Airuncode
Freemium
Developers preferring fully local agent execution
SlopGuard
Freemium
Every week you spend thirty seconds on a PR that turns out to be pure LLM output — polished title, confident summary, zero grasp of your codebase — and you cannot just close it on suspicion without burning the one real first-timer in the batch. SlopGuard scores every incoming PR and issue against heuristics, labels the likely machine-made ones with the specific reasons, and leaves the close button entirely in your hands.
Similar tools
ClixadFreemiumClixad is a terminal coding agent with free daily usage, configurable approval modes and…
ManifestGoFreemiumThe core workflow is a one-prompt generation: describe what you want, and ManifestGo produces…
AiruncodeFreemiumAiruncode runs agents locally, lets you plug in your own provider keys or on-device models…
AtlarixFreemiumAtlarix is a desktop AI workstation where agents plan, write, test, and debug inside workspaces…
Screenshots 1
Summary
The tool installs as a GitHub App with no Action YAML, no CI config, and no secrets to wire. Each contribution gets a 0–100 slop score derived from heuristics only — no LLM API calls — and at or above your configured threshold it adds a quarantine label plus a review comment listing the exact signals, such as leaked chat-assistant phrases or prompt fingerprints. Below the threshold it stays silent. You reply with slash commands to approve, reject, or flag a false positive. The vendor states the golden-set benchmark sits at 100% precision and 92% recall — every flagged item was real slop, and the single miss was slop that slipped through, not a genuine contributor wrongly quarantined.
Bottom line: Pick this if you are an open-source maintainer drowning in AI-generated PRs and need triage help that will never auto-close a real contributor; skip it if your team needs programmatic API access, self-hosted deployment outside the Commons Clause terms, or detection that adapts beyond static heuristics as generation patterns shift.
Pricing Plans
SubscriptionLast verified 4 months ago- Price
- $19/mo
- Free Tier
- For individuals and public repos. Forever free. Fast heuristic detection (100% precision on our eval set), Provenance tagging + quarantine label, Human-in-the-loop /slop commands, .github/SLOP_POLICY.yml policy-as-code, Public repositories, Self-host the whole thing for your own use (source-available)
Free
Free
For individuals and public repos. Forever free.
- Fast heuristic detection (100% precision on our eval set)
- Provenance tagging + quarantine label
- Human-in-the-loop /slop commands
- .github/SLOP_POLICY.yml policy-as-code
- Public repositories
- Self-host the whole thing for your own use (source-available)
Pro
$19per month
For maintainers with private repos and higher limits.
- Everything in Free
- Private repositories
- AI judge: LLM-deepened detection we pay for
- Cross-repo bot-pattern detection
- Network slop intelligence (cross-customer, hosted-only)
- Higher rate limits
Team
$99per month
For orgs that need visibility, alerting, and controls.
- Everything in Pro
- Org-wide dashboard across all repos
- Activity / audit log (who cleared what, when)
- Slack / Discord / webhook alerts on quarantine
- Higher rate limits
- Priority support
Enterprise
$299per month
For companies that need SSO, audit export, and priority support.
- Everything in Team
- SAML / SSO sign-in
- Audit log export + retention
- Priority support & onboarding
- Custom integrations on request
View full pricing on github.com →
Pricing may have changed since last verified. Check the official site for current plans.
Find your fit
Before you choose SlopGuard
More options in Coding Assistants. Compare pricing, platforms, and features side by side.
Atlarix
Freemium
Engineering teams needing private/local AI coding assistance
Pros
- Heuristics-only scoring with no external LLM calls, so detection runs without API keys, per-call costs, or a third-party model availability dependency — the queue keeps moving even when OpenAI is down.
- 100% precision on the vendor's labelled golden set, meaning every contribution it flags is real slop and no genuine first-time contributor gets a quarantine label by mistake — the risk you take by not using it is missed slop, not burned contributors.
