vaultlayer 0.1.0__tar.gz

vaultlayer-0.1.0/PKG-INFO

@@ -0,0 +1,258 @@
+Metadata-Version: 2.4
+Name: vaultlayer
+Version: 0.1.0
+Summary: AI compute arbitrage CLI — move GPU training jobs between clouds automatically
+Author: VaultLayer
+License: MIT
+Keywords: gpu,cloud,training,arbitrage,mlops,ai
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: System :: Distributed Computing
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: click>=8.1.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: redis>=5.0.0
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: boto3>=1.35.0
+Requires-Dist: anthropic>=0.40.0
+Provides-Extra: server
+Requires-Dist: fastapi>=0.115.0; extra == "server"
+Requires-Dist: uvicorn[standard]>=0.29.0; extra == "server"
+Requires-Dist: supabase>=2.4.0; extra == "server"
+Requires-Dist: resend>=2.0.0; extra == "server"
+Requires-Dist: stripe>=9.0.0; extra == "server"
+Requires-Dist: pydantic[email]>=2.0.0; extra == "server"
+Requires-Dist: python-multipart>=0.0.9; extra == "server"
+
+# VaultLayer
+
+> Run AI training jobs across 11 GPU cloud providers — 60–70% cheaper than AWS on-demand, with 99.9% job completion SLA, using your existing commands unchanged. 93% GPU cloud market coverage (~$39B addressable).
+
+```bash
+pip install vaultlayer
+vaultlayer run python train.py --model llama-3-7b --epochs 10
+```
+
+```
+✓ Job completed in 4h 32m
+✓ 1 interruption recovered automatically (AWS Spot → Lambda H100)
+✓ Saved $142.40 vs AWS On-Demand
+→ View full report: https://vaultlayer.pages.dev/jobs/j-0042
+```
+
+---
+
+## What It Does
+
+VaultLayer sits between your training script and the cloud. It:
+
+- **Checkpoints automatically** — syncs model weights + optimizer state to a zero-egress R2 Vault on every save
+- **Detects interruptions** — intercepts AWS/GCP/Azure termination signals before your job dies
+- **Migrates instantly** — provisions a replacement node on the cheapest available provider and resumes from last checkpoint
+- **Tracks savings** — shows real-time cost vs what you would have paid on AWS On-Demand
+
+No changes to your PyTorch or JAX code. No YAML configs. No PhD-level infra knowledge required.
+
+### Commands
+
+```bash
+# Training
+vaultlayer run python train.py                                         # run with full protection
+vaultlayer run --data s3://bucket/prefix python train.py              # mirror S3→R2 then run
+vaultlayer run --data r2://my-dataset python train.py                 # use dataset already in R2
+vaultlayer run --regions eu-central-1,eu-west-1 python train.py      # GDPR-only regions
+vaultlayer run --excluded-regions cn-north-1 python train.py          # never use China region
+vaultlayer stop <job-id>                                               # graceful stop + checkpoint
+vaultlayer logs <job-id> [--tail N] [--follow]                        # stream logs from R2
+
+# Dataset storage (no S3 required)
+vaultlayer sync ./data --dataset-id my-dataset                        # upload local data → R2
+vaultlayer sync s3://bucket/prefix --dataset-id my-dataset            # mirror S3 → R2 (one-time egress)
+vaultlayer datasets                                                    # list datasets + storage costs
+vaultlayer datasets --delete my-dataset                                # delete + stop billing
+
+# Region discovery
+vaultlayer regions list-all                                            # list all valid regions + compliance notes
+vaultlayer regions current                                             # show current provisioning region
+```
+
+---
+
+## Supported Providers
+
+| Provider | Type | Status |
+|---|---|---|
+| AWS EC2 Spot | Hyperscaler | ✅ Live |
+| Lambda Labs | Neocloud | ✅ Live |
+| CoreWeave | Neocloud | ✅ Live |
+| RunPod | Neocloud | ✅ Live |
+| Vast.ai | Neocloud | ✅ Live |
+| Voltage Park | Neocloud | ✅ Live |
+| Crusoe | Neocloud | ✅ Live |
+| Nebius | Neocloud | ✅ Live |
+| Hyperstack | Neocloud | ✅ Live |
+| GCP | Hyperscaler | ✅ Live |
+| Azure | Hyperscaler | ✅ Live |
+| AWS On-Demand | Hyperscaler | ✅ Last-resort fallback |
+
+11 providers live — 93% GPU cloud market coverage (~$39B addressable, ~$21B migratable training).
