Open Science

Open Science

[](https://github.com/aipoch/open-science/releases/latest) [](https://github.com/aipoch/open-science/releases/latest) [](LICENSE)

[](https://github.com/aipoch/open-science/discussions) [](https://discord.gg/85dKfuGM9) [](https://www.youtube.com/@AIPOCHAI) [](https://x.com/aipochai) [](https://www.linkedin.com/company/pochai)

An open-source, model-agnostic AI workbench for scientific discovery. Open Science is a local desktop application for researchers. Create a project, describe a task in plain language, and let the agent read files, run code, search the web, call scientific data connectors, and return reports, tables, figures, and an inspectable activity history in one workspace.

> ⭐ Star the repo: If this project has been helpful, we'd greatly appreciate a star on GitHub. Starring the repository encourages continued development. It only takes a second, but it has a meaningful impact on the project.

> 💡 The application is available now. Installers for macOS, Windows, and Linux are published on the latest release page. Open Science supports the complete plan → execute → produce → preview workflow; use the release notes and the installed app for version-specific details.

Table of Contents

• [Quick Start](#-quick-start)
• [Product Tour](#product-tour)
• [Frequently Asked Questions](#frequently-asked-questions)
• [Why Open Science](#why-open-science)
• [Vision](#vision)
• [Design Principles](#design-principles)
• [Core Capabilities](#core-capabilities)
• [Model Providers](#model-providers)
• [Data, Permissions, and Trust](#data-permissions-and-trust)
• [Project Status](#project-status)
• [Development & Packaging](#development--packaging)
• [Building From Source](#building-from-source)
• [Roadmap](#roadmap)
• [Relationship to the aipoch Ecosystem](#relationship-to-the-aipoch-ecosystem)
• [What This Is Not](#what-this-is-not)
• [Get Involved](#get-involved)
• [License](#license)
• [Star History](#star-history)

🚀 Quick Start

1. Download the app

Open the latest release, expand Assets, and choose the installer for your computer:

| Your computer | Choose | | ----------------------------------- | ---------------------------------------- | | macOS — Apple Silicon (M1 or newer) | The macOS DMG for Apple Silicon / ARM64 | | macOS — Intel | The macOS DMG for Intel / x64 | | Windows x64 | The Windows x64 installer | | Linux x64 | The Linux x64 AppImage or Debian package |

Review the assets and verification information published on the release page. See [Verifying your download](SECURITY.md#verifying-your-download) before installation if you need to validate a package.

> If macOS or Windows shows an unidentified-developer or unknown-publisher warning, verify that the package came from the official Releases page before continuing. See [Building From Source](#building-from-source) for platform-specific guidance.

2. Complete first-time setup

The first launch has two guided steps:

1. Prepare environment checks compatibility, app storage, secure credential storage, network access, the Claude runtime, and optional Python Notebook support. If the runtime is missing, Open Science can install an app-managed copy without requiring Node.js, npm, or an administrator password.
2. Model provider connects and tests the model you want to use. Choose a built-in provider, an Anthropic-compatible custom gateway, or Local Claude to reuse an existing Claude Code login without entering an API Key.

Automatic environment detection and managed runtime setup Provider, API Key, endpoint, and model validation

Python is optional unless you want the built-in Notebook kernel. Every required environment row must pass before Continue becomes available, and the model connection must pass before setup finishes.

3. Start a research project

1. Click New project and give the project a stable research name and optional description.
2. Open a session and describe the goal, input data, constraints, desired outputs, and how the result should be checked.
3. Attach source files, select a verified model, and choose an approval mode.
4. Send the task. Inspect the agent's tool activity, approve sensitive actions, and open generated artifacts in the preview panel.
5. Continue the work in later sessions. Use @ to reference an existing project file and / to explicitly select an enabled skill.

Want to develop the app instead? Skip to [Building From Source](#building-from-source).

> Screenshots in this README illustrate the workflow. Labels, catalogs, and other interface details may differ from the version you install.

Product Tour

One workspace from task to artifacts

Projects keep related sessions, uploads, generated files, and preview state together. The conversation records the agent's answer and the commands, file reads, edits, searches, and connector calls that produced it. Generated reports, figures, and tables remain attached to the session and are also collected in the project file library.

Uploads and generated files organized by project and session Native previews keep data and the research history side by side

Open Science previews common scientific data, documents, images, source code, molecular structures and reactions, and Notebook history. Preview limits do not truncate the underlying file—the full artifact stays available to the agent and external tools.

Scientific skills and data connectors

Open Science includes a growing catalog of featured, file-based research skills. You can create personal skills, upload SKILL.md/ZIP/.skill packages, or preview and import compatible skills from GitHub. Enabled skills can be selected directly in the composer with /.

It also includes life-science connectors across literature, genes and proteins, genomics, variants, structures, clinical research, expression, chemistry, drug regulation, and related resources. Built-in and custom connectors remain behind the permission system, with per-tool Always allow, Ask each time, and Block controls. The installed app shows the current skill, connector, and tool catalogs.

Readable, reusable research skills Scientific databases exposed as permissioned agent tools

Frequently Asked Questions

Q: What should I do the first time I open Open Science?

A: Complete Prepare environment and Model provider. Fix required rows marked Action needed, use Install missing runtime if offered, click Check again, and then test a model connection.

Q: What is an API Key, and where do I get one?

