# aipoch/open-science

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/aipoch-open-science).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

5,490 stars · 552 forks · TypeScript · Apache-2.0

## Links

- GitHub: https://github.com/aipoch/open-science
- Homepage: https://aipoch.com/open-science
- awesome-repositories: https://awesome-repositories.com/repository/aipoch-open-science.md

## Topics

`agent-skills` `ai-agent` `ai-for-science` `ai-research` `ai-research-workbench` `ai-workbench` `desktop-app` `local-first` `mcp` `model-agnostic` `open-science` `open-source` `reproducible-research` `research-tools` `science` `science-agent` `science-package` `scientific-ai` `scientific-computing` `scientific-research`

## Description

Open Science is a local-first AI research workbench in which agents plan and run multi-step scientific tasks on the user's own computer, with results that can be traced back to their code, inputs and environment. Questions, papers or data files given in plain language are worked through by agents that call tools, execute Python and R code in notebook-style cells, and hand tasks to specialist subagents. A separate review context checks each finished turn against replies, execution records and file evidence, and triggers bounded corrections when it finds problems.

What sets it apart is the combination of reproducibility tracking and an open agent platform. Artifacts are stored as immutable versions with their generating code, inputs and environment inventory, can be replayed in isolation to verify outputs, and can be exported as RO-Crate packages. Sessions can also be shared as portable research packages that others replay without running code or calling models. Agents are extended with installable skill packages and MCP tool connectors, and they can run on cloud providers, custom OpenAI-compatible gateways, local model servers, or existing Claude and Codex subscriptions. Python and R code can also be dispatched to remote clusters over SSH or Slurm.

Around that core sits a literature library for importing papers by identifier or link, bringing in Zotero collections, annotating and translating PDFs, running offline OCR, and screening papers against inclusion criteria with AI and human decisions recorded separately. Work is organized into projects and sessions with branches, forks and review-gated plans, and agent permission profiles together with network destination approval control what agents may do. Project data and credentials stay on the local machine.

The same local service backs a desktop app for macOS, Windows and Linux, a browser interface, a headless command-line tool, a dependency-free Node.js SDK, and an MCP server for external AI clients. The command-line tool is distributed through npm, Homebrew, native Linux packages and standalone archives.

## Tags

### Artificial Intelligence & ML

- [AI Research Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-research-tools.md) — A local-first workbench where AI agents plan, run and review scientific research tasks on the user's own computer with traceable results.
- [Research Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/ai-agents/research-agents.md) — Runs multi-step research agents that plan tasks, call tools, and work through questions, papers, or data files on the user's own machine. ([source](https://github.com/aipoch/open-science/tree/main/packages))
- [Scientific Research Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-ai-agent-frameworks/scientific-research-platforms.md) — Offers an extensible research agent platform with installable skills, specialist subagents and MCP connectors, usable from desktop, browser, CLI or SDK.
- [Custom Agent Provider Connections](https://awesome-repositories.com/f/artificial-intelligence-ml/external-server-connectivity/server-connection-managers/custom-server-connections/custom-agent-provider-connections.md) — Connects cloud providers, custom compatible gateways, local model servers, or existing Claude and Codex subscriptions and verifies each with a built-in test. ([source](https://github.com/aipoch/open-science/blob/main/docs/ru/README.md))
- [Workflow Reproducibility](https://awesome-repositories.com/f/artificial-intelligence-ml/research-papers/research-reproductions/workflow-reproducibility.md) — Traces every result back to its code, inputs and environment, then replays, verifies or shares it as a portable package.
- [Agent Backend Selection](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-backend-selection.md) — Runs work through a choice of agent backends with image input and adjustable reasoning effort in one workspace. ([source](https://github.com/aipoch/open-science/blob/main/docs/zh-Hant/README.md))
- [Agent Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-delegation.md) — Lets the main agent hand tasks to installed or user-created specialist agents and subagents, shared through a reviewed marketplace. ([source](https://github.com/aipoch/open-science/blob/main/docs/ja/README.md))
- [Agent Review Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-review-pipelines.md) — Checks each finished agent turn in a separate review context and triggers bounded corrections with re-review when problems are found. ([source](https://github.com/aipoch/open-science#readme))
- [Provider-Agnostic Adapters](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-llm-frameworks/provider-agnostic-adapters.md) — Runs the same agent workflows across cloud providers, custom OpenAI-compatible gateways, local model servers and Claude or Codex subscriptions.
- [Skill Installation](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-skill-frameworks/skill-installation.md) — Extends agents with built-in and marketplace skills installed or updated in one click, plus skills created from conversations or imported from packages and GitHub. ([source](https://github.com/aipoch/open-science/blob/main/docs/ru/README.md))
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Connects cloud providers, OpenAI-compatible gateways, local model servers and existing subscriptions so users choose the model and agent backend.
- [Model Context Protocol](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/model-context-protocol.md) — Connects external tools and data connectors to agents via the Model Context Protocol and serves research tools outward to third-party clients.
- [MCP Tool Connectors](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-tool-connectors.md) — Links to outside MCP tool servers so agents can call additional data sources and services. ([source](https://github.com/aipoch/open-science/tree/main/packages))
- [Provenance Packaging](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-provenance-tracking/data-lifecycle-provenance/provenance-packaging.md) — Exports an artifact's provenance as an RO-Crate 1.1 package and rebuilds managed environments from complete, compatible environment bundles. ([source](https://github.com/aipoch/open-science/blob/main/docs/ja/README.md))