+
+---
+
+## Model Size Support
+
+| Model Size | Method | Checkpoint Size | Status |
+|---|---|---|---|
+| 7B | Full fine-tune | ~69 GB | ✅ MVP |
+| 13B | Full fine-tune | ~125 GB | ✅ MVP |
+| 30B | Full fine-tune | ~288 GB | ✅ MVP |
+| 70B | QLoRA (4-bit) | ~46 GB | ✅ MVP |
+| 70B | Full fine-tune | ~782 GB | 🔜 Phase 2 |
+
+---
+
+## Tech Stack
+
+| Layer | Technology | Cost |
+|---|---|---|
+| Code + Docs | GitHub (this repo) | Free |
+| CI/CD | GitHub Actions | Free (2k min/mo) |
+| Vault / Storage | Cloudflare R2 | Free up to 10GB |
+| Agent Runtime | Railway | Free $5/mo credit |
+| Webhooks | Cloudflare Workers | Free 100k req/day |
+| Agent Message Queue | Upstash Redis | Free 10k cmd/day |
+
+---
+
+## Repository Structure
+
+```
+vaultlayer/
+├── README.md
+├── docs/
+│   ├── PRD.md              # Full product requirements
+│   ├── ARCHITECTURE.md     # System design + agent topology
+│   └── AGENTS.md           # Agent specs + build order
+├── dashboard/
+│   └── index.html          # Savings dashboard prototype
+└── src/
+    ├── cli/
+    │   ├── main.py
+    │   ├── run.py
+    │   ├── checkpoint_template.py
+    │   └── init.py
+    ├── vaultlayer/
+    │   └── _resume_hook.py
+    ├── agents/
+    │   ├── orchestration/
+    │   ├── pricing/
+    │   ├── watchdog/
+    │   │   └── signals.py
+    │   ├── vault/
+    │   ├── broker/
+    │   ├── finops/
+    │   └── namespace/
+    └── shared/
+```
+
+---
+
+## SLA
+
+**99.9% job completion rate** — not node uptime. Jobs survive infrastructure failures.
+Recovery SLA: interrupted job resumes within 10 minutes from last checkpoint.
+
+---
+
+## Dataset Storage (No S3 Required)
+
+VaultLayer's Neutral Zone (Cloudflare R2) is a first-class storage provider. Users with no AWS or
+cloud storage account can upload training data directly and train from it on any provider.
+
+```bash
+# Upload from your laptop / on-prem server
+vaultlayer sync ./training-data --dataset-id my-dataset
+
+# Train — data is mounted at /mnt/vaultlayer on every provisioned node
+vaultlayer run --data r2://my-dataset python train.py
+
+# See what you're storing and the monthly cost
+vaultlayer datasets
+```
+
+**Pricing:**
+
+| Action | Cost |
+|--------|------|
+| Upload (local → R2) | Free |
+| Storage | $0.020 / GB / month ($0.0195 — 30% markup over Cloudflare R2 base rate) |
+| Read (R2 → training node) | $0.00 (zero egress within Cloudflare network) |
+| S3 mirror (one-time) | AWS egress charge (~$0.09/GB, first 100 GB/month free) |
+
+**Storage quotas by plan:**
+
+| Plan | Storage limit |
+|------|--------------|
+| Free | 10 GB |
+| Pro | 500 GB |
+| Enterprise | Unlimited |
+
+Datasets are soft-deleted with `vaultlayer datasets --delete <id>` — billing stops immediately,
+R2 objects are purged within 24 hours.
