ShipIt

We build the parts of the toolchain that usually get skipped: the agent that actually opens the pull request, the runtime underneath it, the trace that explains what an AI system did and what it cost, and the security pass that runs before the model and costs nothing.

Alongside them, we make small native apps for the computer you work on: a Mac cleaner that explains every file before it touches it, a screen-capture studio, and a password manager with no server behind it.

Everything below is open source. Most of it runs on your keys, your infrastructure and your Mac.

	Product	What it is	Platform	Status	Links
🔨	Forge	Autonomous GitHub coding agent: fixes issues, opens PRs, reviews code with a security lens, auto-fixes CI	GitHub App · Action · CLI		Guide
🤖	shipit-agent	Python runtime for tool-using agents: MCP, RAG, memory, permissions, streaming, any LLM	Python 3.11+		Docs · PyPI
📊	Watchtower	Observability for LLM apps: tracing, prompt governance, cost allocation, PII masking	Python 3.11+		PyPI
🧹	MacSweep	Clean, protect, speed up and understand your Mac; AI usage tracking built in	macOS 15+		Website · Download
📸	Snappilot	Screen capture studio: capture, annotate, record, OCR — on-device	macOS 14+		Website · Download
🔐	KeyVault	Zero-knowledge password manager with TOTP — no server, no account	Chrome · Chromium		Website
🎨	shipit-ui-design	Senior UI/UX in your terminal — Claude Code plugin with 11 skills and 9 commands	Claude Code	open source	Live demo
🌈	ShipIt Palette	One hex to a full design system: scales, previews, 14 export formats, Figma	Web	open source	Live
✅	Vouchline	Flagship. AI research & due-diligence platform — every claim links to its quoted source, re-checked	Web		Open app
🔁	Relay	Self-hosted platform where Claude Code takes an issue to a verified pull request	Self-hosted	in development	—
🔍	Pentest skills	One /pentest command: full, evidence-based security audit with an HTML report	Claude Code	private beta	—
🛡️	Sentinel	Autonomous AI penetration testing with 23 attacker agents	SaaS	closed beta	—
🧪	ShipitQA	Evidence-first autonomous product testing in real browsers	Web	in development	—
☁️	ShipIt Cloud	Run ShipIt agents remotely with the same permissions, costs and traces	Cloud	in development	—
⌨️	ShipIt CLI	Terminal agent with 65+ tools and Slack / Discord / Telegram / WhatsApp bots	macOS · Linux	preparing OSS release	—

One runtime, many surfaces. The same agent core powers the GitHub teammate, the terminal, and the cloud — with observability wired through everything.

flowchart LR
    subgraph surfaces["Surfaces"]
        forge["🔨 Forge<br/>GitHub App · Action · CLI"]
        cli["⌨️ ShipIt CLI<br/>terminal agent"]
        cloud["☁️ ShipIt Cloud<br/>remote control plane"]
    end

    subgraph core["Core"]
        runtime["🤖 shipit-agent<br/>Python agent runtime<br/>tools · MCP · RAG · memory · permissions"]
    end

    subgraph quality["Quality & Security"]
        qa["🧪 ShipitQA<br/>autonomous browser testing"]
        sec["🛡️ Sentinel<br/>autonomous AI pentesting"]
    end

    obs["📊 Watchtower<br/>tracing · cost · PII masking"]

    forge --> runtime
    cli --> runtime
    cloud --> runtime
    runtime --> qa
    runtime --> sec
    runtime -.traces.-> obs
    forge -.traces.-> obs
    qa -.evidence.-> obs

pip install shipit-agent

Observability for LLM applications. One coherent record of what an AI system did: which prompt ran, what it cost, which tenant it belonged to, which tools it called, what it retrieved — and why it chose what it chose.

PII is masked before anything is persisted or leaves the process, because masking at display time is theatre once the raw value is on somebody else's infrastructure. Events fan out to Langfuse for analysis and to your own database as the system of record, with failures isolated per destination.

Python 3.11+ MIT · zero required dependencies · framework-agnostic

pip install shipit-watcher

Project	Version	Stars	Language	Last commit
forge
shipit_agent
shipit-watchtower
shipit-ui-design	—
ShipIt_Palette	—
snappilot
mac-sweep
keyvault

The public repos are the foundation. On top of them, currently in private development and closed beta:

Bring your own key. Nothing here proxies your traffic through us or marks up a provider's price. You hold the credentials, you see the bill.

Deterministic where it can be. A model is good at judging whether something is reachable and worth worrying about. It is unreliable at checking four thousand lines the same way twice. So the checks that can be deterministic are, they run first, and they cost nothing.

Not crying wolf is the hard part. A scanner people stop reading is worse than no scanner. A trace nobody trusts is worse than no trace. Most of the work in these tools is in what they don't say.

Own your data. Traces land in your database. Usage lands in your SQLite file. Dashboards are account- or token-gated by default, never public.

ShipIt is built by Rahul Raj — a full-stack & AI engineer in Warsaw, Poland, who has shipped production systems across edtech, automotive, insurance, and health, and now spends his time on one question: how far can autonomous agents go before a human needs to step in — and how do you make that boundary safe, observable, and cheap?

Every tool here comes from running agents in production and hitting the same walls: agents that talk instead of committing, traces nobody can read, security scans nobody trusts, and bills nobody can attribute. ShipIt is the toolchain that came out of fixing those.