Space to askReplay ↺
Get a live walkthrough of any PR, out loud, right now. #
Hold Space and ask what a PR does. DiffGuardian walks you through it as it goes: the features it ships, what each one changes, what it touches. You hear it while the code it's explaining scrolls into view and lights up. Ask a follow-up whenever you like.
- Instant. No setup per PR. Ask and it starts talking.
- Live. The code it's explaining is highlighted and scrolled into view as it talks.
- Yours to steer. Ask for the part you care about first, or skip straight to the one file that matters to you.
Pro. Runs on your own OpenAI or ElevenLabs key, or your system's built-in voice.
Space to askReplay ↺
Ask the whole repo a question. Hear the walkthrough. See it on a live graph. #
DiffGuardian, available on macOS, Windows and Linux, indexes your repo into a code knowledge graph. Hold Space and ask how auth works or where a webhook is verified. It answers out loud while a live visual of the flow builds on screen, straight from your call graph.
Space to askReplay ↺
Every request passes through authMiddleware. It verifies the token, loads the user's role, then asks PermissionService whether that role is allowed to do the action. Admin routes require the admin role. Anyone else gets a 403, and the denial is logged.
▤ Role-based access · on canvas
- 01Ask out loud Hold Space and ask. No typing, no prompt writing.
- 02Hear it explained Plain English, with the real files named as it goes.
- 03See the graph The visual aid builds as it talks.
Prefer typing? The chat is still there.
Prefer to read? Trace It gives you the walkthrough at your pace. #
Hit Trace It! and a 5,000-line PR becomes a guided tour, one feature at a time, each explained in plain English. Read it as slowly as you like, go back, and approve having seen the whole thing, not skimmed a diff.
- Walkthrough, written — the PR broken into the features it ships, each explained in plain English
- Blast radius — a dependency graph built from the diff alone (heuristic, not AI): every file and module a change actually touches, before it merges
Want it spoken instead? Talk to your PR.
Ten agents, forty PRs. You still know what's shipping. #
When agents work in parallel, the bottleneck is you. For every PR, DiffGuardian finds the quickest way for you to understand it, so you spend minutes on each one instead of reading every line or rubberstamping it.
- Read itA written walkthrough, feature by feature Trace It breaks the PR into what it ships and explains each part at your own pace.See how
- Hear itThe same walkthrough, spoken Ask out loud and get it told back, with the code it's explaining highlighted as it goes.See how
- See itA graph of what a change touches Every file and module a change reaches, drawn from the diff alone, before it merges.See how
For everyone who needs to know how their products are actually built. #
Engineers Understand a PR well enough to approve it, without reading every line.
PMs Ask what shipped and get a plain-English answer you can trust, without reading code or waiting for someone to explain it.
Anyone building software Founders, designers, QA, analysts, anyone working on an application: ask what the code does and get a plain-English answer, spoken.
Working with a team?
Onboard in minutes A new developer sets up in a few minutes, then talks to the codebase and hears how auth or billing works, with a live graph.
Everyone understands the PR The author, reviewer and PM each get the walkthrough that suits them: read it, hear it or see it.
PMs ask, engineers keep building A PM asks out loud how a feature works and gets a plain-English answer.
Hand-off without the author Inherit an agent-written PR and get the walkthrough instead of waiting on someone's memory.
Your models. Your keys. #
Your voice.
Your code never touches our servers.
Bring your own key for Anthropic, OpenAI, Gemini or OpenRouter, or run a local model. Pick a model for each job. Voice runs on your own OpenAI or ElevenLabs key, or your system's built-in voice, and none of it reaches our servers.
