Terminal, Kubernetes, Data, Git, and Chat — five professional apps that run in your browser and drive a secure engine on your own machine, free (the Git and Chat engines are coming soon). Beside them, OpenEng AI downloads, orchestrates, and runs open-weight models on your own hardware. One platform, one account.
One account · Free for all five apps · Terminal, Kubernetes & Data engines: Linux x86_64 (Kubernetes also ARM64) and macOS, Windows via WSL · AI engine: Linux x86_64
Engineering apps
Free · in betaBrowser UI, native engine on your machine — your code, clusters, and repos are never sent to OpenEng.
OpenEng AI
Pro · Launching Q4 2026Run open-weight models on your own hardware — driven from the browser.
Any registry, any weight format, the runtime that fits — run on your machine, configured in the Console, composed from 10 live catalogs.
One platform · two pillars
OpenEng is one engineering platform with two pillars: five free developer apps — Terminal, Kubernetes, Data, Git, and Chat — that run in your browser on an engine on your own machine (the Git and Chat engines are coming soon), and OpenEng AI, an agentic ecosystem for open-weight model execution.
“OpenEng is a suite of five professional developer apps — Terminal, Kubernetes, Data, Git, and Chat — that run in your web browser but execute on a small native engine you run on your own machine.”
“OpenEng is an agentic ecosystem for open-weight model execution: it downloads, orchestrates, and runs open-weight (open-source) AI models entirely on your machine.”
One suite
Each app is a focused, professional tool — and they share one account, one secure local engine model, and a price of zero.
The terminal that thinks in blocks.
A modern terminal where every command is a clean, copyable block. Organize sessions into named groups, drive real interactive shells, run one command in two terminals at once, and diff their output — all executing locally on your machine.
A full Kubernetes console, one pane of glass.
Connect every cluster in your kubeconfig — plus cloud clusters through a connector — and work them like a native IDE: browse and edit any resource, stream logs, exec into pods, port-forward, map the topology, and read live metrics. No kubectl required.
Every database, one query workbench.
Connect to any database — SQL (PostgreSQL, MySQL, CockroachDB, SQLite), document (MongoDB), key-value (Redis), graph (Neo4j), object stores, and streaming (Apache Kafka) — browse the full object tree and run queries, all executing on your own machine. Cloud systems connect through least-privilege connectors that run in your own cloud.
A desktop-grade Git client in your browser.
Everything you normally drop to the CLI for — status, diffs, staging, commits, history, the commit graph, branches, and push/pull/fetch — across every repo on your machine, plus CI & CD runs from your forge, in one fast workbench backed by libgit2.
A coding agent that runs on your machine.
A local coding and integration agent. The browser is a thin client; repository indexing, file edits, and every conversation happen inside a sealed engine on your own hardware. By default, inference, indexing, and conversations stay on your machine and nothing is sent to OpenEng; a model you point at an external server, and any MCP server you attach, receive what you send them.
Install an engine, open the app, sign in, and run the one-time command it shows — the page then connects to your machine automatically. Terminal, Kubernetes, and Data engines install in one line today; Git and Chat engines are coming soon.
How the apps work
Unlike SaaS dev tools, the OpenEng apps never send your code, clusters, or repos to our servers. The UI lives in the browser; all the work happens on your hardware.
One line installs the small native engine for the app you want and checks it against its published SHA-256 when a sha256 tool is available — no build step, no toolchain.
Sign in once in your browser. The app shows a one-time command to start your engine, carrying a single-use key tied to your sign-in.
terminal.openeng.appRun the command the app shows — the engine starts on your machine, listens only on 127.0.0.1, and the page connects automatically, sealed end-to-end.
# paste the start command from the appBrowser tab
terminal.openeng.app
Engine · your machine
127.0.0.1:50052 · loopback only
Connection is sealed per frame with a fresh, unique key — end-to-end, even on your own machine. How we keep it private →
Shown for Terminal; Kubernetes and Data install the same way. Git and Chat: engine coming soon.
Why OpenEng
All five OpenEng apps — Terminal, Kubernetes, Data, Git, and Chat — are free to use. No tiers, no subscriptions, nothing to unlock. Just install an engine and open the app (Git and Chat engines are coming soon).
OpenEng AI · open-weight model execution
OpenEng downloads, orchestrates, and runs open-weight (open-source) AI models on your own hardware — from any registry, in any major weight format, on the runtime that fits — its built-in models in the engine’s enclosed model daemon, and catalog models through a local Ollama daemon you install. You drive it from the browser over an encrypted channel, with its streamed replies sealed end-to-end. Private and local — the engine sends no usage telemetry.
Status: OpenEng AI isn’t live yet. The Console and Web Console interfaces load, but the OpenEng AI API routes and the Broker aren’t deployed. Nothing can be saved or published, and no AI engine can register or connect. Pro, Enterprise, and pay-as-you-go launch in Q4 2026 and can’t be purchased yet. This section describes how it is built to work.
