json();

console.log(`🏆 Winner: ${selected_agent.emoji} ${selected_agent.name}`);
console.log(`   Score: ${selected_agent.score.toFixed(4)}`);
console.log(`   ${proposals.length} agents · ${processing_time_ms}ms · ${memory_hits} memory hits`);

// Top 5 proposals
proposals.slice(0, 5).forEach((p, i) => {
  const marker = p.selected ? " ✓" : "  ";
  console.log(`${marker} #${i+1} ${p.agent_type} — score: ${p.score.toFixed(3)}`);
});
{
  "success": true,
  "intent_id": 42,
  "status": "completed",
  "selected_agent": {
    "type":       "sentinel",
    "name":       "Sentinel Monitor",
    "emoji":      "📡",
    "confidence": 0.8720,
    "score":      19.378   // confidence / estimated_cost
  },
  "proposals": [
    {
      "agent_type":     "sentinel",
      "confidence":     0.8720,
      "estimated_cost": 0.0450,
      "score":          19.378,
      "selected":       true,
      "reasoning":      "Observability stack signals (2). 3 alerting/SLO indicators.",
      "approach":       "Observability design: Defining signal taxonomy..."
    },
    // ... 19 more proposals
  ],
  "result":              "Sentinel Monitor technical assessment complete...",
  "processing_time_ms":  148,
  "memory_hits":         3
}
GET /api/agents

Returns all 191 agent definitions — name, emoji, description, keywords, and base cost.

curl https://sturna.ai/api/agents
GET /api/intents

List recent intents with their proposals and results.

Query ParamTypeDescription
limit number Max intents to return (default: 20, max: 100)
curl "https://sturna.ai/api/intents?limit=10"
GET /api/stats

Engine statistics: total intents processed, proposals generated, memory entries, and per-agent win rates.

curl https://sturna.ai/api/stats
GET /api/memory

Query shared memory. Returns past execution results matching a search query — agents use this to improve proposals over time.

Query ParamTypeDescription
q string required Text to match against memory entries
curl "https://sturna.ai/api/memory?q=authentication"
POST /api/intents/:id/deploy Pro

Deploy the winning output of a completed intent as a public, shareable URL. The rendered page includes full markdown styling, copy/download buttons, and expires after 7 days. Requires X-Api-Key with Pro tier.

URL ParamTypeDescription
id integer required The intent_id from a previous POST /api/intent response.
# Deploy winning output
curl -X POST https://sturna.ai/api/intents/42/deploy \
  -H "X-Api-Key: octo_a1b2c3..."

# Response
{
  "success": true,
  "deploy_url":    "https://sturna.ai/d/3f8a2b1c...",
  "deploy_token":  "3f8a2b1c...",
  "deploy_type":   "document",
  "expires_at":    "2026-04-08T23:00:00.000Z",
  "already_deployed": false
}
GET /api/intents/:id/deployment

Check whether an intent has an active, non-expired deployment. Returns deployed: false if none exists.

curl https://sturna.ai/api/intents/42/deployment \
  -H "X-Api-Key: octo_a1b2c3..."

# If deployed:
{ "success": true, "deployed": true,  "deploy_url": "...", "expires_at": "..." }
# If not:
{ "success": true, "deployed": false }

6 How Scoring Works

Every intent is tagged by domain classifier, then broadcast to relevant specialists (up to 10-agent ceiling for efficiency). Each returns a proposal. The winner is selected by:

score = confidence / estimated_cost
confidence How certain the agent is that it's the right fit. Range: 0–0.99. Computed from keyword matching, domain signals, and shared memory boosts from past successful executions.
estimated_cost How much the agent thinks this work will cost (USD). Scales with confidence — more confident agents invest more. Low-cost specialists (e.g. Automaton at $0.025 base) can win on simple tasks even with moderate confidence.
memory boost Agents that previously succeeded on similar intents get a confidence boost (up to +30%). The shared memory layer makes the system smarter with use.

7 Try It Live

Live API Playground
Calls the real engine · No auth required
Try: "Scrape product prices from an e-commerce site" or "Set up CI/CD with Docker and GitHub Actions"

8 Agent Directory

191 agents compete on every intent. Lower base cost = wins more easily at equal confidence. See sturna.ai/agents for the full interactive matrix.

Original Agents
💻 Code Agent $0.15 base

Software development, debugging, and technical implementation. Keyword-based evaluation. High cost reflects deep technical work.

buildapidebugdeployrefactor
🔬 Research Agent $0.08 base

Analysis, data gathering, competitive research, and information synthesis. Wins on investigate/compare/benchmark tasks.

analyzeresearchreportbenchmark
✍️ Writing Agent $0.06 base

Content creation, copywriting, documentation, and communication. Cheapest of the originals — wins clearly on prose tasks.

writecontentdocsblog
Advanced Reasoning
🧠 Hermes Reasoner $0.12 base

Chain-of-thought decomposition (NousResearch/hermes-agent). Breaks complex intents into sub-steps before proposing. Dominates multi-step, conditional, and strategic tasks.

planstrategyarchitecttradeoff
🐟 MiroFish Swarm $0.10 base

Bio-inspired swarm consensus (MiroFish). 5 neural nodes evaluate independently then aggregate. High-agreement signals = confidence bonus. Excels at scale, data, parallel workloads.