+
+---
+
+## Region Control
+
+VaultLayer can provision nodes in any AWS region that has GPU capacity. By default it uses
+the region from your `vaultlayer init` configuration.
+
+**Restrict to specific regions** (e.g. GDPR compliance — EU data stays in EU):
+```bash
+vaultlayer run --regions eu-central-1,eu-west-1 python train.py
+```
+
+**Exclude regions** (e.g. avoid China, GovCloud, sanctioned territories):
+```bash
+vaultlayer run --excluded-regions cn-north-1,cn-northwest-1 python train.py
+```
+
+If both flags are given, `--excluded-regions` takes priority. If neither is given, any region is allowed.
+
+**Discover regions:**
+```bash
+vaultlayer regions list-all    # all GPU-capable regions with compliance notes
+vaultlayer regions current     # show which region your credentials point to
+```
+
+> **Compliance note:** H100/A100 exports to certain regions (China, Russia, some Middle East countries)
+> may require a US Bureau of Industry and Security (BIS) export license. VaultLayer blocks
+> `cn-north-1`, `cn-northwest-1`, and `ru-central-1` by default via OFAC screening.
+> Use `--regions` to limit jobs to GDPR-compliant EU regions.
+
+---
+
+## Getting Started
+
+```bash
+pip install vaultlayer
+vaultlayer init
+vaultlayer run python train.py
+```
+
+---
+
+## License
+
+Private — © 2026 VaultLayer

vaultlayer-0.1.0/README.md

@@ -0,0 +1,221 @@
+# VaultLayer
+
+> Run AI training jobs across 11 GPU cloud providers — 60–70% cheaper than AWS on-demand, with 99.9% job completion SLA, using your existing commands unchanged. 93% GPU cloud market coverage (~$39B addressable).
+
+```bash
+pip install vaultlayer
+vaultlayer run python train.py --model llama-3-7b --epochs 10
+```
+
+```
+✓ Job completed in 4h 32m
+✓ 1 interruption recovered automatically (AWS Spot → Lambda H100)
+✓ Saved $142.40 vs AWS On-Demand
+→ View full report: https://vaultlayer.pages.dev/jobs/j-0042
+```
+
+---
+
+## What It Does
+
+VaultLayer sits between your training script and the cloud. It:
+
+- **Checkpoints automatically** — syncs model weights + optimizer state to a zero-egress R2 Vault on every save
+- **Detects interruptions** — intercepts AWS/GCP/Azure termination signals before your job dies
+- **Migrates instantly** — provisions a replacement node on the cheapest available provider and resumes from last checkpoint
+- **Tracks savings** — shows real-time cost vs what you would have paid on AWS On-Demand
+
+No changes to your PyTorch or JAX code. No YAML configs. No PhD-level infra knowledge required.
+
+### Commands
+
+```bash
+# Training
+vaultlayer run python train.py                                         # run with full protection
+vaultlayer run --data s3://bucket/prefix python train.py              # mirror S3→R2 then run
+vaultlayer run --data r2://my-dataset python train.py                 # use dataset already in R2
+vaultlayer run --regions eu-central-1,eu-west-1 python train.py      # GDPR-only regions
+vaultlayer run --excluded-regions cn-north-1 python train.py          # never use China region
+vaultlayer stop <job-id>                                               # graceful stop + checkpoint
+vaultlayer logs <job-id> [--tail N] [--follow]                        # stream logs from R2
+
+# Dataset storage (no S3 required)
+vaultlayer sync ./data --dataset-id my-dataset                        # upload local data → R2
+vaultlayer sync s3://bucket/prefix --dataset-id my-dataset            # mirror S3 → R2 (one-time egress)
+vaultlayer datasets                                                    # list datasets + storage costs
+vaultlayer datasets --delete my-dataset                                # delete + stop billing
+
+# Region discovery
+vaultlayer regions list-all                                            # list all valid regions + compliance notes
+vaultlayer regions current                                             # show current provisioning region
+```
+
+---
+
+## Supported Providers
+
+| Provider | Type | Status |
+|---|---|---|
+| AWS EC2 Spot | Hyperscaler | ✅ Live |
+| Lambda Labs | Neocloud | ✅ Live |
+| CoreWeave | Neocloud | ✅ Live |
+| RunPod | Neocloud | ✅ Live |
+| Vast.ai | Neocloud | ✅ Live |
+| Voltage Park | Neocloud | ✅ Live |
+| Crusoe | Neocloud | ✅ Live |
+| Nebius | Neocloud | ✅ Live |
+| Hyperstack | Neocloud | ✅ Live |
+| GCP | Hyperscaler | ✅ Live |
+| Azure | Hyperscaler | ✅ Live |
+| AWS On-Demand | Hyperscaler | ✅ Last-resort fallback |
+
+11 providers live — 93% GPU cloud market coverage (~$39B addressable, ~$21B migratable training).