Thin client · renders only · no secrets past the tab
prompt in
via the broker
replies out
sealed end-to-end
On-device · stays on the machine
The OpenEng Broker opens requests only to route them to your engine, and opens the thread history and memory it delivers; it keeps what it routes 7 days by default. The engine’s streamed replies are sealed end-to-end, so the broker can’t read them. Models, provider keys, and your files stay on your machine.
Install · Linux x86_64
One line puts the openeng binary on your PATH, checked against its published SHA-256 when a sha256 tool is available. On Windows, run it under WSL; there is no macOS build of the AI engine yet.
Start · with your OpenEng key
The engine boots only with an OpenEng key — an API key you create in the Console — passed as --key=<K> or read from OPENENG_KEY. Then pick it and a published config in the Web Console.
Plan · Pro
Launching Q4 2026
The engine registers your key with the OpenEng API, which requires an active Pro plan. Pro, Enterprise, and pay-as-you-go are launching Q4 2026 and can’t be purchased yet.
See pricingLive in the public catalogs today
The architecture
The intelligence runs on your machine: the engine owns the agent loop and your provider keys, its built-in models run in its enclosed model daemon, and catalog models run in your local Ollama (a hosted model, such as the Cloud Planner, is a per-role choice). The browser is a thin client that only renders — the only thing between it and your engine is OpenEng's broker, a relay that routes your requests and the data the console loads, and cannot read the engine's streamed replies.
Why it’s built this way
Model weights, embeddings, the engine’s stored provider keys, and your OpenEng key never cross the wire. A secret you type into the Web Console goes one way, write-only, to the vault, and is never read back by a browser. The models run on your machine, and what you exchange in the Web Console crosses the wire, encrypted.
Crosses the wire, encrypted
Never crosses
The wire carries only what you exchange
Your requests, the engine’s streamed replies, and the engine data the Web Console shows you — thread history, learned memory, the running config — encrypted on every hop. Model weights, embeddings, the engine’s stored provider keys, and your OpenEng key never cross.
Sealed replies
The engine’s streamed replies are sealed end-to-end to your browser — the broker that relays them cannot read them. Your requests, and the engine data the console loads, travel encrypted to the broker, which opens them to route them.
Thin client, by construction
The browser bundle holds no model. The engine’s stored provider keys never cross the wire, and a vault value you type is never read back by a browser.
The engine
A model is three independent choices: where the weights come from, what format they are in, and which runtime executes them — the format determines which runtimes can run it. Combine several models in one config — a role group — so each job runs on a right-sized model. Built-in models run in the engine’s enclosed model daemon, catalog models through a local Ollama daemon you install, and hosted models route through one gateway.
The Web Console
A thin React client that streams your own engine's work over an encrypted channel with sealed replies — engine-owned threads, streaming replies, in-browser permission prompts. No native install for the interface.
The control plane
Configure your whole agent platform in the browser, freeze it into an immutable id@version, and every engine you start with your OpenEng key pulls the exact same config version. (Saving and publishing open once the Console’s API is deployed.)
${ENV} names, not values; they resolve on the machine running your engine. If you choose, the optional write-only vault stores a value encrypted on our servers for your engine to fetch, and an environment variable always wins.The ecosystem
Browse and snap together agents, skills, templates, models, cells, plugins, loops, library bundles, roles, and connectors — then publish a config your engine just runs. Compose, don't code.
1,092 agents: 810 single-purpose agents and 282 orchestrators (212 / 68 / 2 on levels 1–3), across 35 categories.
Named, invocable playbooks the engine runs on demand, across 18 categories.
Prompt blueprints prepended above your persona, across 28 segments.
AWS / Azure / GCP cells (435 read, 115 write) exposing 1,053 cloud tools, deployed in your own cloud account.
On-device open-weight models from the Ollama library, about 1 GB up to Llama 3.3 70B, run through your local Ollama — no provider API keys.
14 gateway plugins: 2 built-in modules and 12 external decision, approval, and tooling endpoints, layered above the security floor.
Global loops: backlog burn-down and failing tests until green need no integration; alert triage, inbox-to-done, the nightly PR review sweep, and the ticket sweep need integrations that aren’t live yet.
Curated bundles of agents, skills, templates, cells, and models — backend APIs, CI/CD, FinOps, Kubernetes, security, and more.
Role definitions across 19 categories, each with the components and capabilities it needs.
Bring-your-own-cloud connector packages for the Data, Terminal, and Kubernetes apps — AWS, Azure, GCP, and databases; 13 validated against live services so far.
Under the hood
Pricing
The five engineering apps are free — every app, every feature. OpenEng AI's Pro, Enterprise, and pay-as-you-go plans are launching Q4 2026 — pay-as-you-go planning credit for the included Cloud Planner tops up a Pro or Enterprise account from $5.