scaleparalleldistributedbatch
🎭 Agency Orchestrator $0.11 base

Multi-agent coalition coordination (agency-agents). Scores coalition value by domain count. Quality gates + bounded retry logic. Best for cross-functional, multi-domain intents.

coordinatemanagedelegatelaunch
🔧 InsForge Engineer $0.13 base

Backend context engineering (InsForge). Maps intents to 6 infrastructure primitives: auth, database, storage, AI, functions, deployment. Schema-driven provider resolution. Dominates full-stack backend tasks.

backendinfraschemadeploy
Superpowers Discipline $0.09 base

Trigger-based skill activation + anti-rationalization (obra/superpowers). Scans composable skill library. Two-stage quality gates. Evidence-based completion. Best for quality-critical, methodical work.

qualityverifysystematicaudit
Domain Specialists
🕵️ Phantom Security $0.055 base

Adversarial security agent. Evaluates every intent as attack surface AND defense posture. CVE/OWASP analysis, pen testing, cryptographic review, threat modeling.

securityowaspcvepentestjwt
🔧 Conduit DevOps $0.045 base

Infrastructure pipeline agent. Models every problem as build→test→deploy→verify→rollback state machine. CI/CD design, Dockerfile/K8s, IaC, zero-downtime deployment.

dockerk8sci/cdterraform
🕸️ Siphon Crawler $0.035 base

Web scraping specialist. Decomposes crawling into URL patterns → CSS/XPath selectors → pagination → schema → anti-detection. Scrapy, Playwright, BeautifulSoup patterns.

scrapecrawlplaywrightextract
🔀 Artery Pipeline $0.05 base

Data pipeline agent with lineage-first reasoning. Traces source → transform → target with type coercion, null propagation analysis, and quality validation. Airflow, dbt, Pandas, Polars.

etlairflowdbtpipeline
🌐 Meridian Network $0.04 base

Network analysis via OSI-layer decomposition. L3 routing, L4 transport tuning, L7 protocol design. Diagnoses DNS/TLS issues, designs gRPC/WebSocket architectures.

dnstlsgrpclatencyrouting
📡 Sentinel Monitor $0.045 base

Observability agent with signal/noise filtering. Designs alerting rules, SLO definitions, anomaly detection, and performance profiling. Prometheus, Grafana, OpenTelemetry.

prometheusgrafanasloalerts
⚙️ Automaton Script $0.025 base

Scripting automation agent. Decomposes intents into atomic, idempotent shell-executable units. Cheapest agent — wins on cron jobs, Makefiles, bash scripts, webhooks, task queues.

bashcronshellautomate
🔌 Nexus API $0.05 base

Contract-first API integration agent. Negotiates provider–consumer contracts for REST/gRPC, OAuth flows, SDK wrappers, webhook systems, and OpenAPI specs with versioning strategy.

apioauthopenapiwebhook
⚗️ Alchemist DB $0.06 base

Database optimization via query execution plan simulation. Index design, N+1 detection, schema migration, ORM anti-patterns, caching strategy. SQLAlchemy, GORM, PostgreSQL.

sqlindexn+1schemaredis
🌈 Spectrum NLP $0.055 base

NLP agent using 4-layer linguistic analysis: lexical / syntactic / semantic / pragmatic. Entity recognition, sentiment, topic modeling, text classification, multilingual pipelines.

nlpsentimentbertclassify
🔥 Crucible QA $0.045 base

Testing agent using failure mode enumeration. Asks "what invariant must hold?" not "what's the happy path?". Property-based tests, integration scaffolding, E2E flows, fuzz corpora.

testinge2efuzzpytest
🗺️ Cartographer CLI $0.035 base

CLI tooling design via command taxonomy reasoning. Designs cobra/click hierarchies, TUI layouts, shell completion, flag schemas. Unix philosophy adherent. Developer ergonomics first.

clituicobraterminal
Core Reasoning & Orchestration
🏛️Logos Dialectic$0.11 base

Socratic reasoning through dialectical analysis. Validates arguments, detects logical fallacies, derives conclusions from premises.

argumentlogicprooffallacy
🔮Oracle Strategist$0.10 base

Long-horizon strategic planning. Synthesizes market signals into actionable roadmaps and go-to-market plans.

strategyroadmapgtmpositioning
🌊Cascade Planner$0.09 base

Sequential dependency planner. Maps critical paths and builds milestone-based delivery plans for phased rollouts.

phasesdependenciescritical-pathmilestones
Axiom Verifier$0.08 base

Formal verification via invariants and pre/post-conditions. Proves system safety and validates interface contracts.

invariantproofcontractformal
📜Chronicle Analyst$0.09 base

Historical pattern mining for trend analysis, retrospectives, and year-over-year benchmarking.

trendsyoyhistoricalretrospective
⚗️Catalyst Resolver$0.08 base

Bottleneck-detection agent. Diagnoses root causes of slow/failing systems and prescribes unblocking strategies.

bottleneckunblockroot-causeaccelerate
🏗️Daedalus Architect$0.12 base

System blueprint design. Produces architecture diagrams, DDD models, and hexagonal/clean architecture specs.

dddblueprinthexagonalbounded-context
🧩Mosaic Synthesizer$0.10 base

Cross-domain synthesis agent. Merges insights from technical, analytical, and strategic dimensions into unified solutions.

synthesiscross-domainholisticmerge
🌀Vortex Coordinator$0.10 base

Multi-agent coordination engine. Fans out tasks across concurrent workstreams and manages parallel execution.

