Rampart vs SigmaShake

Rampart and SigmaShake are both guardrails & safety 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.

Rampart

Rampart runs a two-layer pipeline entirely in the browser: a 14.7 MB ONNX token-classification model from Hugging Face combined with a deterministic recognizer layer that catches what the model misses. Nothing leaves the client unredacted — the architecture makes server-side PII exposure structurally impossible, not just policy-dependent. The npm package ships as a complete, reproducible artifact, so your redaction behavior is auditable and consistent across builds. The ceiling arrives when your entity types fall outside what the bundled model was trained to recognize — at that point you are retraining or replacing the model, not tweaking a config. Teams needing real-time redaction across high-volume server-side pipelines will hit the browser-only constraint immediately.

SigmaShake

SigmaShake intercepts tool calls from agents running in Claude Code, Cursor, VS Code Copilot, and Gemini CLI, evaluating each action against a rule set before it executes. The vendor states decisions resolve in roughly 85 ms using deterministic native evaluation — no model inference, no GPU, no token spend. Rules follow an Allow/Ask/Deny pattern, where Ask routes the action to a human approval queue rather than blunting everything with a hard block. The desktop app installs in about 30 seconds with no admin rights; the CLI drops into any shell or CI hook chain. Self-hosting is supported, which means the guardrail layer stays offline and never sends your code or commands to a third-party model.

Attribute	Rampart	SigmaShake
Pricing	Free	Paid
Price	—	$5/mo
Free trial	No	No
Open source	Yes	No
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	Browser, Node.js	Windows 10+, macOS 14+, Linux (Ubuntu 22.04+ / Fedora 38+ / Pop!_OS)
Pros	Client-side ONNX inference means PII never leaves the browser unredacted, so a misconfigured server filter or a mid-request failure cannot expose raw user text to your LLM provider. Defense-in-depth pipeline — model layer plus deterministic recognizer — so structured entities like emails and phone numbers are caught even when the token classifier is uncertain, reducing the false-negative surface area compared to single-pass approaches. Ships as a versioned npm package with an eval suite and bundled model weights, so redaction behavior is reproducible across builds and auditable by commit — which matters when a compliance reviewer asks what changed between releases. Open-source with MIT or equivalent license (per the repository), so your legal team can read the full implementation rather than trusting a vendor's privacy attestation on a black-box API. Hugging Face model loading with an in-repository fallback, so air-gapped or reproducibility-sensitive deployments do not depend on an external CDN staying up.	Deterministic local evaluation at roughly 85 ms per check, so you avoid the latency and per-token cost of routing every agent action through a model-based policy guard. Ask mode holds a risky action in a human approval queue rather than blocking it outright, which means your agent keeps moving on safe tasks while you review the one call that needs a second look. PreToolUse hook integration for Claude Code and MCP server integration for Cursor, Codex, and VS Code Copilot, so the guardrail wires into agents your team is already running without a custom shim. Self-hosted deployment with no model inference, so your code, file paths, and shell commands never leave the machine — critical for teams with data-handling obligations. Per-user install with no admin or UAC rights required, which means individual developers can adopt it without waiting for IT to sign off on an organization-wide rollout.
Cons	The pipeline is architected for browser execution — teams running redaction server-side in Node.js, Python, or a backend compliance layer have no supported path and need a different tool entirely. The bundled model covers the entity types it was trained on; when your domain introduces entity patterns outside that distribution — internal employee IDs, proprietary product codes, jurisdiction-specific ID formats — the model does not adapt without retraining, and the deterministic layer only catches patterns explicitly coded into it. At 14.7 MB, the ONNX model adds a non-trivial initial load cost in browser contexts; applications targeting low-bandwidth users or requiring sub-second first-interaction readiness need to measure this against their performance budget before committing. No API, no hosted option, and no server-side SDK means teams that want managed PII redaction with SLA guarantees or audit logging infrastructure will switch to a commercial data-loss-prevention service — Rampart's local-first design is exactly what those teams cannot use.	No API is exposed, so teams building custom agent runtimes or embedding safety checks inside their own orchestration code cannot call SigmaShake programmatically — they wrap the CLI binary, which introduces a process boundary and complicates error handling at scale. The SHAKEDOWN benchmark that positions SigmaShake as the top-ranked guardrail was authored by SigmaShake, and competitor scores were modeled from public docs rather than measured runs; teams doing their own evaluation should run independent tests before treating the benchmark as a neutral comparison. Fleet management and team-level policy enforcement are paid-only features, which means a free-tier team cannot centrally audit what rules individual developers are running — a gap that matters the moment more than one engineer is using an AI coding agent on shared infrastructure. Windows support is the primary release target based on page emphasis and download prominence; macOS and Linux builds are listed but community reports on edge cases outside Windows are sparse, so teams running heterogeneous developer environments should validate on non-Windows machines before committing.

Bottom line

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

Frequently asked questions

What is the difference between Rampart and SigmaShake?

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

Is Rampart better than SigmaShake?

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.