Binarius AI Code Studio — Product documentation

Version 1.0.0 · Binarius Systems Private Limited

License

Binarius AI Code Studio is licensed under the Eclipse Public License 2.0 together with the Binarius end user license terms, which cover license keys, AI agents and services, data and privacy, warranty and liability. Every installation includes a 28-day free evaluation; after that a license key is required to keep using the product. Reinstalling does not restart the evaluation.

• Full terms: License terms (also shown by the installer).
• Get a key: Request a license.
• Coding agents (Claude Code, Codex, Gemini CLI, GitHub Copilot CLI) are not included; they are downloaded on first use under their own terms, and your prompts and the files they read are sent to their providers. The local agent keeps everything on your computer.

System requirements

Download

Download from the download section of the website. Each platform is available as an installer and as a zip file:

Installation

Windows — installer

1. Run binarius-ai-code-studio-1.0.0-setup.exe. If Windows SmartScreen shows Windows protected your PC, choose More info > Run anyway.
2. Accept the license terms, choose the folder (default C:\Program Files\Binarius AI Code Studio).
3. Keep Install local AI (Ollama) ticked to work offline; optionally create a desktop icon.
4. Finish and start Binarius AI Code Studio from the Start menu or desktop.

Silent install for companies: setup.exe /VERYSILENT /SUPPRESSMSGBOXES /POLICYURL=https://your-server/aijt-policy.json. Uninstall from Settings > Apps; your workspaces and settings are kept.

Windows — zip

1. Unzip to a short path such as C:\BAICS (long paths can fail on Windows).
2. Start BAICS.exe. (Do not start other .exe files in the folder.)

macOS

1. Open the .dmg and drag Binarius AI Code Studio to Applications (or unzip the zip into Applications).
2. First start: if macOS says the app cannot be checked, right-click the app > Open > Open, or System Settings > Privacy & Security > Open Anyway.

Linux

• Debian/Ubuntu: sudo apt install ./binarius-ai-code-studio-1.0.0-linux-amd64.deb, then start it from the applications menu or with baics.
• Any distribution: unzip, then run ./BAICS in the folder (GTK 3 is required). Local AI needs zstd (e.g. sudo apt install zstd).

Opening the tool for the first time

1. Choose a workspace — the folder where your projects are kept (e.g. C:\Users\you\baics-workspace). Tick Use this as the default to skip the question next time.
2. The welcome page opens. The evaluation banner shows how many days are left.
3. Choose your AI: Set up local AI (offline, downloads Ollama and the model once) or Sign in to an agent (Claude Code, Codex, Gemini CLI, GitHub Copilot CLI).
4. The AI Assistant tab is on the right of the editor (Window > AI Assistant if closed).

Activating a license key

When the evaluation ends, the product asks for a key at startup (Activate or Exit). You can enter it earlier in Preferences > Binarius AI Code Studio > License > Enter license key…. Keys look like AIJT1.… and are checked offline.

Creating a project

With the AI Assistant (recommended)

1. In the AI tab, set Project to (workspace folder).
2. Describe the program, e.g. Create a library management system in core Java with JUnit tests or Create a REST API for books with Spring Boot, and press Ctrl+Enter.
3. The agent creates a Maven project named after the task, writes the classes and tests; the IDE builds it, runs the tests and the program, and asks the agent to fix anything that fails. The new project is selected, so your next message continues on it.

By hand

File > New > Project > Maven Project or Java Project (or the New project card on the welcome page). Existing projects: File > Import > Existing Maven Projects or Projects from Git.

Using the AI Assistant

1. Pick the Agent and, if you like, the Model; choose the Project.
2. Decide on Auto-approve: on lets the agent work on its own; off asks before each step and shows every change for review.
3. Type the request and send it. Watch the steps in the transcript and the progress bar; Stop cancels.
4. Read the result: ✔ Done means it built, the tests passed and the program ran. Otherwise the transcript says what is still failing.
5. Continue with follow-ups (add a search by author), open earlier chats with History…, and commit through your chosen Git mode.

Every part of the AI Assistant and every setting is explained in detail below.

Features and usage

Binarius AI Code Studio is a complete Java IDE (Eclipse-based, with Java, Maven and Git support) plus an AI Assistant tab that connects to coding agents: Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, or a local model that runs on your computer.

Install

• Windows: run binarius-ai-code-studio-1.0.0-setup.exe. Keep Install local AI (Ollama) ticked to work offline. A Java runtime is included; nothing else is needed.
• macOS / Linux: unpack the archive and start BAICS. Local AI is installed automatically on first use.

First run in three steps

1. Choose a workspace folder (where your projects live).
2. On the welcome page, click Set up local AI (offline) or Sign in to an agent.
3. In the AI Assistant tab, type what you want, e.g. Create a project that demonstrates OOP concepts with tests, and press Ctrl+Enter.

Welcome page

Shown when the IDE starts. Cards open the AI Assistant, set up local AI, sign in to an agent, create or import projects and open settings. Clicking an example prompt puts it into the AI tab.

Workspaces and projects

A workspace is a folder with your projects. The Project box in the AI tab chooses where the agent works: one project, or (workspace folder) to let the agent create new projects. Projects the agent creates are imported and selected automatically; your next message continues on them.

The AI Assistant tab

The transcript shows your messages, the agent's replies, each tool call (e.g. Write Main.java [done]) and notices from the IDE (ℹ information, ⚠ problems, with buttons to fix them). The plan pane below the transcript shows the agent's plan when it sends one.

