Stable evidence state
v2.0.0‑rc1 represents the separated and more stable runtime and evidence line.
NQIS
Local AI platform with audit, memory and governance.
NQIS is the technical core behind the Nova concept. The platform is intended to make local AI work reviewable: with knowledge base, grounded chat, roles, safety boundaries, operational status, evidence and controlled release states.
v2.0.0-rc1 evidence statev2.1.1-dev activeAuth/RBAC hardening
Active development
v2.1.1‑dev focuses on Auth/RBAC hardening, protected areas, role logic and governance for mutating actions.
Public framing
NQIS is described as a local auditable assistant platform without AGI, consciousness or unlimited autonomy claims.
Functional state
From experiment to reviewable AI operations platform.
The current state contains several building blocks that together form a traceable local AI environment. The important part is not only that an answer is generated, but how it is derived, which sources were used, which role is allowed to access it and which change remains traceable later.
NQIS is not a single chatbot. It is an orchestration and governance layer for local AI work. Memory, knowledge, API, dashboard, safety, evidence and release processes work together.
Covered areas
- local operation on owned infrastructure
- retrieval from memory/knowledge base
- grounded chat with source context
- refusal of uncertain current questions without reliable source
- API routes and OpenAPI description
- dashboard, ops and status data
- health, readiness and ops checks
- Auth/RBAC foundation
- roles admin, operator, reader, auditor
- protected dashboard, docs and ops areas
- secured mutating actions
- executor/tool execution blocked by default
- audit and evidence files
- release freeze and archiving
- restore and rollback probes
- separation of stable runtime and development line
Architecture principle
Every step should remain explainable.
| Layer | Task | Value |
|---|---|---|
| Memory & Knowledge | Provide sources, chunks, claims and concepts in structured form. | Answers can rely on traceable context. |
| Grounded Chat | Retrieve relevant sources and derive answers from them. | Reduces hallucinations and makes uncertainty visible. |
| Ops & Dashboard | Show health, readiness, workers, status, logs and evidence. | Operation, diagnosis and maintenance remain reviewable. |
| Auth/RBAC | Enforce roles, permissions and protected areas. | Not every role may view or modify everything. |
| Safety & Governance | Apply risk gates, STOP_ALL, blocked shell execution and approvals. | Automation remains controlled and auditable. |
| Release & Evidence | Document checks, freeze packages, checksums and restore probes. | Changes become measurable, comparable and reversible. |
Grounded Chat
Grounded chat means that an answer should not be free text generated without context. Relevant knowledge and memory chunks are retrieved first. If sufficient context exists, the answer is derived from it. If evidence is missing, cautious refusal is safer than an invented claim.
This approach is especially important for current, technical or security-relevant questions. It does not eliminate all errors, but it provides a better basis for review, diagnosis and trust.
Auth/RBAC and protected actions
Role logic separates reading, reviewing and mutating access. A dashboard may display information without automatically triggering productive actions. Mutating actions require stronger boundaries because they can change system state.
The goal is an assistant that can help without acting uncontrolled. Direct shell execution from model output therefore remains blocked by default.
Next development stage
NQIS as review and improvement layer for Nova agents.
The target picture is that Nova agents, scripts and tools are reviewed by NQIS before productive execution. Safety, quality, compatibility, testability, auditability and governance conformity are evaluated.
Code review
Shell and Python scripts are analyzed before execution. Risky patterns, missing error handling or unclear side effects are marked.
Approval gate
Changes should only be promoted after review, evidence and optional manual approval.
Rollback path
Every change is considered against a baseline. A return path must exist when quality regresses.
Limits
Realistic positioning
Development state: NQIS is a growing local project, not a public cloud service.
Quality: Grounding, tests and evidence improve traceability but do not replace expert review in critical cases.
Autonomy: Self-improvement is understood as a controlled approval-based process, not as unrestricted self-modification.