Pricing
Enterprise-grade code intelligence. Simple pricing.
Ganvil coordinates and indexes your codebase entirely in the cloud or securely syncs down to your local infrastructure. All plans include a 14-Day Card-Upfront Free Trial ($0.00 today).
LAUNCH20 for 20% off).Ganvil hosts the Hammer and the index in the cloud: compute embeddings once, coordinate collaborative editing via CRDT, and synchronize workspaces remotely.
- ▸Hosted index: embeddings built once, shared across the org
- ▸Cloud-Hosted Hammer: zero local CPU/RAM pressure for indexing
- ▸Remote MCP gateway with tenant scoping and rate limits
- ▸Real-time CRDT relay for concurrent, conflict-free edits
- ▸Silent degradation: falls back to local execution if offline
- ▸Wallet with $10/mo in credits for Hammer & Anvil compute
- ▸Wallet recharge rate of $0.02 / minute for active VM compute
Audit every byte agents write. Built for teams whose security reviews require cryptographic proof of origin, tamper-proof logs, and approval workflows. Includes SOC 2 and others.
- ▸Includes all Hammer & Burst READ capabilities
- ▸Symbol-level provenance viewer: see who changed what and why
- ▸Signature-required proposals: agent writes demand an Ed25519 key
- ▸Append-only, hash-chained audit trail of agent activity
- ▸Wallet with $25/mo in credits for Hammer & Anvil compute
- ▸Active workspace and deployment lifecycle event telemetry
- ▸Dedicated integration and setup support
Confine agent execution to absolute boundaries. Grasp complete control over what models can read, write, or access with zero-trust posture enforcement. Contact us for custom on-premise or private cloud deployments.
- ▸Includes all Compliance & Governance READ capabilities
- ▸Role-based access control (RBAC) scoped to token claims
- ▸Includes all Compliance & Governance WRITE capabilities
- ▸mTLS CA + cert issuance + CRL + OCSP validation responder
- ▸Wallet with $50/mo in credits for Hammer & Anvil compute
- ▸As-needed, time-bound feature grants for AI agents
- ▸Path-cone confinement sandboxing for agent execution
- ▸Fail-closed security posture for all remote tool access
None of ours. All of yours — and the product's job is making "yours" small. The data layer spends zero LLM tokens: outlines, callers, impact, symbol diffs are computed from parsing and graph analysis, not from a model. Whatever reasoning happens runs in your model, on your bill, and every table on the benchmarks page is about shrinking that bill.
We never hold LLM keys and we never mark up tokens. There is no margin hiding in your usage, on any tier.