Forensic-deepdive vs SlopGuard

Forensic-deepdive and SlopGuard are both coding assistants 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.

Forensic-deepdive

The tool analyzes a codebase across nine languages, builds an embedded graph at `/.deepdive/graph.lbug`, and exposes it over an MCP server so coding agents get structured answers about symbols, imports, call chains, endpoints, and git authorship — not raw file dumps. Five durable Markdown artifacts serve as the human-readable projection of that same graph, so your team gets onboarding docs and mental-model documentation without a separate documentation pass. The graph nodes cover Files, Symbols, Modules, Commits, Authors, Endpoints, and DbTables, which means cross-stack call flow tracing and co-change pattern analysis are first-class queries. The project is Apache-2.0 and self-hosted, with no hosted offering described — your codebase never leaves your infrastructure. The graph must be rebuilt or updated as the codebase changes; the freshness burden falls on the team.

SlopGuard

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.

Attribute	Forensic-deepdive	SlopGuard
Pricing	Free	Paid
Price	—	$19/mo
Free trial	No	No
Open source	Yes	No
Has API	Yes	No
Self-hosted option	Yes	No
Platforms	Python	GitHub
Pros	Persistent embedded graph at `/.deepdive/graph.lbug` stores structural relationships across files, symbols, imports, call chains, and git history, so coding agents query pre-computed architecture instead of reparsing source on every session — which means context windows go to reasoning, not reconstruction. MCP server exposes the graph directly to AI coding agents, so tools like Claude's agent loop can ask structured questions about endpoints, authorship, or call flows and get answers grounded in the actual codebase rather than probabilistic recall. Nine-language polyglot analysis means a single graph covers mixed-stack repositories — teams running Python services alongside TypeScript frontends and Go infrastructure get cross-language call tracing without splitting the analysis. Five auto-generated Markdown artifacts produce human-readable documentation as a by-product of graph construction, so onboarding docs and architectural mental models stay in sync with the codebase without a separate writing pass. Apache-2.0 license and self-hosted-only design mean the graph — and every piece of codebase structure it encodes — stays on your infrastructure, which matters for teams whose source cannot leave a private environment.	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	The graph captures codebase state at analysis time and does not update itself; on a codebase with frequent commits, agents query stale structural data between runs — teams that need accurate context on active branches wire a graph-rebuild step into CI, which adds pipeline complexity and rebuild time proportional to repo size. Zero community forks and zero stars at the time of scraping means bug reports, edge-case language support, and parser correctness issues have no community surface — teams that hit a parsing failure in their stack have no forum thread to find and must open an issue against a single-maintainer repo, with no documented SLA. Teams that need agents to not just query structure but act on it — planning refactors, executing multi-file edits, managing PRs autonomously — will find forensic-deepdive provides context supply only; the execution layer is absent by design, and those teams reach for a full agent platform (Devin, SWE-agent, or similar) where the context graph is one component inside a broader task loop.	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.

Bottom line

Forensic-deepdive is free while SlopGuard is paid; Forensic-deepdive is open source; only Forensic-deepdive exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Forensic-deepdive and SlopGuard?

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

Is Forensic-deepdive better than SlopGuard?

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.