DreamerOS
Developer Portal

Your AI has no integrity layer.
One API call fixes that.

DreamerOS is not another AI wrapper. It is a verified execution pipeline. Every response passes through a question shaper, integrity checks, drift detection, and a follow-up forecaster before it reaches your application. Ship AI features that are structured, checked, and auditable from day one.

Request API access Explore endpoints
quickstart.py
from dreameros import DreamerOS client = DreamerOS(api_key="dos_...") # One call. Verified output. response = client.prompt( input="Summarize the key risks in this contract", mode="structured", verify=True ) # Every response includes: # - Verified output (structured) # - Integrity score # - Digital Buoyancy breakdown # - Session ID for memory # - Routing metadata print(response.output) print(response.integrity_score) # 0.97 print(response.integrity.drift) # None
Who this page is for

This is the developer surface. If you do not write code, skip it - the same integrity checks run behind the scenes when you use the Pro web app or the GPT. If you do write code, this is how you ship the same pipeline inside your own product: one HTTP call, structured output, an integrity score on every response, a session id for memory, and an audit trail your compliance team can actually export. The endpoints below cover the full pipeline. The quickstart below runs in three lines.

Architecture

What runs on every API call

Six stages. Your user sees none of them. Your team can audit all of them.

Input
Your prompt
Layer 1
Question Shaper
Layer 2
Smart Routing
Layer 3
Integrity Check
Layer 4
Forecaster
Output
Verified response

Every stage is logged. Every stage is queryable. Your compliance team will thank you.

Endpoints

Six endpoints. Every response checked.

REST API. JSON in, JSON out. Bearer auth. Rate limits scale with your tier.

POST /v1/prompt

The core endpoint. Send natural language, get structured, checked output. Every response passes through the full question shaper, integrity check, and routing pipeline.

Question shaped Integrity verified Auto-routed
{ "output": { "quick": "...", "deep": "...", "forecast": "..." }, "integrity": { "score": 0.97, "flags": [], "drift": null }, "buoyancy": { "auth": 100, "authz": 98, "acct": 100 }, "routing": { "engine": "execution", "mode": "strategic" }, "session_id": "ses_a1b2c3..." }
POST /v1/integrity/check

Submit any AI output for integrity checking. Returns hallucination flags, assumption detection, unsupported claims, and a confidence score. Works on output from any model - not just DreamerOS.

Hallucination scan Assumption flags
{ "score": 0.94, "flags": [{ "type": "assumption", "text": "Assumes US jurisdiction" }], "silent_drops": [], "drift_detected": false }
POST /v1/route

Let DreamerOS pick the right engine and thinking mode for a task. Returns routing metadata without running the prompt. Useful for pre-flight checks and custom pipelines.

auto mode detection 6 core domains
GET /v1/session/{id}

Retrieve session state, conversation history, and accumulated context. Sessions persist across API calls so each new request builds on everything before it.

Persistent memory Cross-call context
POST /v1/webhooks

Register webhook URLs for real-time event callbacks. Get notified when tasks hit integrity checkpoints, chains complete, integrity scores drop below threshold, or human approval is needed.

Review gates Automation triggers
GET /v1/buoyancy/score

Your trust score for the account - authentication, authorization, and accounting metrics rolled up across every API call. Export it for compliance reporting.

Compliance ready Audit trail
MCP dreameros_slop_check

Anti-Slop Check. Catches weak AI output patterns - defensive guards, narration comments, premature abstractions, half-finished stubs - before they reach your users.

Pro tier MCP tool Advisory on all tiers
B2B Trust API - live in production

Ten endpoints. Trust and integrity primitives for AI products.

Built on the core pipeline. Verify any AI output, underwrite a claim, issue bonds against integrity scores, prove provenance, and export compliance audit trails. Five public-callable consumer endpoints, five B2B and enterprise endpoints. All use the same Bearer token.