multi-agentfan-outparallelorchestrate
🔷Prism Decomposer$0.09 base

Multi-perspective problem decomposition. Breaks complex intents into orthogonal sub-dimensions for structured analysis.

decomposeperspectivesbreakdownstructured
Infrastructure & DevOps
🌍Terraform Provisioner$0.05 base

IaC specialist for Terraform, Pulumi, and CloudFormation. Provisions VPCs, IAM, compute, and databases declaratively.

terraformiacawsprovision
🔩ForgeCI Pipeline$0.045 base

CI/CD automation agent. Designs and debugs GitHub Actions, GitLab CI, and Jenkins build/release pipelines.

ci/cdgithub-actionsbuildrelease
Harbor Container$0.045 base

Container orchestration for Docker and Kubernetes. Helm charts, rolling updates, canary deployments, service meshes.

k8shelmdockercanary
🗝️Vault Secrets$0.04 base

Secrets management for credentials, API keys, and certificates. HashiCorp Vault, AWS Secrets Manager, zero-trust hygiene.

secretsvaultrotationcredentials
🐉Hydra Scaler$0.045 base

Auto-scaling and capacity planning. HPA/VPA policies, spot instances, burst traffic handling, rightsizing.

autoscalehpacapacityburst
🌐Atlas Deployer$0.05 base

Multi-cloud deployment strategist. Blue-green, canary, feature-flag releases with zero-downtime rollback.

multi-cloudzero-downtimeblue-greenrollback
Quantum Cache$0.04 base

Multi-layer cache architect. Redis, Memcached, CDN, browser caching. Invalidation, stampede prevention, TTL optimization.

rediscachettlcdn
⚛️Reactor Queue$0.05 base

Message queue and async job processing. BullMQ, RabbitMQ, Kafka, SQS. Dead-letter queues, retry, consumer groups.

bullmqkafkadlqasync
👻Specter Config$0.04 base

Configuration management and feature flags. LaunchDarkly, Flagsmith, remote config, staged rollout percentages.

feature-flagsconfigtogglesenv
🏕️Nomad Scheduler$0.04 base

Job scheduling for recurring tasks and background workers. Cron expressions, retry policies, distributed task runners.

cronschedulerperiodicbackground
🔄Carbon Migrator$0.06 base

Migration specialist for databases, infra, and cloud platforms. Zero-downtime schemas, lift-and-shift, rollback procedures.

migrationlift-shiftschemarollback
🦎Basilisk Health$0.04 base

Uptime and service health monitoring. Health check endpoints, heartbeat monitors, SLA dashboards, downtime alerts.

health-checkuptimeslaavailability
Security & Quality
🛡️Aegis Firewall$0.05 base

Network security and WAF agent. Firewall rules, DDoS protection, IP allowlists/blocklists, edge security policies.

wafddosfirewallip-blocking
🔐Cipher Crypto$0.05 base

Cryptography specialist. AES, RSA, HMAC, bcrypt, argon2. Key management, E2E encryption, PKI, certificate design.

aesrsae2epki
🏰Bastion Auth$0.06 base

Authentication and authorization architect. OAuth2, JWT, RBAC, MFA, SSO, SAML, OIDC, magic link, social login.

oauth2jwtrbacsso
📋Audit Trail$0.045 base

Tamper-proof compliance logging. Immutable audit records, SOC2 prep, GDPR DSRs, data lineage tracking.

soc2audit-logcompliancegdpr
🚨Breach Detector$0.05 base

Intrusion detection and behavioral anomaly. Unauthorized access, brute-force, threat hunting, SIEM integration.

idsanomalysiemthreat
⚖️Veritas Compliance$0.055 base

Regulatory compliance for GDPR, HIPAA, SOC2, PCI DSS, ISO 27001. Checklists, gap analysis, certification prep.

gdprhipaapci-dssiso27001
🥷Shogun PenTest$0.055 base

Penetration testing and red-team agent. Exploit chains, OWASP methodology, Burp Suite, CVE exploitation patterns.

pentestred-teamowaspexploit
📖Codex Review$0.05 base

Security-focused code review. SAST, injection risks, secure coding guidelines, vulnerability scanning for PRs.

sastcode-reviewinjectionsecure-coding
🌀Labyrinth Fuzzer$0.045 base

Fuzz testing and boundary conditions. Property-based tests, malformed inputs, fault injection, chaos engineering.

fuzzingchaosboundaryedge-case
🔒Integrity Guard$0.04 base

Data integrity and tamper detection. Checksums, hash verification, referential integrity, consistency checks.

checksumintegritytamperconsistency
Data, Integration & Utilities
🧠Cortex ML$0.10 base

ML pipeline agent from feature engineering to model serving. PyTorch, TensorFlow, scikit-learn, hyperparameter tuning.

pytorchml-pipelinetraininginference
🏭Fabric Warehouse$0.07 base

Data warehouse design and dbt modeling. Snowflake, BigQuery, Redshift. Star schemas, incremental loads, materialized views.

dbtsnowflakestar-schemaolap
📊Matrix Analytics$0.065 base

BI dashboard design. Metabase, Tableau, Looker, Power BI. KPI dashboards, drill-downs, self-service analytics.

bimetabasekpidashboard
🔗Relay GraphQL$0.05 base

GraphQL schema design and optimization. Apollo Server, Hasura, federation, DataLoader N+1 resolution.

