Trial/license funnel, private inference, governed RAG, admin, install control, audit foundations, license ops, catalog studio, and security review packet.
BuiltPublic roadmap
Execution roadmap.
Built today, validating now, and planned next. Srasta separates current capability from committed build direction, and every public claim is tied to a deployment/runtime profile we can actually prove.
Roadmap discipline
We do not pitch roadmap items as shipped capability.
The website and pitch deck align on the same backbone: private inference, agent-registered install, admin operations, governance evidence, and catalog-certified deployment profiles. Public status follows the catalog/support matrix: Apple Silicon MLX is Built, NVIDIA Blackwell vLLM single-node is Validating, and broader enterprise profiles stay behind their own proof gates.
Milestones
Where the platform evolves.
The public roadmap mirrors what we can prove: GTM baseline and Apple Silicon MLX are Built; NVIDIA Blackwell vLLM, Catalog Studio, repeatability, multi-host, Kubernetes, HA, and cloud-provider profiles move only when validation evidence exists.
Apple Silicon / MLX single node, NVIDIA Blackwell / vLLM single node passed the clean install, activation, runtime binding, model access, RAG, and audit proof path.
Builtprofiles currently under validation is the next supported hardware path. It runs on real infrastructure, but remains Validating until clean proof is repeatable.
ValidatingHugging Face and Unsloth source intake, reviewed candidates, runtime profiles, evidence capture, and publish workflow are being hardened for operator use.
ValidatingTighten clean-room reset, provenance, service discovery, audit delivery, user onboarding, and proof receipts so validation is repeatable without stale local state.
NextNVIDIA multi-host, production operations, backup/restore, rollback, support bundles, and private registry posture.
NextKubernetes, HA, AWS, Azure, GCP, Vast, and other runtime adapters become supported only after their own certification evidence exists.
LaterBeyond the governed knowledge base: capture what works and promote validated intelligence across the org (individual → team → firm) under review and audit — the membrane runtime, built incrementally from customer revenue.
LaterBuild detail
What each phase includes.
Private AI foundation
The GTM baseline is built: private inference, governed RAG, admin operations, license lifecycle, role-aware model access, audit foundations, and customer-controlled deployment profiles.
- Private inference path for open-weight models on customer-controlled hardware
- Gateway foundations for role-aware model access and auditable AI requests
- Admin foundations for users, roles, licenses, model access, and runtime visibility
- Governance foundations for prompt, model, memory, tool, policy, and admin events
- Catalog authority for which hardware, runtime adapters, inference engines, and model bindings are installable
- Srasta-Agent heartbeat, runtime health, controlled actions, and proof receipts
Apple Silicon MLX trial/community path
Apple Silicon / MLX single node, NVIDIA Blackwell / vLLM single node is the first certified deployment profile: install, run, test, and inspect Srasta locally without manual serving — proof-gated and handed over.
- Apple Silicon local profile using host-native model runtime where practical
- Local install plane with agent registration, prechecks, verify, reset, and logs
- Developer proof gate: prompt enters Srasta and produces audit-visible evidence
- Clear limits on what is local-only versus enterprise-ready
- No SSH/SCP operating model after local agent registration
NVIDIA Blackwell vLLM pilot path
profiles currently under validation is the next pilot deployment profile. It has real infrastructure behind it, but it remains Validating until the same clean proof standard is repeatable.
- NVIDIA Linux single-node profile with vLLM-backed private inference
- Agent registration as the primary install backbone after bootstrap
- Hard gates for prompt-to-audit workflow proof before handover
- Operator-visible evidence for runtime health, gateway routing, role checks, and audit events
- Deployment Charter and Pilot Charter for design partners
- Sanitized support package flow for debugging without exposing customer data or PII
Catalog certification factory
Catalog Studio is becoming the operator workflow for adding and certifying more hardware, inference engines, embedding models, runtime profiles, and LLM models without changing customer-side code.
- Hugging Face and Unsloth source intake for model candidate discovery
- Operator review screens for model metadata, runtime fit, quantization, parser support, and evidence
- Certification targets for Apple MLX and NVIDIA vLLM profiles
- Publish workflow that updates the catalog authority consumed by license and installer flows
- Public supported-deployment matrix sourced from the same catalog data
Repeatability and day-2 hardening
The next hardening gate is repeatable proof from clean state: no stale local data, no hidden fallbacks, no duplicate proof paths, and no unsupported service discovery assumptions.
- Clean-room install reset and provenance checks
- Service discovery as the only installed-platform service authority
- Audit authority delivery and replay hardening
- User onboarding, activation, invite, and recovery regression coverage
- Support bundles and operator-visible proof receipts
Multi-host, Kubernetes, and HA operations
Multi-host GPU, Kubernetes, HA, cloud-provider adapters, backup/restore, rolling upgrade, registry trust, support collection, and SLA posture require their own validation evidence before becoming supported profiles.
- NVIDIA multi-host deployment profile
- Kubernetes operator and upgrade posture for enterprise deployment profiles
- HA-oriented topology guidance for gateway, inference, admin, governance, memory, and audit layers
- No-planned-downtime upgrade patterns where architecture and customer infrastructure allow it
- Disaster recovery, restore drills, rollback drills, and proof artifacts
- Formal SLA commitments only after measured validation with paying customers
Governed integrations, Membrane, and specialized enterprise requirements
These are not day-one promises. We will scope and price them when a paying customer has the requirement and the environment to validate it.
- Governed Tool Pack registry and approval lifecycle
- Agentic harness support for customer workflows that need planning, tool use, and operator guardrails
- Membrane runtime for governed memory and reusable organizational intelligence
- Customer-specific certified images and private registry
- Windows node support
- Vast.ai or similar GPU-marketplace customer installs
- Formal five-nines SLA backed by measured production evidence
- Advanced workspace, role, and sector-specific compliance automation
- AMD, Intel, and specialized edge AI machines after demand and validation
Design partner fit
Have a workflow that should shape the roadmap?
The best roadmap input is a real environment, a real governance boundary, and a measurable workflow. We capture requests in the same CRM-backed funnel as pilot and product-update interest.