Agent-QA vs Forensic-deepdive

Agent-QA and Forensic-deepdive 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.

Agent-QA

The tool lets you write test steps in plain language — 'Click on the Create issue icon', 'Verify that the created issue is shown' — and an agent translates those into browser actions at runtime, reading visible labels and screen state instead of fragile CSS selectors. After each run, it builds execution memory: observations about navigation contracts, UI quirks, and previously healed steps, which get injected into future runs so the agent stops rediscovering the same UI patterns. Self-healing means that when a component shifts, the agent iterates through recovery attempts rather than failing immediately. The ceiling appears when test logic branches on conditional application state — the YAML authoring model is built for linear flows, and complex branching sends teams back to scripting.

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.

Attribute	Agent-QA	Forensic-deepdive
Pricing	Paid	Free
Free trial	No	No
Open source	Yes	Yes
Has API	Yes	Yes
Self-hosted option	Yes	Yes
Platforms	Web and mobile (Chromium, mobile drivers)	Python
Pros	Natural language test authoring against visible UI labels rather than DOM selectors, so a component rename or layout shift does not immediately break the test suite the way a hard-coded selector would. Execution memory that accumulates across runs with trust scores and confirmation counts, which means the agent stops wasting run time rediscovering navigation patterns it has already mapped — later assertions stay focused on actual page behavior. Self-healing iteration within a single run — when an action fails, the agent retries with updated screen state observation rather than failing the step immediately, so transient UI delays cause fewer false negatives. Support for custom and open-source LLM models at the infrastructure level, so teams with data-residency requirements or API cost constraints can run inference locally without forking the tool. Open-source codebase with self-hosted deployment option, which means teams are not locked into a vendor's uptime or data pipeline when running tests against internal staging environments.	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.
Cons	The YAML step format is built for linear flows — action, verify, action, verify. Test scenarios that branch based on runtime application state (for example, different assertion paths depending on what a previous step returned from the server) have no native expression in the authoring model. Teams with conditional logic either maintain a parallel scripting layer or restructure tests into multiple flat suites, which defeats the maintenance advantage. Execution memory is only as reliable as the trust scores the agent has accumulated. On a new application or after a major redesign, early runs produce low-confidence observations and the agent behaves closer to a first-run tool — the adaptive advantage appears after repeated runs against a stable-ish UI, not on day one. Teams whose test requirements outgrow linear natural-language flows — particularly those already running Playwright or Cypress suites with custom fixtures, parameterized data, and programmatic assertions — will find agent-qa's authoring model too constrained and switch back to code-first frameworks where branching logic is a function call, not a workaround.	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.

Bottom line

Agent-QA is paid while Forensic-deepdive is free. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Agent-QA and Forensic-deepdive?

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

Is Agent-QA better than Forensic-deepdive?

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.