- Per-repository threshold configuration via a slider, so a high-traffic org repo and a small side project can run at different sensitivity levels without separate installs or config files.
- Provenance trail attached to each flagged item — leaked phrases, prompt fingerprints, and the specific signals — so when you review a quarantined PR you are not just seeing a score, you are seeing exactly why it was flagged.
- One-click GitHub App install with no Action YAML or secrets to wire, so a maintainer can have it running on a new repo in under a minute without touching CI configuration.
Cons
- Detection is bounded by a static heuristic ruleset, so when LLM output patterns shift — shorter prompts, less boilerplate, better title generation — recall degrades silently until someone updates the rules manually. Teams processing high volumes of slop that evades the current heuristics have no model-retraining path and no feedback loop beyond the slash commands; at that point they evaluate classifier-backed alternatives.
- There is no API, which means a team that wants to pull slop scores into a separate dashboard, feed them into a Slack alert, or trigger any downstream automation has no supported integration path. The label-and-comment output is the only interface. Teams that need scores as data rather than GitHub UI annotations will be screen-scraping labels or abandoning the tool for a solution with a query endpoint.
- Self-hosting is gated behind Commons Clause terms, which permits personal use but blocks commercial redistribution. An organization that wants to run SlopGuard on internal infrastructure for a commercial product and control the full deployment will hit a licensing wall and need either a separate commercial agreement with the vendor or a different tool.
About
- Platforms
- GitHub
- API Available
- No
- Self-Hosted
- No
- Last Updated
- June 11, 2026
Best For
Who it's for
- Open-source maintainers receiving high volumes of AI PRs
- Teams wanting provenance tracking without auto-closing
- Repositories that prefer heuristics over LLM calls
What it does well
- Triage incoming PRs and issues for AI-generated content
- Quarantine suspected slop while preserving human review
- Tag provenance and leaked phrases on machine-generated contributions
- Configure thresholds and policies per repository
Integrations
Frequently Asked Questions
- Is SlopGuard free?
- SlopGuard offers a free option alongside paid upgrades. Pricing: $19/mo. Check the current allowances and terms before choosing a plan.
- What platforms does SlopGuard support?
- SlopGuard is available on: GitHub.
SlopGuard sits between your GitHub inbox and your review queue. When a PR or issue arrives, the app scores it against a heuristic ruleset — looking for leaked chat-assistant boilerplate, prompt fingerprints, generic auto-generated titles, and empty descriptions — and returns a 0–100 slop score with the specific signals attached. At or above the threshold you configure, it labels the contribution and leaves a review comment. Below it, nothing happens. You respond via slash commands: `/slop approve`, `/slop reject`, or `/slop false-positive`. Nothing is ever auto-closed.
The defining design decision is that it runs entirely on heuristics, with no LLM key required. That removes per-call API costs and avoids the latency and availability risk of routing every PR through an external model. The tradeoff is that the detection ceiling is fixed to the heuristic set — the system does not learn from your corrections in the way a model-backed classifier would, and as generation patterns evolve the recall figure the vendor reports against its 25-case golden set will need manual ruleset updates to hold.
Public repositories get the GitHub App install at no cost, according to the vendor’s site. Self-hosting is source-available under Commons Clause, which permits personal use but restricts commercial redistribution. There is no API, so any workflow that requires reading SlopGuard’s scores programmatically — to feed a dashboard, trigger a downstream automation, or integrate with a separate triage system — has no supported path. Teams that outgrow label-and-comment-only output and want to route flagged PRs into a wider workflow will be building around the tool, not with it.
Installation is one click from the GitHub App directory with no secrets, no Action YAML, and no CI configuration needed. The threshold slider is adjustable per repository, and the vendor’s live demo shows PRs reclassifying between quarantined and passed in real time as the line moves — which means you can tune aggressiveness per project without touching config files.
Contribute
- Work on SlopGuard? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.