Skip to main content
AIDiveForge AIDiveForge

Northbeams vs Selvedge

Northbeams 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.

Northbeams

Northbeams

Northbeams sits between your workforce and their AI tools, classifying what's running, blocking what shouldn't be, and generating the evidence chain your SOC 2 or HIPAA auditor will ask for. The browser-based agent installs without network changes, so IT doesn't need a procurement cycle to get visibility. Discovery is ungated, which means you can map your shadow AI footprint before committing to enforcement. The ceiling appears when your environment scales past a single site or when you need MCP agent governance — those capabilities are paid-only features. Teams running large multi-site deployments report that per-seat policy management becomes the operational bottleneck.

Selvedge

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.

AttributeNorthbeamsSelvedge
PricingPaidFree
Price$9,600/yr
Free trial14 daysNo
Open sourceNoYes
Has APIYesNo
Self-hosted optionNoYes
PlatformsBrowser (Chrome, Edge, Brave, Arc), Mac, Windows, CLILinux, macOS, Windows (via Python)
Released2026-05
Pros
  • Agent deploys without network changes or procurement approval, so a security team can have full shadow AI inventory running in hours rather than after a six-week firewall project.
  • Real-time PII, credential, and source-code interception fires before data leaves the browser, which means you catch the leak before it becomes a breach notification obligation.
  • Automated generation of SOC 2, HIPAA, and EU AI Act audit evidence means compliance reviews don't require a two-week manual log reconstruction before every auditor call.
  • Per-tool allow/block/sandbox policies for MCP agent access, so engineering teams using Cursor or Claude Desktop don't operate in a governance blind spot while the rest of the org is covered.
  • Discovery tier is ungated, which means you can produce a complete AI tool inventory and make the business case for enforcement before spending a dollar — removing the 'prove it first' blocker most security budgets impose.
  • 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
  • Browser-agent coverage means any AI workload running outside the browser — CLI tools, server-side agents, API integrations — is invisible to Northbeams; teams with significant non-browser AI usage will maintain a separate inventory for those surfaces and live with two parallel governance systems.
  • MCP agent governance and Fleet (multi-site policy management) are paid-only features, so organizations that deploy on the free tier and then discover their primary risk is in coding agents or distributed sites face a forced upgrade decision mid-rollout rather than before it.
  • Teams that outgrow per-tool policy management at scale — typically when seat counts push into the hundreds across multiple locations — report that policy administration becomes a recurring manual burden; at that inflection point, organizations with dedicated security engineering staff typically migrate to a network-layer DLP or CASB that handles enforcement at the infrastructure level rather than the browser.
  • 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

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

Frequently asked questions

What is the difference between Northbeams and Selvedge?

Northbeams 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 Northbeams 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.

Northbeams vs Selvedge: which should I pick?

Pick Northbeams if its pricing model, openness, or platform fit matches your constraints; pick Selvedge otherwise. Check free-trial availability on each listing if you want to test before committing.

Comparison data is sourced and verified by the AIDiveForge data pipeline. AIDiveForge is editorially independent.