Agents and sign-in

Online agents are downloaded on first use (via npx) and run under their publishers' own terms. Your prompts and the files they read are sent to that provider.

Models and options

The Model box lists the models the selected agent offers; Options… holds its other settings. The list is read when you select the agent (it starts briefly in the background) and your choice is remembered per agent.

Temperature (local models)

How much randomness the model uses: 0 exact and repeatable (fixing errors), 0.2 recommended for code, 0.5 more varied ideas, 0.8–1 creative but more mistakes (not for code).

Local AI (offline)

The local agent runs a model on your computer with Ollama: code never leaves the machine and no account is needed.

• Default model: qwen2.5-coder:14b (about 9 GB; 16 GB RAM, a GPU with 8 GB+ recommended). Smaller PCs: choose qwen2.5-coder:7b in the Model box.
• Company model server: set the endpoint in Preferences > Local agent, or by admin policy.
• Settings: Preferences > Local agent (endpoint, model, temperature, max tool calls, max tokens, request timeout, Test connection).

Writing requests

• Say what you want and, if it matters, how: Create a library management system in core Java with JUnit tests; Add a REST endpoint to delete a book, with a test.
• Name a framework if you want one: … with Spring Boot and H2, … with Hibernate.
• Follow-ups work on the same project: add an interface Payable and use it in Main.
• Ask questions too: Explain this project, Why does this test fail?

The first message on a project with code makes the agent read it first and summarise it before working, so it keeps your packages, naming and libraries.

Framework and Java version

The agent reads the request first, then decides:

• You name a framework (Spring Boot, Hibernate, Quarkus, Jakarta EE…) → it uses exactly that.
• Plain programs, algorithms, OOP and data-structure demos → core Java only.
• The request needs a framework (REST API, web app, database) but names none → if one clearly fits it says which and starts; if several fit it asks you which one before creating files.

Build, test, run and fix

After every reply that changed files, the IDE checks the work itself:

1. Build the changed projects and collect compile errors.
2. Tests: if there are none, the agent is asked to write JUnit 5 tests; then they are run.
3. Main class: if a runnable program has none, the agent is asked to add one; a run configuration is created so you can run it with the Run button.
4. Run the program and read its output (servers that keep running count as started).
5. Anything failing is sent back to the agent with the errors and log, up to 5 fix rounds.

The transcript ends with ✔ Done (build clean, tests passed, program ran) or with what is still failing.

Approvals and reviewing changes

• Auto-approve on (header checkbox): the agent works without asking, like an autonomous mode. Every step is still recorded in the audit log.
• Auto-approve off: each tool call asks Allow once / Always allow for this session / Deny, and each file change opens a Compare editor. The pending changes list in the AI tab has Review, Apply, Reject and Apply all. You can edit the change before applying it.
• Allow read-only tool calls without asking (Preferences) skips the question for reading and searching.
• An admin can force review of every change and block shell commands by policy.

Switching agents and follow-ups

Change the Agent box at any time. The new agent starts on its next message, first analyses the existing code and is told which agent worked on it before and what it was asked. Use Use my last message with … in the notice to resend your request to the new agent.

Git and GitHub

Chat history

Every chat is saved per project: your messages, the agent's replies, tool calls and IDE notices, with the time of each entry and secrets removed.

Audit log

A record of AI activity for teams and compliance: sessions, prompts (secrets removed; optional), tool calls, approvals, file changes (paths, hashes and line counts, never file contents), verification results, model changes and Git actions.

Admin policy

Administrators control the IDE for a team with a policy file aijt-policy.json: allowed agents, default agent, enforced Git mode, local model server, whether shell commands are allowed, forced review, audit and chat history settings, updates. Locked settings appear greyed out with Set by your organization's policy.

Evaluation and license keys

Every installation can be used free for 28 days from its first start (the AI tab and the welcome page show the days left). After that a license key is required: at startup the IDE asks for it (Activate or Exit). Reinstalling does not restart the evaluation.

A key (AIJT1.…) names the licensee, the number of seats and the expiry date. It is checked on your computer; no internet connection is needed. Request one at the Binarius AI Code Studio website (License page).

Preferences

Agents table

The coding agents available in the AI tab's Agent box.

Claude Code, Gemini CLI, Codex and Copilot CLI need Node.js. Sign in once with each agent's own login (⋮ > Sign in to Agent in the AI tab) or put its API key into the agent's environment.

Local agent

Settings of the built-in local agent, which works with Ollama, LM Studio, vLLM or a company server with an OpenAI-compatible API.

Environment for all agents

Variables given to every agent, one NAME=value per line, for example HTTPS_PROXY=http://proxy.company:8080 or NODE_EXTRA_CA_CERTS=C:\certs\company.pem. Kept in secure storage. An agent's own environment (Edit…) overrides a variable with the same name.

Approvals

IDE tools

Git and GitHub

The Git mode itself (Manual, Branch or Pull request) is chosen per project in the AI tab.

Audit log and chat history

Updates

License

Where things are stored

Add .baics/ to .gitignore if chats should not be committed with the project.

Menus and shortcuts

Updates

If your company or Binarius provides an update site, the IDE checks it at startup and offers updates (Preferences > Updates: on/off, stable or beta). Help > Check for Updates checks manually.

Troubleshooting

© 2026 Binarius Systems Private Limited · Based on Eclipse · Eclipse Public License 2.0