A: An API Key is a secret credential issued by a model provider. Create or copy one from that provider's developer/API console. The provider may bill requests made with the key. Treat it like a password: never share it or commit it to a repository.

Q: Do I need an API Key?

A: Not if you choose Local Claude and already have a working Claude Code login on this computer. Built-in cloud providers and custom gateways require their own keys.

Q: Which model providers can I use?

A: Open the provider picker during setup or under Settings → Model for the choices supported by your installed app. You can use a built-in cloud provider, an Anthropic-compatible Custom Gateway, or Local Claude.

Q: Why does the model connection test fail?

A: Check the API Key for missing characters or spaces, verify the Base URL and region, use the provider's exact model ID, and confirm network access and account balance. For Local Claude, run claude in a terminal and complete login before testing again.

Q: Why is Continue disabled during setup?

A: At least one required environment check has not passed. Fix the row marked Action needed, return to automatic detection, and click Check again. Python is optional and only affects Notebook execution.

Q: Setup is complete. How do I start a research task?

A: Create or open a project, start a session, attach any source files, and describe the goal, constraints, expected output, and validation criteria. Use @ to reference a project file and / to select an enabled skill.

Q: Does my research data stay on my computer?

A: Projects, sessions, files, settings, and configured credentials are stored locally by default. Content needed for model requests, web searches, or connector calls may still be sent to the external service you selected, so review sensitive inputs and provider policies before running a task.

Why Open Science

Research work is usually split across chat windows, notebooks, local scripts, scientific databases, file browsers, and reporting tools. Context is lost at every handoff, and the answer is often separated from the code and files that produced it.

Open Science brings those pieces into one inspectable desktop workspace:

• Work that persists. Projects, sessions, drafts, files, previews, and run history survive application restarts.
• Execution, not just suggestions. The agent can run commands and Python, edit files, search, call connectors, and generate artifacts with the user's approval.
• Multiple model choices. Use a built-in cloud provider, a compatible custom gateway, or a local Claude login.
• Local-first ownership. The application and project state run on your computer; external calls happen through services you explicitly configure or approve.
• Inspectability. The source code, skills, connector definitions, tool activity, and generated files are available for review.
• Extensibility. Add skills and MCP connectors instead of waiting for a closed plugin roadmap.
• No seat license. Open Science is Apache-2.0 software. You pay only for the model or infrastructure you choose to use.

Open Science is an independent product built from scratch. It is not a proxy, unofficial client, or reskin of another AI research application.

Vision

Our goal is to make the AI research workbench a piece of open infrastructure rather than a rented product surface. A student with a laptop, a lab using a regional model provider, and an institution running its own gateway should be able to use the same research workspace while keeping control of their models, tools, and data boundaries.

The long-term destination is a traceable loop connecting literature, data, computation, artifacts, review, and reusable scientific skills. The released desktop app is the working foundation for that direction, not a placeholder for a future concept.

Design Principles

• Open by default. Source code, formats, connectors, and skills should remain inspectable and forkable.
• Multi-provider with explicit compatibility. The app validates provider configuration and makes endpoint requirements visible instead of treating every API protocol as interchangeable.
• Local-first and data-aware. Keep project state local, surface external data flows, and make autonomy opt-in.
• Human-in-the-loop. File edits, commands, network access, and connector calls are governed by explicit approval profiles.
• Durable research records. Sessions, tool activity, files, and Notebook history should remain reviewable after the run ends.
• Composable capabilities. Skills, connectors, models, previews, and future compute backends should be replaceable parts rather than one black box.
• Honest scientific boundaries. Generated output does not replace expert judgment, statistical review, or validation against primary evidence.

Core Capabilities

This section describes durable product capabilities rather than a version-specific inventory. The installed app and latest release notes are the source of truth for changing catalogs, packaging details, and newly added options.

| Area | Core capability | | ---------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Projects and sessions | Create, rename, and delete projects; maintain multiple sessions; restore recent work, drafts, conversation history, and preview state. | | Agent workflow | Natural-language tasks, streamed responses, typed tool-activity cards, stop controls, approval pauses, and recovery of sessions interrupted by an application restart. | | Models | Built-in cloud providers, custom compatible gateways, Local Claude, connection validation, and model selection per session. | | Agent backend | A selectable agent-framework backend so the same workspace can run on more than one underlying agent implementation, with provider and model choices validated against the selected backend, and app-managed backends installable, switchable, and removable from Settings. | | Execution | A persistent Python Notebook kernel with durable code/output history and a user terminal shared with the agent. | | Inputs and artifacts | File attachments, project-level file library, generated artifact cards, @ references to existing uploads/outputs, and read-only multi-tab previews. | | Preview formats | Common scientific data, documents, images, source code, molecular structures and reactions, and Notebook history. | | Local data management | Local project and application data, configurable storage location, and guided migration. | | Skills | Featured and personal skills, package upload, GitHub preview/import, enable/disable controls, and explicit / selection in a session. | | Connectors | Built-in life-science connectors, custom local/remote MCP connectors, contact metadata, and connector/tool-level permissions. | | Safety controls | Ask for approval, Auto-approve edits, and Full access conversation profiles, plus per-connector and per-tool policies.

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: aipoch
• Source: aipoch/open-science
• License: Apache-2.0
• Homepage: https://www.aipoch.com/open-science

Install and usage instructions live in the source repository linked above.