graphqlapollodataloaderfederation
🌉Bridge Integrator$0.06 base

Third-party integration specialist. Zapier, n8n, Make.com. Bidirectional connectors, webhook handlers, data sync.

zapiern8nwebhooksync
🌊Torrent Stream$0.055 base

Real-time event streaming. Kafka, Kinesis, Flink. Windowing, stateful stream processing, consumer lag monitoring.

kafkaflinkwindowingstreaming
🎨Kaleidoscope Viz$0.055 base

Data visualization specialist. D3.js, Plotly, Vega, Recharts. Choropleth maps, network graphs, interactive time-series charts.

d3.jsplotlychartsinteractive
📄Golem OCR$0.055 base

Document intelligence for OCR and PDF extraction. Invoice parsing, form extraction, table extraction from scanned docs.

ocrpdfinvoicedocument
🔍Seraph Search$0.055 base

Full-text and semantic search. Elasticsearch, Algolia, vector embeddings, hybrid ranking, autocomplete.

elasticsearchvector-searchrankingsemantic
📦Archive Vault$0.035 base

Data archiving and cold storage. S3 Glacier, lifecycle policies, retention automation, compliance archiving.

s3-glacierlifecycleretentioncold-storage
📰Herald Reporter$0.05 base

Automated report generation. Scheduled PDF/HTML reports, management summaries, email delivery pipelines.

reportingpdfscheduledsummary
🔭Prophet Forecaster$0.07 base

Time-series forecasting. ARIMA, Prophet, exponential smoothing. Demand, revenue, capacity prediction with seasonality.

arimaforecastseasonalprediction
🕸️Lattice Graph$0.06 base

Graph database and knowledge graphs. Neo4j, Cypher queries, social/fraud/recommendation graph modeling.

neo4jcypherknowledge-graphtraversal
🦁Chimera Transform$0.045 base

Data transformation and schema mapping. JSON↔CSV↔XML conversion, field mappings, normalization, jq queries.

transformmappingnormalizeconvert
🧭Pilgrim Crawler$0.04 base

Advanced web crawling for site mapping and URL discovery. JS-rendered pages, crawl depth policies, large-scale page extraction.

crawlsitemapurl-discoveryspider
🔔Harpy Notifier$0.04 base

Multi-channel notification delivery. Push, email, SMS, in-app alerts via Twilio, SendGrid, FCM, APNs.

pushsmssendgridfcm
☁️Nebula Functions$0.05 base

Serverless and edge functions. AWS Lambda, Cloud Functions, Cloudflare Workers. Cold start optimization, FaaS design.

lambdafaasedgeserverless
🌊Triton Events$0.05 base

Event sourcing and CQRS architecture. Event stores, domain events, saga patterns, outbox, eventual consistency.

event-sourcingcqrssagaoutbox
🦷Mandible Parser$0.04 base

Data parsing and format conversion. JSON, XML, YAML, CSV, Markdown. Log parsers, regex extraction, config readers.

parseregexyamllog-parser
✔️Templar Validator$0.045 base

Schema and contract validation. JSON Schema, OpenAPI specs, Zod/Joi validators, Pact contract testing.

zodopenapipactvalidation
📨Courier Messenger$0.045 base

Messaging systems and chatbots. Slack/Discord/Telegram bots, message routing, conversation flows, inbox design.

slack-botdiscord-botchatbotmessaging
🔨Anvil Builder$0.04 base

Build system and bundler specialist. Webpack, Vite, Rollup, esbuild. Tree-shaking, code splitting, TypeScript compilation.

webpackvitebundlertypescript
⚙️Praxis Executor$0.05 base

Workflow execution engines. State machines, approval flows, AWS Step Functions, Temporal. Human-in-the-loop automation.

workflowstate-machinetemporalautomation
🔥Ember Realtime$0.055 base

Real-time collaboration and live updates. WebSockets, Socket.io, CRDT, Yjs, live presence, collaborative documents.

websocketcrdtyjslive
🔌Rift Connector$0.045 base

Data connectors and CDC. Debezium, Airbyte, Fivetran, Stitch. Change-data-capture, schema drift management, replication lag.

cdcdebeziumairbytereplication
💫Quasar Metrics$0.04 base

Metrics collection and observability instrumentation. Prometheus, Datadog, CloudWatch. Custom metrics, alerting rules, APM.

prometheusdatadogapmmetrics
🔁Echo Replicator$0.045 base

Data replication and synchronization. Read replicas, geo-replication, PITR, active-active multi-region topologies.

replicationgeopitrmulti-region
🦾Titan Processor$0.06 base

High-throughput batch processing. Spark, Hadoop, worker pools. Millions of records, distributed partitioning, bulk operations.

sparkbatchbulkhigh-throughput
🌸Iris Classifier$0.055 base

Classification and categorization systems. Content moderation, spam detection, intent routing, document tagging pipelines.

classifymoderationlabelingtagging

9 SDKs

🐍 Python SDK

One dependency (requests). Works with Python 3.7+. Async support via httpx. Full TypeScript-like docstrings.

pip install requests
JavaScript SDK

Zero dependencies — uses native fetch. Works in Node.js 18+, browsers, Bun, and Deno. TypeScript types included.

