Legal terms, safety & operating boundaries

All sensitive credentials—including inference API keys, messaging bot tokens, database passwords, and cryptographic secrets—must reside strictly in git-ignored environment configuration files or secure hardware key stores. Credentials must never be embedded in source code, committed to version control, stored in client-side browser storage, or included in shareable entity shells.

Hosted inference credentials must remain server-side behind the runtime gateway. Network interfaces, WebSocket bridges, and spatial daemon endpoints require strict cryptographic token authentication, schema-validated payloads, and rate-limiting. Local deployments do not require public network exposure; LAN mode must only be operated across verified, trusted private networks. Any remote gateway deployment must be secured with TLS, IP allowlists, and scoped credential boundaries.

ngram features self-directed agency, autonomous wake cycles, background routines, and multi-modal tool integration. When enabled by the operator, tools possess the capability to read, write, modify, or delete local filesystem records, execute arbitrary shell commands, invoke external APIs, initiate financial transactions, and transmit outbound messages across connected platforms.

Assumption of Risk: The operator assumes sole, non-delegable responsibility and risk for all actions taken by an entity. The operator must audit filesystem root allowances, command-line whitelists, external Model Context Protocol (MCP) server integrations, and messaging access controls prior to enabling autonomous operation. Under no circumstances should destructive tools, unconstrained shell execution, or high-privilege credentials be granted without active human oversight.

TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, THE SOFTWARE, ACCOMPANYING DOCUMENTATION, SPATIAL RUNTIMES, AND ASSOCIATED CODE REPOSITORIES ARE PROVIDED ON AN “AS IS” AND “AS AVAILABLE” BASIS, WITH ALL FAULTS AND DEFECTS, WITHOUT WARRANTY OF ANY KIND.

THE CONTRIBUTORS, MAINTAINERS, AUTHORS, AND COPYRIGHT HOLDERS SPECIFICALLY AND EXPRESSLY DISCLAIM ALL WARRANTIES, WHETHER EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE, INCLUDING WITHOUT LIMITATION ANY IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, QUIET ENJOYMENT, SYSTEM INTEGRATION, ACCURACY, TIMELINESS, COMPLETENESS, FREEDOM FROM PROGRAM BUGS, COMPUTER VIRUSES, OR MALICIOUS CODE, AND NON-INFRINGEMENT OF THIRD-PARTY INTELLECTUAL PROPERTY RIGHTS.

NO ORAL OR WRITTEN ADVICE, DOCUMENTATION, OR INFORMATION PROVIDED BY CONTRIBUTORS OR MAINTAINERS SHALL CREATE ANY WARRANTY OR IN ANY WAY EXPAND THE SCOPE OF RESPONSIBILITY BEYOND THIS DISCLAIMER.

TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL THE CONTRIBUTORS, MAINTAINERS, AUTHORS, COPYRIGHT HOLDERS, OR AFFILIATES BE LIABLE UNDER ANY LEGAL OR EQUITABLE THEORY—WHETHER IN CONTRACT, TORT (INCLUDING NEGLIGENCE), STRICT LIABILITY, INDEMNITY, OR OTHERWISE—FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, PUNITIVE, CONSEQUENTIAL, OR RELIANCE DAMAGES WHATSOEVER.

THIS EXCLUSION EXTENDS TO, WITHOUT LIMITATION, DAMAGES FOR LOSS OF PROFITS, ANTICIPATED SAVINGS, BUSINESS REVENUE, BUSINESS INTERRUPTION, LOSS OR CORRUPTION OF DATA, HARDWARE FAILURE, SYSTEM CORRUPTION, LOSS OF GOODWILL, PRIVACY BREACHES, THIRD-PARTY TOKEN BILLING EXCEEDANCES, FINANCIAL LOSSES INCURRED THROUGH AUTOMATED ACTIONS, OR ANY OTHER COMMERCIAL, PERSONAL, OR BODILY INJURY RESULTING FROM OR RELATED TO YOUR USE, MISUSE, INABILITY TO USE, OR RELIANCE UPON THE SOFTWARE OR ITS GENERATED OUTPUTS, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.

ngram operates by interfacing with probabilistic, generative machine learning models. Generative model outputs are inherently non-deterministic, fallible, and subject to algorithmic hallucinations, confabulations, omissions, contextual distortions, and unexpected behaviors. Generated responses do not reflect the viewpoints, policies, or endorsements of project contributors.

No Professional or Regulated Advice: Outputs generated by an ngram entity do not constitute licensed medical, psychiatric, psychological, legal, tax, financial, accounting, safety, or engineering advice. Operators, downstream integrators, and end users must never rely on entity output for life-critical, medical, emergency, regulatory, investment, or safety decisions without independent, qualified human verification.

ngram Spatial operates within immersive WebXR, virtual reality, and mixed reality hardware environments. Operators and users must at all times maintain an unobstructed physical boundary zone, observe hardware manufacturer chaperone boundaries, and discontinue usage immediately if experiencing visual disorientation, vertigo, nausea, or optical fatigue.

Prohibition on High-Risk and Industrial Deployments: Under no circumstances may the software, spatial bridge, motion generation provider, or entity tool system be deployed in connection with high-risk applications, including but not limited to life support systems, medical devices, nuclear operations, aircraft control, emergency response dispatch, or the actuation of heavy industrial robotics and safety-critical physical machinery. Any physical harm, property destruction, or casualty arising from unauthorized high-risk deployment is solely the liability of the operator.

Local-first deployment (e.g., via Ollama or local inference engines) retains conversation transcripts, semantic memory embeddings, and personal data exclusively on operator-controlled hardware. The core ngram runtime contains zero telemetry, analytics, or centralized surveillance tracking.

When configured in hosted or hybrid modes, prompt context, user messages, and entity memories are dispatched over the network to external third-party API providers (e.g., OpenAI, Anthropic, Google, Venice, OpenRouter, Mistral, xAI). Operators are solely responsible for reviewing and complying with the third-party privacy policies, terms of service, and data retention guidelines of their selected model providers. Operators must ensure lawful consent is obtained prior to transmitting personal data, voice recordings, image captures, or confidential information through external endpoints.

You agree to indemnify, defend, and hold harmless the project contributors, maintainers, authors, and associates from and against any and all claims, demands, losses, damages, liabilities, judgments, settlements, penalties, costs, and expenses (including reasonable attorneys’ fees and litigation costs) arising out of or relating to: (a) your access to, deployment of, or operation of ngram; (b) any actions, messages, or transactions executed by an entity under your configuration; (c) your breach of these terms, applicable law, or third-party intellectual property or privacy rights; or (d) any dispute between you and third-party API providers or downstream end users.

Operators agree to comply with all applicable local, national, and international laws, export control statutes, and sanctions. The following uses are strictly prohibited:

• Engaging in unlawful activities, computer crimes, denial of service, malware generation, or unauthorized network exploitation.
• Deceptive impersonation, identity fraud, non-consensual deepfake generation, or dissemination of intentional disinformation.
• Stalking, harassment, extortion, hate speech, or non-consensual surveillance, recording, or automated profiling of individuals.
• Development, enhancement, or operation of conventional, chemical, biological, or nuclear weaponry.
• Bypassing or subverting third-party terms of service, security barriers, rate limits, or access controls.

Security vulnerabilities should be reported responsibly through private security advisories and coordinated disclosure channels. Never publish vulnerabilities, active exploit scripts, credential leaks, private memory containers, or sensitive user transcripts in public issue trackers or open communication forums.