Build with AI agents. Ship with proof.
OpenThunder is the agentic dev environment you can trust. It understands your repo, runs AI agents that make real changes, and independently verifies their work with evidence. No account or AI key required to start.
npx @skillstech/openthunder can-i-ship
More than a terminal. An agentic workbench.
Understand, build, verify, and master a repo in one place. The agents do the work; OpenThunder proves it before you ship.
Agentic missions
Describe a change in plain language. A builder implements it, an independent reviewer challenges it, your real tests run, and you get a PR evidence pack. No green check without proof.
Overnight runs
Queue verified agents to work while you sleep. Wake up to changes that already passed an independent review, with the evidence attached.
Built-in browser Preview
Reach OpenThunder Cloud and Repo Mastery inside the app, right next to your code and your agents. No tab-switching, no context lost.
Repo Mastery, included
Every repo becomes walkthroughs, flashcards, and a mastery score, built into OpenThunder on Desktop, Cloud, and the web. No separate product to buy.
See your repo clearly
OpenThunder runs on your machine and shows its work, visually.
Architecture Lens
Map the system as it actually exists: critical flows, dependencies, hotspots, coupling, testability, and production readiness.
Code Health Lens
Maintainability, reliability, complexity, duplication, and test posture, with new-code focus so you fix what this branch introduced, not years of legacy.
Security Lens: Traditional + AI
A security scorecard and STRIDE threat model, plus AI security: prompt injection, unsafe RAG, excessive agency, and tool/MCP risk in AI-era codebases.
Evidence reports
Every verified change includes build logs, test results, reviewer findings, and the proof behind the green check.
AI made building faster. Ownership got harder.
The hard part is no longer generating code. It's understanding what changed, knowing what could break, and being able to defend the system after AI touched it. OpenThunder gets you from a guess to proof.
The repo intelligence layer for AI-assisted development
Understand it, give your AI tools context, track what changed, and verify it, all on your machine.
Understand the repo
See the architecture the AI actually built: maps, critical flows, dependencies, fragile zones, and cited answers to your questions.
Feed your AI tools context
Generate CLAUDE.md, AGENTS.md, Cursor rules, and copy-ready prompts so Claude Code, Codex, Cursor, and Copilot make safer changes with real repo context.
Track what changed
Catch-up briefs and a change ledger explain what moved since you last looked, including what other developers changed, straight from git history.
Secure it
Surface security risks and threat-model the system before changes ever reach production.
Verify and prove it
Describe a change in plain language. A builder implements it, an independent reviewer challenges it, your real tests run, and you get a PR evidence pack. No green check without evidence.
Explain and defend it
Turn repo understanding into the words to explain the architecture in a review, and into Skills Tech Talk® practice to rehearse defending it.
What OpenThunder is, and is not
A clear category, so you know exactly where it fits.
- Mission control for AI-assisted software engineering: the local-first workbench to understand, plan, verify, and prove changes
- The context source your AI coding tools were missing (CLAUDE.md, AGENTS.md, Cursor rules)
- An architecture and security lens that tracks how the code evolved
- A way to verify AI-assisted changes with evidence, and a bridge into Skills Tech Talk® practice
- Not just another IDE: it starts beside your editor and AI coding tools, then gives them repo intelligence, mission planning, safer context, and verification
- Not a generic chatbot: it is structured around software missions, understand, plan, change, verify, explain, and ship
- Not a blind auto-merge agent: it can automate low-risk work over time, but every change is governed by evidence, tests, policy, and Can-I-Ship checks
- Not a course platform: OpenThunder emits repo intelligence and native Repository Mastery; Skills Tech Talk turns it into learning, explanation, and defense
Use OpenThunder when…
The moments where understanding and proof matter most.
Why not just ChatGPT, Cursor, or Claude Code?
They are great at what they do. OpenThunder does the part they leave out.
| Tool | Best for | What it leaves out |
|---|---|---|
| ChatGPT | General explanations and brainstorming | Not continuously grounded in your repo unless you paste context |
| Cursor / Copilot | Writing code faster | Does not prove architecture, security, and change safety end to end |
| Claude Code | Implementing repo changes | Still needs independent review, evidence, and mastery |
| OpenThunder | Understanding, securing, and verifying the repo | Not trying to replace your coding editor |
| Skills Tech Talk® | Practicing until you can explain and defend the repo | Needs OpenThunder for real repo intelligence |
Download
One file. Double-click and run it like any desktop app.
Verify this release yourself
OpenThunder is built with AI and verified with evidence, and that includes its own releases. Each desktop release publishes its Evidence Pack alongside the installers: SHA-256 checksums for every artifact, a full CycloneDX SBOM (every resolved dependency with its integrity digest), and SLSA-style provenance recording the source commit and the CI workflow that built them. Don’t take the download on trust; check it:
cd ~/Downloads
curl -fsSLO https://openthunder.dev/releases/OpenThunder-mac-universal.dmg
curl -fsSLO https://openthunder.dev/releases/evidence/SHA256SUMS
shasum -a 256 -c SHA256SUMS --ignore-missing
Re-download the installer so you verify the current build (an older copy in Downloads will not match).