- One OpenRouter key reaches ~400 models, with no new account per vendor
- You pay the provider directly, with no markup
- Ollama, LM Studio, llama.cpp and vLLM work out of the box
- Knowledge bases stay on your machine, and credentials sit in your OS keychain
Your machine llama-3.3-70b · local Anthropic not contacted
OpenRouter~400 models · not contacted
0 bytes left your machine
0 tokens in cloud cache
100% keys held in your OS keychain
Most tools take you out of the code. DiffGuardian keeps you in it, and makes it quick. #
| How DiffGuardian compares with most AI code tools | |
|---|---|
| Most AI code tools | DiffGuardian |
| --- | --- |
| Hand you a verdict or a list of comments | Explain what the change does, so you can decide |
| Summarise the code so you can skip it | Walk you through the code, in writing or out loud |
| Ask you to trust the AI | Show you the code behind every answer |
| Give you long text to read | Talk you through it, highlighting the code, and build a graph when you ask about the whole codebase |
| Lock you to one model and one vendor | Work with your own models and keys, or fully local |
The goal isn't less code in your head. It's the same understanding in a fraction of the time. See the full comparison.
Free to start. Upgrade to talk to your code. #
Every plan works with local models. Pro adds voice and cloud providers on your own keys. Enterprise, with single sign-on, is coming soon.
$8/mo
For engineers who want to move fast.
[Get Pro](https://diffguardian.ai/#download)
- Everything in Basic
- Voice: talk to your PRs and your codebase
- Unlimited repositories and AI reviews
- Managed AI Providers — BYOK, incl. OpenRouter
- Trace It, Ask, Explain and Polish
- Analyze Project, knowledge bases and RAG
- MCP Servers integration
- And many more…
$8/seat/mo
For teams moving fast, working together.
[Register my team](https://diffguardian.ai/team)
- Everything in Pro, for everyone
- Centralised seat billing for the whole team
- Seat management and invoicing
- Minimum of 3 seats
Set up by an organisation admin, who buys the seats for the team. Everyone else just downloads the app — individual sign-in happens inside DiffGuardian during onboarding, never here.
Every feature, side by side. #
| Features | BasicFree | ProUSD $8/mo | TeamUSD $8/seat/mo |
|---|---|---|---|
| Connected repositories | 1, public only | Unlimited | Unlimited |
| AI reviews | 5 / month | Unlimited | Unlimited |
| Models | |||
| Locally-hosted models (Ollama, LM Studio, llama.cpp, vLLM) | |||
| Cloud providers with your own keys (Anthropic, OpenAI, Gemini) | – | ||
| OpenRouter — ~400 models on one key | – | ||
| Review & understanding | |||
| Voice: talk to PRs and your codebase | – | ||
| AI reviews & summaries | |||
| Dependency graphs | |||
| Stack maps | |||
| Trace It — guided walkthrough of a diff | – | ||
| Ask — question your project and PRs | – | ||
| Explain & Polish | – | ||
| Analyze Project | – | ||
| Knowledge bases & RAG | – | ||
| MCP Servers | – | ||
| Teams | |||
| Centralised seat billing | – | – | |
| Add or remove users any time | – | – |
Your questions, answered. #
What does DiffGuardian actually do? #
understand code as fast as agents write it. It gives you a walkthrough of a pull request one feature at a time, lets you talk to a PR or your whole codebase and hear the answer, and leaves the decision to approve with you.
Can I really talk to a PR? #
What's the difference between Trace It and voice? #
Can it keep up with many agents working in parallel? #
I'm a PM, not an engineer. Is it for me? #
Is it only for solo developers? #
Where does my voice go? #
Is my code private? #
Security page for the full data-flow breakdown.
Which platforms is DiffGuardian available on? #
macOS,
Windows and
Linux. The Windows build is an x64 installer that isn't code-signed yet, so Windows may show a SmartScreen warning before you can run it. On Linux, install the
.deb or
.rpm package for your distribution — they declare the dependency DiffGuardian's secure key storage needs, so it works out of the box. Use the
AppImage only if neither package fits your distribution; it still auto-updates like every other build.
How does billing work, and can I cancel? #
How is this different from the AI tools I already have? #
how DiffGuardian compares.