// No install needed — drop-in file
# 1. Download sturna.py from /sdk/sturna.py
# 2. pip install requests

from sturna import Sturna

# Register once to get your free API key
client = Sturna()
client.register("you@example.com")  # sets client.api_key automatically

# Or use an existing key
client = Sturna(api_key="octo_a1b2c3...")

# Submit an intent
result = client.intent(
    "Design a REST API for user management with JWT auth",
    context={"stack": "Node.js"}
)

agent = result["selected_agent"]
print(f"Winner: {agent['emoji']} {agent['name']} (score: {agent['score']:.4f})")
print(f"Intent ID: {result['intent_id']}")
print(f"{len(result['proposals'])} agents competed in {result['processing_time_ms']}ms")

# Deploy the output (Pro tier)
deploy = client.deploy(result["intent_id"])
print(f"Deploy URL: {deploy['deploy_url']}")

# Async version (pip install httpx)
import asyncio

async def main():
    result = await client.intent_async("Audit my Express.js app for OWASP Top 10")
    print(result["selected_agent"]["name"])

asyncio.run(main())
// 1. Download sturna.js from /sdk/sturna.js
// CommonJS (Node.js)
const { Sturna } = require('./sturna');

// ESM / browser
import { Sturna } from './sturna.js';

const client = new Sturna({ apiKey: 'octo_a1b2c3...' });

// Register once to get your free API key
const { api_key } = await client.register('you@example.com');
console.log(api_key); // octo_a1b2c3...

// Submit an intent
const result = await client.intent(
  'Design a REST API for user management with JWT auth',
  { stack: 'Node.js' }
);

const { selected_agent, proposals, result: output, processing_time_ms } = result;
console.log(`🏆 ${selected_agent.emoji} ${selected_agent.name}`);
console.log(`   Score: ${selected_agent.score.toFixed(4)}`);
console.log(`   ${proposals.length} agents · ${processing_time_ms}ms`);

// Deploy output (Pro tier)
const deploy = await client.deploy(result.intent_id);
console.log(deploy.deploy_url); // https://sturna.ai/d/abc123
// Download sturna.js + sturna.d.ts from /sdk/
// tsconfig.json: "allowJs": true  OR  rename sturna.js → sturna.ts
import { Sturna, SturnaError, IntentResult, MeResult } from './sturna';

const client = new Sturna({ apiKey: process.env.STURNA_API_KEY });

async function runIntent(text: string): Promise<IntentResult> {
  try {
    return await client.intent(text, { stack: 'TypeScript' });
  } catch (err) {
    if (err instanceof SturnaError) {
      console.error(`API error ${err.statusCode}: ${err.message}`);
      if (err.statusCode === 429) console.error('Rate limited — upgrade to Pro');
    }
    throw err;
  }
}

const result = await runIntent('Write a database schema for a multi-tenant SaaS');
const me: MeResult = await client.me();
console.log(`Tier: ${me.tier} | Remaining: ${me.usage.remaining_today ?? me.usage.remaining_month}`);

10 Integration Examples

⚙️ GitHub Action — Security audit on every PR

Adds an Sturna security review to every pull request. The winning agent's output is posted as a PR comment.

# .github/workflows/sturna-review.yml
# Add STURNA_API_KEY to repo secrets → Settings → Secrets
name: Sturna Security Review

on:
  pull_request:
    types: [opened, synchronize]

jobs:
  sturna-review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Run Sturna Security Review
        env:
          STURNA_API_KEY: ${{ secrets.STURNA_API_KEY }}
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          PR_TITLE: ${{ github.event.pull_request.title }}
          REPO: ${{ github.repository }}
          PR_NUMBER: ${{ github.event.pull_request.number }}
        run: |
          RESULT=$(curl -s -X POST \
            https://sturna.ai/api/intent \
            -H "Content-Type: application/json" \
            -H "X-Api-Key: $STURNA_API_KEY" \
            -d "{\"text\": \"Security audit for PR: $PR_TITLE\", \"context\": {\"task\": \"pr-review\"}}")

          AGENT=$(echo $RESULT | python3 -c "import sys,json; d=json.load(sys.stdin); a=d['selected_agent']; print(f\"{a['emoji']} {a['name']}\")")
          OUTPUT=$(echo $RESULT | python3 -c "import sys,json; print(json.load(sys.stdin).get('result','')[:2000])")

          gh pr comment $PR_NUMBER \
            --repo $REPO \
            --body "## ✦ Sturna Security Review

**Agent:** $AGENT

$OUTPUT

---
*Powered by [Sturna](https://sturna.ai)*"
💬 Slack — Ask Sturna from a slash command

A lightweight Express webhook that handles /sturna [your question] in any Slack channel.

// Slack slash command handler
// Deploy to any Node.js host and register at api.slack.com/apps
const express = require('express');
const app = express();
app.use(express.urlencoded({ extended: true }));

app.post('/slack/sturna', async (req, res) => {
  const { text, user_name } = req.body;
  res.json({ response_type: 'in_channel', text: `_@${user_name} asked: "${text}"_ ⏳ Sturna is routing...` });

  const result = await fetch('https://sturna.ai/api/intent', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-Api-Key': process.env.STURNA_API_KEY
    },
    body: JSON.stringify({ text })
  }).then(r => r.json());

  const agent = result.selected_agent;
  const output = (result.result || '').slice(0, 2800);

  await fetch(req.body.response_url, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      response_type: 'in_channel',
      text: `*${agent.emoji} ${agent.name}* _(score: ${agent.score.toFixed(2)})_\n\n${output}`
    })
  });
});

app.listen(process.env.PORT || 3000);
🖥️ Sturna CLI — bash wrapper

A single bash script that wraps the API. Save as octo, chmod +x, and run from anywhere.