OK means the file on your disk is byte-for-byte the build this evidence describes.
With OpenThunder installed you can verify the whole manifest instead:
openthunder verify-artifacts checksums.json --dir .
Want more proof? See the engine run in public against well-known open-source repos in the Evidence Gallery, or read how Evidence Packs work.
How it works
No setup required to start. Add model routing, test commands, or cloud sync only when you want more control.
-
1. Open your project
Point OpenThunder at any folder. It maps your architecture and highlights risks, no setup required.
-
2. Ask anything about the code
Ask "how does auth work here?" and get answers grounded in your actual files, with the relevant code cited.
-
3. Describe a change in plain language
Tell OpenThunder what you want changed. A builder makes it, an independent reviewer challenges it, and your tests run automatically.
-
4. Ship with proof
Every verified change comes with an evidence report: build logs, test results, reviewer findings, and risk checks.
Local-first by default. Cloud only by choice.
Source code is not uploaded by default. API keys stay on your machine. OpenThunder does not force-push or auto-merge. Cloud sync and repo training are optional and opt-in. See exactly what happens to your code →
Runs locally
Repo analysis happens on your computer. Your source code is not uploaded by default.
No account required
Open a repo and start offline. Sign in only if you want cloud sync or repo training.
Your keys stay yours
API keys live on your machine. They never touch OpenThunder servers, logs, or your repo.
Your git stays yours
OpenThunder never force-pushes or auto-merges to your main branch, and warns before working on a dirty tree.
From a repo you inherited to a map you can defend.
OpenThunder traces the real architecture the AI built: components, how data flows, and the risky paths, generated from your code on your machine.
System & container maps
See every component and how they connect, plus C4 container, data-flow, dependency, and trust-boundary diagrams.
Critical flows, traced
Follow a request end to end through the code, with the risky paths flagged and explained.
Exportable to mastery
Every map becomes part of a Repository Mastery Pack you can study and defend in Skills Tech Talk®.
What OpenThunder gives you
Concrete artifacts you can read, share, and defend.
Architecture Map
The major components, responsibilities, critical flows, and risky dependencies.
Code Health Report
Maintainability, reliability, complexity, duplication, and test posture, with a new-code focus so you fix what this branch introduced.
Security & AI Security Findings
Trust boundaries and STRIDE risks, plus AI-era risks: prompt injection, unsafe RAG, excessive agency, and tool/MCP exposure.
Evidence Report
What changed, what passed, what failed, and what the independent reviewer challenged.
Agent Fix Prompts
Every finding turns into a Claude, Codex, or Cursor-ready prompt with context, constraints, and the tests to prove the fix.
Repo Mastery
Summaries, walkthroughs, flashcards, quiz questions, and a repo mastery score, built into OpenThunder on Desktop, Cloud, and the web.
Master any repo. Repo Mastery, included.
Repo Mastery is built into OpenThunder, on Desktop, Cloud, and the web. It turns any codebase into study material you can learn, practice, and defend, with no separate account.
- A plain-English repo summary
- Architecture walkthroughs
- Tech stack explanations
- Critical flow breakdowns
- Flashcards
- Multiple-choice questions
- Try Voice prompts
- Interview questions
- A repo mastery score
Repo Mastery lives inside OpenThunder. Skills Tech Talk® takes it further: interviews, practice, and certification.
From scan to mastery
OpenThunder is the first step. Mastery is the payoff.
- 1
Scan the repo
Open any folder in OpenThunder and let it map the codebase.
- 2
Read the architecture map
See components, flows, dependencies, and risks at a glance.
- 3
Verify risky changes
Build, review, and test changes with evidence behind the green check.
- 4
Master it with Repo Mastery
Turn the repo into walkthroughs, flashcards, and a mastery score, built in.
- 5
Go further in Skills Tech Talk®
Optional: drill until you can explain and defend the repo under pressure.
Guides and how-tos
Short, practical walk-throughs of the core surfaces.
Open your first repo
Point OpenThunder at a folder, run your first scan, and read the architecture map.
Your first verified change
Describe a change, review the result, and read the evidence report behind the green check.
Map and question a repo
Scan a codebase, read the scorecard, and ask architecture questions with cited answers.
See the risks before you ship
Review findings, walk the STRIDE threat model, and see what needs attention before release.
Use local or cloud models
Run Ollama locally for privacy, or route complex steps to cloud models when you choose.
Train on this repo
Export a Repository Mastery Pack and turn the codebase into guided learning.
More guides are on the way.
Releases and updates
OpenThunder keeps itself up to date. Here is what is in each build.
OpenThunder™ Desktop is free. Teams are the upgrade.
Desktop and Repo Mastery are free for individuals: understand, build, verify, and master any repo on your own machine. OpenThunder Cloud adds shared repos, agent governance, and organization-wide evidence for teams. Skills Tech Talk® is the connected practice product for interviews, defense, and certification.
Stop shipping code you cannot explain.
OpenThunder helps you understand the architecture, find the risks, verify the change, and turn the repo into a mastery path.
Own the repo. Master the story.