### Part of an Awesome List

- [Artifact Provenance Management](https://awesome-repositories.com/f/awesome-lists/productivity/reproducible-research/artifact-provenance-management.md) — Stores immutable artifact versions with generating code, inputs, and environment inventory, enabling isolated replay and RO-Crate export for reproducibility.

### Development Tools & Productivity

- [Notebook Execution Environments](https://awesome-repositories.com/f/development-tools-productivity/code-execution-environments/notebook-execution-environments.md) — Executes Python, R, notebook and shell code in managed or custom environments with background runs, saved history and SSH or Slurm compute.
- [Desktop and CLI Distribution Channels](https://awesome-repositories.com/f/development-tools-productivity/desktop-and-cli-distribution-channels.md) — Delivers signed desktop installers with auto-update alongside a localhost web interface, headless CLI, SDK, mobile access, and translated interfaces. ([source](https://github.com/aipoch/open-science/blob/main/docs/ROADMAP.md))
- [Headless CLI and SDK Clients](https://awesome-repositories.com/f/development-tools-productivity/headless-cli-and-sdk-clients.md) — Provides a headless command-line tool and dependency-free Node.js SDK sharing the same local service, projects, sessions, and permissions as the desktop app. ([source](https://github.com/aipoch/open-science/blob/main/docs/ja/README.md))
- [Headless Service Scripting](https://awesome-repositories.com/f/development-tools-productivity/headless-service-scripting.md) — Drives projects, agent runs and results without a desktop window through a command line, Node.js SDK or external MCP clients.
- [Parallel Branches and Review-Gated Plans](https://awesome-repositories.com/f/development-tools-productivity/parallel-branches-and-review-gated-plans.md) — Supports conversation branches, writable forks, side chats, queued messages, and review-gated plans so work can be explored in parallel and approved first. ([source](https://github.com/aipoch/open-science/blob/main/docs/ROADMAP.md))

### Programming Languages & Runtimes

- [Notebook Code Execution](https://awesome-repositories.com/f/programming-languages-runtimes/multi-language-script-execution/notebook-code-execution.md) — Runs Python, R, notebook, and shell code locally in managed or custom environments with background execution, saved history, and remote SSH or Slurm dispatch. ([source](https://github.com/aipoch/open-science#readme))