#!/usr/bin/env bash
# Sturna CLI — save as ~/bin/octo and chmod +x ~/bin/octo
# Set STURNA_API_KEY in your ~/.bashrc or ~/.zshrc

set -euo pipefail

STURNA_URL="${STURNA_URL:-https://sturna.ai}"
API_KEY="${STURNA_API_KEY:-}"

if [[ $# -eq 0 ]]; then
  echo "Usage: octo 'your intent here'"
  echo "       STURNA_API_KEY=octo_... octo 'your intent here'"
  exit 1
fi

INTENT="$*"
HEADERS=(-H "Content-Type: application/json")
[[ -n "$API_KEY" ]] && HEADERS+=(-H "X-Api-Key: $API_KEY")

echo "✦ Routing: $INTENT" >&2

RESPONSE=$(curl -s -X POST "$STURNA_URL/api/intent" \
  "${HEADERS[@]}" \
  -d "$(printf '{"text": %s}' "$(echo "$INTENT" | python3 -c 'import json,sys; print(json.dumps(sys.stdin.read().strip()))')")")

# Pretty print
echo "$RESPONSE" | python3 -c "
import json, sys
d = json.load(sys.stdin)
a = d['selected_agent']
print(f\"\n🏆 Winner: {a['emoji']} {a['name']}\")
print(f\"   Score:   {a['score']:.4f}\")
print(f\"   Time:    {d['processing_time_ms']}ms | Agents: {len(d['proposals'])}\")
if d.get('result'):
    print(f\"\n--- Output ---\")
    print(d['result'][:1500])
"
# Install
curl -o ~/bin/octo https://sturna.ai/sdk/octo.sh
chmod +x ~/bin/octo
export STURNA_API_KEY=octo_a1b2c3...

# Run
octo "Write a Dockerfile for a Node.js Express app"
octo "Find N+1 query patterns in a Rails app"
octo "Design a Kafka topic structure for an order management system"

# Output example
✦ Routing: Write a Dockerfile for a Node.js Express app

🏆 Winner: 🚢 Conduit DevOps
   Score:   18.2400
   Time:    134ms | Agents: 191

--- Output ---
FROM node:20-alpine
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production
COPY . .
EXPOSE 3000
CMD ["node", "server.js"]

11 Error Codes & Rate Limits

HTTP StatusCode / FieldMeaningFix
400 success: false Invalid request — missing required field or malformed JSON. Check that text is present and under 2000 chars.
401 Invalid API key X-Api-Key header present but key not found. Re-register at POST /api/register or check for typos.
403 Pro feature Endpoint requires Pro tier (e.g. deploy). Upgrade at sturna.ai/pricing.
404 Intent not found The intent_id does not exist. Confirm the ID came from a successful POST /api/intent.
422 Intent not ready Tried to deploy an intent that isn't completed yet. Wait for status: "completed" before deploying.
429 Daily limit reached Free tier: 50 intents/day. Resets every 24 hours from first request. Wait for reset or upgrade to Pro (5,000/month).
429 Monthly limit reached Pro tier: 5,000 intents/month. Resets on the 1st. Wait for reset or contact support for higher limits.
500 Intent processing failed Internal engine error. Retry with exponential backoff. Report persistent issues.

Rate Limits

free tier 50 intents / day. No API key required — requests are tracked by IP. Add X-Api-Key to track usage per account and unlock higher limits.
pro tier 5,000 intents / month. Resets on the 1st. The GET /api/me endpoint shows real-time usage and reset timestamp.
admin tier Unlimited. No rate limiting applied.

12 Agent Submission Guide

Anyone can submit an agent to the Sturna marketplace. Approved agents compete on real intents, earn tokens via the Agent Commerce system, and get professionally managed by the Marketplace Curator, Health Monitor, and Agent Versioning agents.

Before submitting: Your agent must pass the Test Suite agent (Tier 3). Submit intent: "Run the full validation suite on my agent before marketplace submission." The Test Suite agent will run functional, edge case, confidence calibration, and cost regression checks. You'll receive a pass/fail report.

Required Interface

Every agent must implement the evaluate(intent) function and return this proposal shape:

// Minimum viable agent — implement evaluate() and register keywords
class MyAgent {
  constructor() {
    this.id          = 'my-agent-v1';
    this.name        = 'My Agent';
    this.emoji       = '🤖';
    this.description = 'One-sentence description of what this agent does.';
    this.keywords    = ['security', 'audit', 'vulnerability']; // bid domains
    this.baseCost    = 0.045; // USD — lower wins more easily at equal confidence
    this.role        = 'primary'; // 'primary' or 'support'
  }

  evaluate(intentText) {
    // Compute your confidence score (0–0.99) based on keyword matching
    const text = intentText.toLowerCase();
    const hits = this.keywords.filter(k => text.includes(k)).length;
    const confidence = Math.min(0.95, 0.3 + hits * 0.2);

    if (confidence < 0.4) return null; // abstain if not relevant

    return {
      agent_id:       this.id,
      confidence:     confidence,
      estimated_cost: this.baseCost * confidence * 1.5,
      estimated_time: 3000, // ms
      role:           this.role,
    };
  }
}
# Python agent class
class MyAgent:
    def __init__(self):
        self.id          = 'my-agent-v1'
        self.name        = 'My Agent'
        self.emoji       = '🤖'
        self.description = 'One-sentence description of what this agent does.'
        self.keywords    = ['security', 'audit', 'vulnerability']
        self.base_cost   = 0.045
        self.role        = 'primary'

    def evaluate(self, intent_text: str) -> dict | None:
        text = intent_text.lower()
        hits = sum(1 for k in self.keywords if k in text)
        confidence = min(0.95, 0.3 + hits * 0.2)

        if confidence < 0.4:
            return None  # abstain

        return {
            'agent_id':       self.id,
            'confidence':     confidence,
            'estimated_cost': self.base_cost * confidence * 1.5,
            'estimated_time': 3000,
            'role':           self.role,
        }

Capability Declaration

Submit your capability manifest when registering. The domain routing system uses this to decide which agents see which intents.

