Skip to main content
AIDiveForge AIDiveForge

Aegitox vs Selvedge

Aegitox 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.

Aegitox

Aegitox

Aegitox intercepts Discord messages before they are read, runs them through a dual MiniLM-L6-v2 semantic pipeline locally, and replaces hostile content with target-aware de-escalation placeholders in 2–12ms — bypassing cloud API round-trips entirely. The free tier covers real-time toxicity interception and raid defense. Automated karma-based penalties, incident reports, and the one-click DM appeal system that routes staff review are paid-only features. The appeal system is the architectural detail that matters most for enterprise use: the bot acts autonomously, but a human signs off on the final penalty — so you are not handing discipline entirely to a model. The system has no API and no self-hosted option, so teams that need on-premise deployment or want to pipe moderation signals into their own data stack will hit a hard wall.

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.

AttributeAegitoxSelvedge
PricingPaidFree
Price$0 forever; $14.99/mo Professional
Free trialNoNo
Open sourceNoYes
Has APINoNo
Self-hosted optionNoYes
PlatformsDiscordLinux, macOS, Windows (via Python)
Released2026-05
Pros
  • Dual MiniLM-L6-v2 semantic pipeline runs locally with no cloud API call during inference, so moderation decisions are not blocked by external API latency or outages.
  • Unicode and markdown evasion detection via mathematical intent mapping rather than character matching, which means the filter catches obfuscated content that bypasses every regex-based AutoMod configuration.
  • Target-aware placeholder replacement (40 stubs per threat category, 120 total) substitutes hostile content with de-escalation text matched to the specific threat vector — so the message thread continues without a visible gap or a bot warning banner.
  • Karma-based automated penalty engine with a built-in DM appeal system that routes to staff for final review, which means admins get autonomous enforcement without fully removing human judgment from the discipline loop.
  • Free tier includes the core AI interceptor and raid defense with no keyword list to maintain, so a guild can move from manual moderation to AI interception without any ongoing filter upkeep.
  • 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 API is exposed, so teams that want to pipe moderation events, karma scores, or incident data into an external dashboard, SIEM, or data warehouse cannot — the data stays inside the Aegitox system and there is no documented export path.
  • Self-hosted deployment is not available, which means any organization with a compliance requirement to keep message content on-premise — legal, healthcare, or enterprise security teams — cannot use this tool and will need to evaluate self-hostable alternatives instead.
  • The automated penalty engine and appeal workflow are paid-only features, so guilds that deploy the free tier and hit a raiding event get interception but no automated disciplinary escalation — moderators must handle timeouts and bans manually until they upgrade.
  • System prompt customization for the replacement text layer is a paid-only feature, so free-tier communities get the default placeholder pool regardless of tone or community norms — a formal professional server and a casual gaming server get the same de-escalation language.
  • 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

Aegitox is paid while Selvedge is free; Selvedge is open source. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Aegitox and Selvedge?

Aegitox 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 Aegitox 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.

Aegitox vs Selvedge: which should I pick?

Pick Aegitox 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.