Apertis vs Selvedge

Apertis and Selvedge are both inference engines & infra tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Apertis

Apertis functions as an API gateway layer that sits between your coding agents — Cursor, Cline, Claude Code and the like — and the underlying model providers. You point your agent at one endpoint, authenticate once, and the platform handles provider routing, failover, and cost tracking behind it. The vendor states that automatic failover keeps production agents running when a provider has an outage, which removes a class of silent failures teams usually discover too late. The free tier covers basic models with no payment required; premium models and higher quotas are paid-only features. The platform is cloud-only — no self-hosted option — so your API traffic routes through Apertis infrastructure, and teams with data-residency requirements hit that wall immediately.

Selvedge

Selvedge is a local MCP server that AI coding agents (Claude Code, Cursor, Copilot) call as they work, logging the reasoning behind every change into a SQLite file that lives next to your code under .selvedge/. Queries are entity-scoped — you ask about users.email or deps/stripe, not line numbers — so the answer surfaces in the same terms you search in. The vendor describes zero telemetry, no accounts, and no external servers; everything stays on disk. The wall appears when your team needs cross-repo provenance or wants to pipe this data into an existing observability stack — Selvedge emits records but does not integrate with those systems out of the box.

Attribute	Apertis	Selvedge
Pricing	Paid	Free
Price	$33/quarter	—
Free trial	No	No
Open source	No	Yes
Has API	Yes	No
Self-hosted option	No	Yes
Platforms	Web-based API; CLI/TUI agents via supported integrations	Linux, macOS, Windows (via Python)
Released	—	2026-05
Pros	Single API endpoint for multiple model providers, so rotating a compromised key or switching a model mid-project touches one config entry instead of one per agent per provider. Automatic provider failover is built into the routing layer, which means a production coding agent keeps running through an upstream outage instead of throwing an unhandled exception at the worst possible time. Unified billing across providers, so monthly AI infrastructure cost is one line item rather than a reconciliation exercise across five separate vendor invoices. New model versions are added to the platform automatically per vendor documentation, so your agent gains access without a credentials update or a config change on your end. Free tier covers basic models with no payment required, which means a team can validate the integration and routing behavior before committing budget to premium model access.	Reasoning is captured in the same context window that produced the change — not reconstructed from the diff afterward — which means the intent survives even when the original prompt, the developer who wrote it, and the model version are all gone. Entity-scoped queries (selvedge blame payments.amount, selvedge diff users --since 30d) let you ask about the things you actually search for rather than hunting through line-level history, so a schema audit that would take an afternoon takes a single command. Fully local storage in a SQLite file with no accounts, no telemetry, and no external servers, which means sensitive schema and API change history never leaves the machine — a hard requirement in compliance-heavy environments. Provider-agnostic MCP integration wires into Claude Code, Cursor, and Copilot through a single setup command, so teams already using any of those agents get provenance logging without changing their workflow. Full-text search across all logged events (selvedge search "stripe") and changeset grouping (selvedge changeset add-stripe-billing) mean you can reconstruct the full scope of a feature build after the fact, which is the audit trail that git log alone cannot provide.
Cons	No self-hosted deployment option exists — all API traffic routes through Apertis cloud infrastructure. Teams with data-residency requirements, HIPAA obligations, or any compliance posture that restricts where model prompts travel cannot use this platform and will move to a self-hostable gateway like LiteLLM or a direct provider integration instead. The value proposition depends entirely on the providers Apertis has contracted with at any given moment. If your agent's critical model — a specific Anthropic version, a fine-tuned endpoint — is not available through the platform, you are back to maintaining a direct integration alongside the gateway, which recreates the fragmentation problem you were solving. Cost predictability, which the platform positions as a core benefit, breaks down if your agent usage is highly variable and you are comparing against a pay-per-token direct model. Flat subscription pricing on a low-usage month means you overpay relative to direct API access — teams that run bursty, project-gated workloads rather than continuous agent pipelines see worse economics here.	Selvedge has no API and no export integration — teams that need to push reasoning records into an existing compliance platform, a data warehouse, or a centralized observability system must write their own pipeline against the SQLite file, adding a maintenance surface that grows with audit requirements. The store is scoped to a single local project directory; teams running multi-repo codebases where an agent change in one repo depends on a change in another get no cross-repo provenance, and at that point teams managing compliance across repositories will move to a dedicated audit-log solution that operates at the organization level. Selvedge only captures what the agent explicitly logs through the MCP tool call — if an agent skips the log_change call, makes changes outside a supported tool, or the MCP connection drops mid-session, that change has no recorded reasoning and the gap is invisible in the history.

Bottom line

Apertis is paid while Selvedge is free; Selvedge is open source; only Apertis exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Apertis and Selvedge?

Apertis is Paid, while Selvedge is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Apertis better than Selvedge?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.