+
+---
+
+## Model Size Support
+
+| Model Size | Method | Checkpoint Size | Status |
+|---|---|---|---|
+| 7B | Full fine-tune | ~69 GB | ✅ MVP |
+| 13B | Full fine-tune | ~125 GB | ✅ MVP |
+| 30B | Full fine-tune | ~288 GB | ✅ MVP |
+| 70B | QLoRA (4-bit) | ~46 GB | ✅ MVP |
+| 70B | Full fine-tune | ~782 GB | 🔜 Phase 2 |
+
+---
+
+## Tech Stack
+
+| Layer | Technology | Cost |
+|---|---|---|
+| Code + Docs | GitHub (this repo) | Free |
+| CI/CD | GitHub Actions | Free (2k min/mo) |
+| Vault / Storage | Cloudflare R2 | Free up to 10GB |
+| Agent Runtime | Railway | Free $5/mo credit |
+| Webhooks | Cloudflare Workers | Free 100k req/day |
+| Agent Message Queue | Upstash Redis | Free 10k cmd/day |
+
+---
+
+## Repository Structure
+
+```
+vaultlayer/
+├── README.md
+├── docs/
+│   ├── PRD.md              # Full product requirements
+│   ├── ARCHITECTURE.md     # System design + agent topology
+│   └── AGENTS.md           # Agent specs + build order
+├── dashboard/
+│   └── index.html          # Savings dashboard prototype
+└── src/
+    ├── cli/
+    │   ├── main.py
+    │   ├── run.py
+    │   ├── checkpoint_template.py
+    │   └── init.py
+    ├── vaultlayer/
+    │   └── _resume_hook.py
+    ├── agents/
+    │   ├── orchestration/
+    │   ├── pricing/
+    │   ├── watchdog/
+    │   │   └── signals.py
+    │   ├── vault/
+    │   ├── broker/
+    │   ├── finops/
+    │   └── namespace/
+    └── shared/
+```
+
+---
+
+## SLA
+
+**99.9% job completion rate** — not node uptime. Jobs survive infrastructure failures.
+Recovery SLA: interrupted job resumes within 10 minutes from last checkpoint.
+
+---
+
+## Dataset Storage (No S3 Required)
+
+VaultLayer's Neutral Zone (Cloudflare R2) is a first-class storage provider. Users with no AWS or
+cloud storage account can upload training data directly and train from it on any provider.