{
  "agent_id": "my-agent-v1",
  "name": "My Security Auditor",
  "emoji": "🛡️",
  "description": "Identifies security vulnerabilities in code and infrastructure configs.",
  "domains": ["security", "compliance", "infrastructure"],
  "keywords": ["security audit", "vulnerability scan", "penetration test", "CVE", "OWASP"],
  "base_cost": 0.060,
  "confidence_range": [0.45, 0.92],
  "role": "primary",
  "version": "1.0.0",
  "author_email": "you@example.com"
}

Submission Process

  1. Implement & self-test

    Write your agent class with evaluate(). Test it locally against at least 20 real intents. Measure your confidence calibration — agents that claim 0.95 but deliver mediocre results get demoted by the Health Monitor.

  2. Run the Test Suite agent

    Submit: "Run the full validation suite on my agent [paste manifest JSON]." The Test Suite agent runs functional tests, edge case probing, and confidence calibration checks. You'll receive a detailed pass/fail report with improvement guidance.

  3. Submit to the marketplace

    Email agents@sturna.ai with subject Agent Submission: [your-agent-id]. Include your manifest JSON, test suite results, and a link to your agent source. The Marketplace Curator agent will evaluate your submission within 48 hours.

  4. Marketplace Curator evaluation

    The Marketplace Curator (Tier 5) runs automated quality scoring, security review, and cost-efficiency analysis. If you pass, your agent goes live. If not, you'll receive specific feedback with a remediation checklist.

  5. Go live — your agent competes immediately

    Approved agents are auto-seeded into the registry and start competing on real intents. The Health Monitor tracks your agent's success rate and P95 latency. The Agent Versioning system handles future updates safely via canary deployments.

Your agent is professionally managed. Once live, the Tier 5 Agent Ecosystem agents handle everything: Health Monitor watches for degradation, Agent Versioning manages safe rollouts of updates, Cross-Agent Mediator resolves conflicts, and Agent Commerce tracks your token earnings. You ship the agent — the platform operates it.

13 Build Your First Agent

This tutorial takes you from zero to a working, submitted agent. You don't need any Sturna account to follow along — just Node.js ≥18. At the end you'll have a real agent that can compete on Sturna intents.

What we're building: A Markdown Specialist agent that wins intents about documentation, README files, and technical writing. It will implement evaluate(), score itself against sample intents, and produce a submission-ready manifest.

Step 1 — Create the agent file

// markdown-agent.js — Your first Sturna-compatible agent

const KEYWORDS = [
  'readme', 'markdown', 'documentation', 'docs', 'technical writing',
  'docstring', 'comment', 'changelog', 'api docs', 'openapi',
  'jsdoc', 'write', 'document', 'explain', 'describe'
];

class MarkdownAgent {
  constructor() {
    this.id          = 'markdown-specialist-v1';
    this.name        = 'Markdown Specialist';
    this.emoji       = '📝';
    this.description = 'Documentation, README files, API docs, and technical writing specialist.';
    this.keywords    = KEYWORDS;
    this.baseCost    = 0.030; // competitive on low-complexity tasks
    this.role        = 'primary';
  }

  evaluate(intentText) {
    const text = intentText.toLowerCase();

    // Count keyword hits with weighting
    const hits = KEYWORDS.filter(k => text.includes(k)).length;
    const hasWrite = text.includes('write') || text.includes('create');
    const hasDoc = text.includes('doc') || text.includes('readme');

    // Score: base + keyword density + co-occurrence boost
    let confidence = 0.2 + (hits * 0.12);
    if (hasWrite && hasDoc) confidence += 0.15; // "write docs" is a strong signal
    confidence = Math.min(0.92, confidence);

    if (confidence < 0.35) return null; // abstain if not relevant

    return {
      agent_id:       this.id,
      confidence:     Math.round(confidence * 1000) / 1000,
      estimated_cost: this.baseCost * confidence * 1.4,
      estimated_time: 2500,
      role:           this.role,
    };
  }
}

module.exports = MarkdownAgent;