Tier 1 - consumer endpoints (any tier)
POST /api/v1/verify

Submit any text claim for verification. Returns a signed verdict you can share with your own customers. Three depth tiers: light (free, any tier), deep (Pro+, $0.05), exhaustive (Elite, $0.25). More depth means more detail in the response.

light: free deep: $0.05 exhaustive: $0.25
{ "verdict": "verified", "score": 0.94, "depth": "deep", "flags": [], "signature": "ed25519:...", "cost_usd": 0.05 }
GET /api/v1/fingerprint/export

Export your behavioral fingerprint as a signed, portable passport. Five behavioral axes plus engine trust scores, signed with ed25519. Any downstream AI can verify and import it via MCP, so your tone, preferences, and trust history follow you to every tool you use.

Cross-tool continuity Signed receipt MCP-importable
GET /api/v1/leaderboard/caught-this-week

Public, no-auth feed of the top 20 users by high and critical integrity catches in the past 7 days. User IDs are SHA-256 pseudonyms - no PII. It proves the system catches real drift in real time, not just benchmark cases.

Public Pseudonymous
GET /api/v1/dashboard/cross-service-feed

Unified event feed across Sentry, Railway, Vercel, Supabase, and GitHub for your account. One endpoint, one shape, one auth. Tells you what just broke without opening five dashboards. Per-source failures degrade to a warning - the whole feed never goes blank.

Elite 5 sources unified
POST /api/v1/intent/clarify

Send an ambiguous prompt, get back the structured version that would actually run. Public for any tier; Pro+ unlocks the full layer - emotion signal, depth hint, and an ambiguity score. Use it to pre-flight a prompt before paying for execution, or to figure out why an AI misread you.

Public Pro+ full
Tier 2 - B2B and Enterprise endpoints
POST /api/v1/underwrite

Submit an AI-generated decision or recommendation; get back an underwritten verdict you can stand behind. Combines a fidelity score, depth audit, and a signed certificate. Pro+, $0.10 per call. Use it when "the AI said so" is not a defensible answer.

Pro+ $0.10 / call Signed receipt
GET / POST /api/v1/bonds/*

Issue and list bonds backed by integrity scores. GET /listings returns public bond inventory. POST /issue mints a new bond against an underwritten claim. Bonded performance instead of unbacked promises. Pro+ to issue, public to read.

/listings public /issue Pro+
{ "bond_id": "bond_a1b2c3...", "backing_score": 0.96, "underwriter_signature": "ed25519:...", "face_value_usd": 10000 }
POST / GET /api/v1/provenance/*

Anchor an AI output to a verifiable provenance chain. POST /claim registers a new claim with engine, model, integrity metadata, and a content hash. GET /{claim_id} resolves the chain. C2PA-aligned. Use it to prove which model said what, when, and under which integrity check.

Pro+ C2PA-aligned
GET /api/v1/audit/export

Audit Export. Returns the full append-only integrity events trail for your account as a compliance-ready bundle - JSONL plus manifest plus signature. One endpoint, no manual assembly, ready for SOC, ISO, and internal review. Elite only.

Elite Append-only Compliance-ready
Pricing

Tier 2 endpoints are usage-billed through integrity_events.cost_usd - no separate metered-billing setup. Costs land on your Stripe invoice at month-end, itemized by endpoint. Underwriter is $0.10 per call, Bonds is per-bond face-value percentage, Provenance is included with Pro+, Audit Export is included with Elite. No surprise charges - every call is logged before it bills.

No metered surprises Stripe-itemized
MCP Connectors

Integrity checks inside any AI tool

DreamerOS ships as an MCP connector for any compatible AI client. Plug integrity checks directly into Claude, ChatGPT, Gemini, Grok, Perplexity, or any MCP-compatible tool.

Light connector (free)

Behavioral integrity. A 27-principle contract shapes output quality without computational transformation. Works with all supported engines.

Pro connector ($39.99/month)

The full pipeline. Question shaping, integrity validation, smart routing, token efficiency tracking, and connected memory. The complete integrity layer running inside whatever AI tool you already use.

Integration

The connector endpoint is live at the DreamerOS gateway. Authentication is via API key. Tier-based routing runs server-side - the connector surface looks the same on Light and Pro, but the pipeline depth changes with your subscription.

Get started

Three lines. Verified output.

