From intent to cluster
State your team size, budget, and workload type in plain language — Tashkil translates that intent into a fully provisioned, optimized cluster in minutes.
Compose HPC & AI Clusters in Minutes
Tashkil turns plain-language workload needs into fully provisioned, optimized clusters — across bare metal, cloud, and neoclouds — no dedicated DevOps team required.
Tashkil
Cluster Composer
Agent session · From intent to running cluster
AR
Drain node-04 for maintenance and requeue its jobs.
Thought for 3s · 2 tool calls
Drained node-04 and requeued its jobs onto spare capacity — no preemptions.
Cordon node-04done
Migrate 12 jobsdone
Health test gpu-3queued
How's spot pricing on H100s this week?
Thought for 4s
Down 8% week-over-week. us-east-2 has the deepest pool if you need sustained capacity.
Describe the cluster you need…
13b-train
Without Tashkil
With TashkilTotal flexibility across bare metal, cloud, and neoclouds
One platform that composes, optimizes, and heals every cluster
Tashkil collapses your entire infrastructure stack into a single conversational interface — built to provision, optimize, and self-heal without the orchestration tax.
Benchmark-driven hardware
Tashkil selects the most cost-effective hardware for each job from real-world performance benchmarks, not instance labels — so budgets go further.
The challenge
A dedicated cluster gives your team an edge, but standing one up yourself comes with tradeoffs
- The DevOps Bottleneck
- Weeks disappear into Kubernetes, SLURM, and cloud networking before a single job ever runs.
- Mispriced Compute
- Instance labels hide real performance, so teams overpay for hardware that doesn't match their workload.
Run anywhere
One control plane across bare metal, cloud, and neoclouds
- No lock-in
- Move between providers without changing your workflow.
- Benchmarks, not labels
- Hardware is picked by measured throughput, not by what an instance is called.
Built for research teams
Multi-tenant from day one, no infra staff required
- Quotas & isolation
- Set quotas and isolated environments per team.
- Access control
- Manage users and SSO without a platform team.
Sovereign by design
Keep full ownership of your compute plane
- Self-hosted
- Run Tashkil entirely inside your environment.
- Managed updates
- The orchestration engine keeps improving without the upkeep.
Frequently asked questions
Everything you need to know about deploying Tashkil. Can't find an answer? Our infrastructure team is one message away.
Tashkil is an agentic infrastructure platform that composes production-ready HPC and AI clusters in minutes. Describe your workload in plain language — team size, compute budget, workload type — and Tashkil translates that intent into a fully provisioned, optimized cluster, no Kubernetes or SLURM wrestling required.
Compose your next cluster in minutes, not weeks
Unify provisioning, scheduling, and governance on one platform — and let your team focus on research while Tashkil handles the orchestration.