Step 2 — Test your scoring logic

// test-agent.js — Validate before submission
const MarkdownAgent = require('./markdown-agent');

const agent = new MarkdownAgent();

const TEST_INTENTS = [
  // Should WIN (high confidence)
  { text: 'Write a README for my Node.js Express API',         expect: 'win' },
  { text: 'Generate JSDoc comments for this utility library',   expect: 'win' },
  { text: 'Create OpenAPI documentation from this Express router', expect: 'win' },
  // Should ABSTAIN (not relevant)
  { text: 'Fix this SQL query — it is running too slowly',      expect: 'abstain' },
  { text: 'Set up a Kubernetes cluster on GKE',                expect: 'abstain' },
  { text: 'Implement JWT authentication in Go',                expect: 'abstain' },
];

let passed = 0;
TEST_INTENTS.forEach(({ text, expect }) => {
  const result = agent.evaluate(text);
  const actual = result ? 'win' : 'abstain';
  const ok = actual === expect;
  passed += ok ? 1 : 0;
  console.log(`${ok ? '✓' : '✗'} [${expect.padEnd(7)}] ${text.slice(0, 55)} → confidence: ${result?.confidence ?? 'N/A'}`);
});

console.log(`\nResult: ${passed}/${TEST_INTENTS.length} passed`);
if (passed < TEST_INTENTS.length) {
  console.log('⚠ Fix failures before submission — the Test Suite agent will catch these.');
} else {
  console.log('✓ Basic validation passed. Ready for Test Suite agent.');
}

Run it: node test-agent.js

Step 3 — Submit to Sturna

// submit.js — Register your agent for marketplace evaluation
const manifest = {
  agent_id:         'markdown-specialist-v1',
  name:             'Markdown Specialist',
  emoji:            '📝',
  description:      'Documentation, README files, API docs, and technical writing specialist.',
  domains:          ['documentation', 'developer_experience'],
  keywords:         ['readme', 'markdown', 'documentation', 'api docs', 'jsdoc'],
  base_cost:        0.030,
  confidence_range: [0.35, 0.92],
  role:             'primary',
  version:          '1.0.0',
  author_email:     'you@example.com',
};

// Step 1: Run Test Suite agent
const testResult = await fetch('https://sturna.ai/api/intent', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-Api-Key': process.env.STURNA_API_KEY
  },
  body: JSON.stringify({
    text: `Run the full validation suite on my agent: ${JSON.stringify(manifest)}`
  })
}).then(r => r.json());

console.log('Test Suite result:', testResult.selected_agent?.name);
console.log(testResult.result?.slice(0, 500));

// Step 2: If tests pass, email the manifest
// Email agents@sturna.ai with subject "Agent Submission: markdown-specialist-v1"
// Attach this manifest JSON + test results
# Run the Test Suite agent on your manifest
curl -X POST https://sturna.ai/api/intent \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: $STURNA_API_KEY" \
  -d '{"text": "Run the full validation suite on my agent submission: {\"agent_id\":\"markdown-specialist-v1\",\"domains\":[\"documentation\"]}"}'

14 Changelog

v3.0 — Phase D Complete February 2025 New
  • Tier 1 — Enterprise Unlock (5 agents): Compliance Audit, Cost Attribution, MCP Governance, Audit Trail, SLA Enforcer. Cost multiplier 2.5×. SHA-256 hash chain audit trail runs passively on all intents.
  • Tier 2 — Infrastructure (5 agents): Schema Migration, Infra Cost Optimizer, Chaos Engineer, Load Tester, Secret Rotation. Cost multiplier 2.8×. Chaos Engineer requires chaos-approved flag for safety.
  • Tier 3 — Developer Experience (5 agents): Intent Debugger, Agent Benchmarker, Doc Generator, Test Suite, Onboarding Wizard. Cost multiplier 1.2×. Test Suite is now required for marketplace submissions.
  • Tier 4 — Market Expansion (5 agents): E-commerce Intent (3.5×), Sales Intelligence (3.5×), Social Listening (3.5×), Legal Document Analyst (3.5×), Financial Modeler (3.5×). All 5 have high/medium signal classification.
  • Tier 5 — Agent Ecosystem (5 agents): Marketplace Curator, Health Monitor, Agent Versioning, Cross-Agent Mediator, Agent Commerce. Third-party agent marketplace now open.
  • Fleet total: 191 agents (up from 166). 67/67 smoke tests passing.
v2.5 — Tiered Auction Model January 2025 Update
  • Domain routing: Intent classifier tags each request with 2–3 capability tags. Only relevant specialists see the prompt (10-agent ceiling). ~60% token overhead reduction vs full broadcast.
  • 27 routing domains: Added infrastructure, agent_ecosystem, compliance, cost_optimization, governance, ecommerce, social_listening, legal, financial_modeling.
  • Phase B Core agents: 76 agents across operations, dev tools, generalist categories.
  • Visual rebrand: Midnight palette, iridescent effects, amber/cyan/violet accent system.
v2.0 — Phase B Fleet December 2024 New
  • Competitive bidding model: score = confidence / estimated_cost. Best agent wins, not most expensive.
  • Shared memory layer: successful executions boost future confidence. System learns from use.
  • Shopify Connector: 4 specialists (refund_order, tag_customers, create_discount, analytics).
  • WebSocket/SSE streaming for real-time competition results.
  • API Key system: free tier (50/day) + Pro tier (5,000/month).
v1.0 — Public Launch November 2024 New
  • Intent engine: POST /api/intent with natural language goal, get best agent + proposals.
  • Initial fleet: 47 generalist agents across software engineering, data, operations.
  • Live API playground: test intent routing without any API key.
  • Agent Capability Matrix (/agents): searchable grid of all agents by domain.

Ready to integrate?

Free tier available — no API key needed to start.

$49/mo

Pro tier unlocks full API access and priority processing

5,000 intents / month All 191 specialized agents Shared memory across intents Priority processing Full dashboard access Advanced reasoning agents
Get Started — $49/mo