Python SDK, Node SDK, or raw cURL. Pick your tool.

Python

Async-ready. Type-hinted. Works with FastAPI, Django, and Flask.

Python SDK - coming soon

Node.js

ESM and CommonJS. Works with Next.js, Express, and serverless.

Node.js SDK - coming soon

cURL / REST

Standard REST. JSON in, JSON out. Bearer auth. Drop it into any stack.

Authorization: Bearer dos_...
terminal
from dreameros import DreamerOS client = DreamerOS(api_key="dos_your_key") response = client.prompt( input="Should I open a second location?", verify=True ) print(response.output.quick) # "Before expanding, audit unit economics on location one. # Most second-location failures are location-one problems # that got exported." print(response.integrity_score) # 0.96 - no hallucinations, no assumptions flagged
CI/CD ready

Integrity checks that ship with your code

Drift detection in your pipeline. File hash verification on every deploy. Integrity scoring in your tests.

Drift Sentinel

Automated behavioral tests on every deploy. Define expected behaviors in YAML. DreamerOS runs test prompts against the live system and checks outputs against your baselines. Drop below 90% pass rate and the pipeline stops.

# .github/workflows/drift.yml - name: Run Drift Sentinel run: dreameros drift-test --baseline v5.yaml

File Hash Verification

Every integrity file is SHA-256 hashed in a registry. The gateway checks hashes on startup. If any file has been tampered with, the system will not start. Add verify_canon.py to your CI to catch drift before it ships.

# Block deploys on canon mismatch - name: Verify Canon Integrity run: python verify_canon.py

Fail-Closed Gateway

If the integrity check system is unreachable, the API returns 503 - not a degraded response. If file hash verification fails, the gateway will not start. If direction sets fail to load, no requests go through. Integrity is never optional.

# No silent degradation. Ever. "error": "integrity_unavailable" "status": 503
Integrity

Every request authenticated, authorized, and accounted for

API keys are scoped to your organization and tied to tier permissions. Rate limits scale with your plan. Every request is logged in the accounting layer.

Keys are generated from your DreamerOS dashboard. Each key is bound to a single organization with configurable permission scopes. You can rotate, revoke, or scope keys to specific endpoints at any time.

Rate limits are applied per key and vary by tier - from development sandbox to production throughput. Every request is logged for auditability.

auth.sh
# Bearer token authentication curl -X POST https://api.dreameros.app/v1/prompt \ -H "Authorization: Bearer dos_your_key" \ -H "Content-Type: application/json" \ -d '{ "input": "Analyze this quarterly report", "verify": true }' # Response headers include: # X-RateLimit-Remaining: 94 # X-Integrity-Score: 98 # X-Integrity-Status: passed # X-Session-ID: ses_a1b2c3
Who this is for

Builders who take AI seriously

Whether you are shipping your first AI feature or running AI at organizational scale.

Solo devs and indie hackers

"I need AI features but I don't have a team to build safety infrastructure."

Ship AI features with built-in integrity checks from day one. Hallucination detection, integrity checking, and audit trails come with every API call. Focus on your product, not AI reliability plumbing.

Product teams and SaaS platforms

"Our AI features are inconsistent. Users don't trust the output."

Embed DreamerOS into your existing product. Every response includes integrity metadata so you can build trust into your UX - not just hope for it.

CS students and AI researchers

"I want to understand intent-verified AI architecture, not just consume APIs."

DreamerOS exposes its integrity internals. Every response includes routing metadata, integrity scores, and engine selection rationale. Study how checked AI systems work, build research projects around drift detection, or benchmark integrity scoring against your own models.

Enterprise and Elite teams

"We need verified AI across our entire org with role-based access and audit trails."

Multi-engine orchestration, organization-wide session memory, role-based API keys, full audit logging, custom domain modules, and webhook-driven automation. The integrity infrastructure you would eventually build yourself - already built and running in production.

Ready to build?

Request API access and start shipping AI with integrity checks built in from day one.

Request API access Try DreamerOS free DreamerOS GPT

Or see all tiers side by side for the full feature breakdown.

DreamerOS API - intent-verified AI for developers Request access
98