+
+```bash
+# Upload from your laptop / on-prem server
+vaultlayer sync ./training-data --dataset-id my-dataset
+
+# Train — data is mounted at /mnt/vaultlayer on every provisioned node
+vaultlayer run --data r2://my-dataset python train.py
+
+# See what you're storing and the monthly cost
+vaultlayer datasets
+```
+
+**Pricing:**
+
+| Action | Cost |
+|--------|------|
+| Upload (local → R2) | Free |
+| Storage | $0.020 / GB / month ($0.0195 — 30% markup over Cloudflare R2 base rate) |
+| Read (R2 → training node) | $0.00 (zero egress within Cloudflare network) |
+| S3 mirror (one-time) | AWS egress charge (~$0.09/GB, first 100 GB/month free) |
+
+**Storage quotas by plan:**
+
+| Plan | Storage limit |
+|------|--------------|
+| Free | 10 GB |
+| Pro | 500 GB |
+| Enterprise | Unlimited |
+
+Datasets are soft-deleted with `vaultlayer datasets --delete <id>` — billing stops immediately,
+R2 objects are purged within 24 hours.
+
+---
+
+## Region Control
+
+VaultLayer can provision nodes in any AWS region that has GPU capacity. By default it uses
+the region from your `vaultlayer init` configuration.
+
+**Restrict to specific regions** (e.g. GDPR compliance — EU data stays in EU):
+```bash
+vaultlayer run --regions eu-central-1,eu-west-1 python train.py
+```
+
+**Exclude regions** (e.g. avoid China, GovCloud, sanctioned territories):
+```bash
+vaultlayer run --excluded-regions cn-north-1,cn-northwest-1 python train.py
+```
+
+If both flags are given, `--excluded-regions` takes priority. If neither is given, any region is allowed.
+
+**Discover regions:**
+```bash
+vaultlayer regions list-all    # all GPU-capable regions with compliance notes
+vaultlayer regions current     # show which region your credentials point to
+```
+
+> **Compliance note:** H100/A100 exports to certain regions (China, Russia, some Middle East countries)
+> may require a US Bureau of Industry and Security (BIS) export license. VaultLayer blocks
+> `cn-north-1`, `cn-northwest-1`, and `ru-central-1` by default via OFAC screening.
+> Use `--regions` to limit jobs to GDPR-compliant EU regions.
+
+---
+
+## Getting Started
+
+```bash
+pip install vaultlayer
+vaultlayer init
+vaultlayer run python train.py
+```
+
+---
+
+## License
+
+Private — © 2026 VaultLayer

vaultlayer-0.1.0/pyproject.toml

@@ -0,0 +1,83 @@
+[build-system]
+requires = ["setuptools>=42"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vaultlayer"
+version = "0.1.0"
+description = "AI compute arbitrage CLI — move GPU training jobs between clouds automatically"
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.10"
+authors = [{ name = "VaultLayer" }]
+keywords = ["gpu", "cloud", "training", "arbitrage", "mlops", "ai"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: System :: Distributed Computing",
+]
+
+dependencies = [
+    "click>=8.1.0",
+    "httpx>=0.27.0",
+    "pydantic>=2.0.0",
+    "python-dotenv>=1.0.0",
+    "redis>=5.0.0",
+    "aiohttp>=3.9.0",
+    "boto3>=1.35.0",
+    "anthropic>=0.40.0",
+]
+
+[project.optional-dependencies]
+server = [
+    "fastapi>=0.115.0",
+    "uvicorn[standard]>=0.29.0",
+    "supabase>=2.4.0",
+    "resend>=2.0.0",
+    "stripe>=9.0.0",
+    "pydantic[email]>=2.0.0",
+    "python-multipart>=0.0.9",
+]
+
+[project.scripts]
+vaultlayer = "cli.main:cli"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "strict"
+testpaths = ["tests"]
+filterwarnings = [
+    "ignore::DeprecationWarning:supabase",
+    "ignore::DeprecationWarning:postgrest",
+    "ignore::DeprecationWarning:pyiceberg",
+    "ignore::RuntimeWarning:asyncio",
+]
+
+[tool.ruff]
+line-length = 120
+target-version = "py311"
+
+[tool.ruff.lint]
+ignore = [
+    "E401",
+    "E501",
+    "E402",
+    "E701",
+    "E702",
+    "E741",
+    "F401",
+    "F541",
+    "F811",
+    "F821",
+    "F841",
+]

vaultlayer-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+