Engineering apps
$0
Free · all five apps, every feature
OpenEng AI · Pro
Soon
Launching Q4 2026 · needed for the AI engine
Pay-as-you-go
from $5
planning credit for the Cloud Planner · Launching Q4 2026
Enterprise
Custom
size it yourself · Launching Q4 2026
FAQ
The short version: five professional dev apps, free, running on your own machine — and OpenEng AI for running open-weight models on your own hardware.
OpenEng is one engineering platform with two pillars: five free developer apps — Terminal, Kubernetes, Data, Git, and Chat — that run in your browser on an engine on your own machine (the Git and Chat engines are coming soon), and OpenEng AI, an agentic ecosystem for open-weight model execution.
OpenEng is a suite of five professional developer apps — Terminal, Kubernetes, Data, Git, and Chat — that run in your web browser but execute on a small native engine you run on your own machine. The browser is a thin UI — the real work happens locally on your hardware — and every app and every feature is free.
OpenEng is an agentic ecosystem for open-weight model execution: it downloads, orchestrates, and runs open-weight (open-source) AI models entirely on your machine. A local engine runs the models (the built-in ones in its enclosed model daemon, catalog models through your local Ollama) and holds the agent loop, your threads, and your provider keys; you drive it from the browser Web Console and configure it in the Console. The AI engine starts with an OpenEng key and needs a Pro plan, which launches in Q4 2026.
OpenEng Terminal (terminal.openeng.app): The terminal that thinks in blocks.
OpenEng Kubernetes (k8s.openeng.app): A full Kubernetes console, one pane of glass.
OpenEng Data (data.openeng.app): Every database, one query workbench.
OpenEng Git (git.openeng.app): A desktop-grade Git client in your browser.
OpenEng Chat (chat.openeng.app): A coding agent that runs on your machine.
All five are free and open in your browser. The Terminal, Kubernetes, and Data engines are published today; the Git and Chat engines are coming soon.
Open-weight means the model’s trained weights are published for download, so you can run the model yourself — which is exactly what OpenEng does, on your own hardware. “Open source” in the strict sense (the OSI Open Source AI Definition) is a higher bar that also covers training data and process. Most downloadable models people call “open source” are, precisely, open-weight. OpenEng uses “open-weight” for accuracy and treats “open-source models” as the common synonym. Note: the models are open-weight; the OpenEng platform itself is not open source.
For an engineering app, install the small native engine for that app with a one-line script — for example curl -fsSL https://openeng.app/engine/terminal/install.sh | bash — then open the app in your browser and sign in once. The app shows you a one-time command to start the engine (openeng-terminal serve --oauth=<key>, carrying a one-time key tied to your sign-in); copy it, run it, and the page connects automatically. Engines are published for Terminal, Kubernetes, and Data; the Git and Chat engines are coming soon.
For OpenEng AI, install the AI engine on Linux x86_64 with curl -fsSL https://openeng.app/engine/install.sh | bash, then start it with an OpenEng key from the Console; the engine needs a Pro plan, which launches in Q4 2026. Every installer, binary, and checksum is listed at openeng.app/download.
Not in the five apps: your code, repositories, clusters, terminal output, and databases are never sent to OpenEng. Each engine runs locally, listens only on 127.0.0.1, and the web app seals every frame of its session with the engine. What you point an app at yourself — your SSH hosts, clusters, forges, MCP servers, connectors, or an external model server for Chat — receives what you send it.
In OpenEng AI, your files are read and processed on your machine, but anything that appears in a conversation — your prompts and the engine’s replies, which can quote your code — passes through the OpenEng Broker, which can read the prompts and the thread history and keeps it for 7 days by default, and a hosted model you choose receives what you send it. Local models run on your machine — the built-in models in the engine’s enclosed model daemon, catalog models in your local Ollama — and a hosted model is used only for a role you point at one (the Console’s default planner option, the included Cloud Planner, is one). The browser Web Console is a thin client that holds no model, and a vault value you type is never read back by a browser. What you type there travels encrypted to the OpenEng Broker, which opens each request to route it to your engine. The engine’s streamed replies are sealed end to end, so the Broker cannot read them. The engine data the Web Console loads — your thread list and history (past prompts and answers, which can quote your code), learned memory, the running config, placeholder names, and loop, warm-up, and device status — is sealed to the Broker, which opens it to deliver it. The Broker keeps everything it routes for a retention window (7 days by default), then deletes it.
The engineering apps are. Terminal, Kubernetes, Data, Git, and Chat are free to use — every app and every feature, with no tiers, subscriptions, or paywalls.
OpenEng AI is different: the AI engine starts only with an OpenEng key and an active Pro plan, and Pro — like Enterprise and pay-as-you-go credit — launches in Q4 2026, so it cannot be bought yet. The public catalogs of models, agents, skills, templates, and more are open to everyone.
Install the Terminal engine, open terminal.openeng.app, sign in, and run the one-time command it shows — the page then connects to your machine automatically. OpenEng AI’s engine joins it when Pro launches in Q4 2026.
Install the Terminal engine · Linux x86_64 · macOS (Apple silicon, Intel) · Windows via WSL