### Scientific & Mathematical Computing

- [Artifact Replay Verification](https://awesome-repositories.com/f/scientific-mathematical-computing/artifact-replay-verification.md) — Reruns eligible artifact versions in isolation from their full recipe, inputs and environment, compares outputs, and exports verification records as reproducibility evidence. ([source](https://github.com/aipoch/open-science/blob/main/docs/zh-Hant/README.md))
- [Inclusion Criteria Screeners](https://awesome-repositories.com/f/scientific-mathematical-computing/automated-literature-reviewers/inclusion-criteria-screeners.md) — Screens papers against inclusion and exclusion criteria with a configured model while keeping AI and manual decisions recorded separately for human review. ([source](https://github.com/aipoch/open-science/blob/main/docs/ja/README.md))
- [Literature Collectors](https://awesome-repositories.com/f/scientific-mathematical-computing/automated-literature-reviewers/literature-collectors.md) — Searches scholarly sources and collects relevant studies for a research question so candidate papers can be screened. ([source](https://github.com/aipoch/open-science/tree/main/packages))
- [Literature Screening and Reference Management](https://awesome-repositories.com/f/scientific-mathematical-computing/literature-screening-and-reference-management.md) — Imports, annotates, translates and screens scholarly papers against inclusion criteria, then organizes references and exports citations.
- [Research Package Replay](https://awesome-repositories.com/f/scientific-mathematical-computing/research-package-replay.md) — Loads a research package into another project or computer as a read-only record replayable step by step without running code, calling models or restoring credentials. ([source](https://github.com/aipoch/open-science/blob/main/docs/ja/README.md))

### Software Engineering & Architecture

- [Local-First Architectures](https://awesome-repositories.com/f/software-engineering-architecture/local-first-architectures.md) — Keeps project data, credentials, and artifact history on the user's machine, with the desktop app running all logic locally.
- [Multi-Kernel Code Execution](https://awesome-repositories.com/f/software-engineering-architecture/code-execution-engines/multi-kernel-code-execution.md) — Runs Python and R code through notebook-style kernels in managed or user-supplied interpreters, with background execution and remote dispatch over SSH or Slurm.
- [Agent Skill Packages](https://awesome-repositories.com/f/software-engineering-architecture/software-architecture/architectural-patterns/plugin-module-systems/modular-plugin-architectures/plugin-based-architectures/plugin-based-architectures/agent-skill-packages.md) — Defines agent abilities as installable file bundles that can be imported, versioned, and delegated to subagents without changing the core application.

### Data & Databases

- [Notebook Cell Execution](https://awesome-repositories.com/f/data-databases/horizontal-database-scaling/multi-region-scaling/cell-based-scaling/notebook-cell-execution.md) — Executes Python and R code in notebook-style cells so analysis steps run and produce results within the research workflow. ([source](https://github.com/aipoch/open-science/tree/main/packages))
- [Python Data Analysis](https://awesome-repositories.com/f/data-databases/python-data-analysis.md) — Runs Python and R code in notebook-style cells locally or on SSH and Slurm clusters to analyze scientific data with saved history.
- [Research Data Sharing Frameworks](https://awesome-repositories.com/f/data-databases/research-data-sharing-frameworks.md) — Saves a completed session as a portable package with chosen conversation branches, file versions, notebook records and verification evidence for review, handoff or archiving. ([source](https://github.com/aipoch/open-science/blob/main/docs/ja/README.md))

### Security & Cryptography

- [Local Data Storage](https://awesome-repositories.com/f/security-cryptography/local-data-storage.md) — Keeps project data, settings, artifact versions, provenance and credentials on the local machine, protecting keys with the operating system's secure store. ([source](https://github.com/aipoch/open-science/blob/main/docs/de/README.md))
- [AI Agent Permissions](https://awesome-repositories.com/f/security-cryptography/permission-based-access-control/ai-agent-permissions.md) — Limits what agents may edit, run or send over the network through approval, auto-approve-edits or full-access profiles with scoped grants and approved folders. ([source](https://github.com/aipoch/open-science/blob/main/docs/zh-Hant/README.md))

### System Administration & Monitoring

- [Headless Local Services](https://awesome-repositories.com/f/system-administration-monitoring/headless-local-services.md) — Runs as a background service reachable through an authenticated browser, CLI, or SDK with no desktop window, sharing projects and permissions. ([source](https://github.com/aipoch/open-science/blob/main/docs/standalone-runtime.md))
