AIPOCH Open-Science

AI research workbench for reproducible science — open-source, local-first, and model-agnostic.

AIPOCH Open-Science is an AI research workbench for scientists and researchers, developed by AIPOCH with an open-source, local-first, model-agnostic approach. It enables reproducible, inspectable research with scientific AI agents, Python and R execution, scientific data connectors, and cross-platform support for macOS, Windows, and Linux. Create a project, describe your research goal in plain language, and let the agents read files, search the web, run code, query scientific data sources, and produce reports, tables, and figures with traceable provenance—all in one workspace.

AIPOCH Open-Science supports computational and data-intensive research across disciplines, including machine learning, statistics, life sciences, chemistry, materials science, physics and environmental science. It supports the research process from literature review and hypothesis development to code execution, data analysis, simulation, visualization, and the production of traceable research outputs.

Completed research sessions can also be exported as portable .science packages for review, handoff, and archiving, with selected conversation branches, file versions, Notebook records, and verification evidence.

💡 AIPOCH Open-Science v1.0.1 _(updated October 2026)_. This patch adds one-click .science package imports from your browser, a clearer and more reliable in-app updater (especially on Windows), always-visible session wait states, security fixes for MCP OAuth credential handling, and a round of PDF, literature, and session-package fixes. See the 1.0.1 release notes for details. Downloads continue to follow the latest published release.

Table of Contents

• Quick Start
• Product Tour
• AIPOCH Open-Science .science Research Packages
• AIPOCH Open-Science Paper and Citation
• Benchmark Performance
• Core Capabilities
• Model Providers
• Data, Permissions, and Trust
• Development & Packaging
• Frequently Asked Questions
• Get Involved
• License
• Star History

🚀 Quick Start

1. Download the app

Open the official download page and choose the installer for your computer:

| Your computer | Choose | | --------------------------------------- | ------------------------------------------ | | macOS 12+ — Apple Silicon (M1 or newer) | The macOS DMG for Apple Silicon / ARM64 | | macOS 12+ — Intel | The macOS DMG for Intel / x64 | | Windows x64 | The Windows x64 installer (code-signed) | | Linux x64 | The Linux x64 AppImage or Debian package | | Linux ARM64 | The Linux ARM64 AppImage or Debian package |

Download from the official download page; see download verification if needed.

On macOS, you can also install with Homebrew:

brew install --cask open-science

For the standalone CLI on macOS or Linux, use the separate AIPOCH tap:

brew install aipoch/tap/open-science

This Formula includes Node and runs without the desktop app; its release may differ from the desktop Cask. See the standalone runtime guide for prerequisites and upgrades.

For the standalone CLI and Web UI, install the published npm package with Node.js 22.13.0 or later:

npm install --global @aipoch/open-science
open-science start --no-open
open-science url

Open the printed URL to complete setup, or follow the terminal setup guide. npm supports macOS ARM64/x64, glibc Linux ARM64/x64 and Windows x64; the desktop app is not required. Keep npm optional dependencies enabled and review the Linux prerequisites and upgrade instructions. The URL contains an authentication token; keep it private.

Windows reinstalls preserve research data. For a full cleanup, see the data reset tool, which permanently deletes local data after confirmation.

2. Complete first-time setup

Follow the setup wizard: Environment → Data location → Agent runtime → Model provider → Notebook runtime.

Complete the required environment and agent-runtime checks and test your model connection. Python/R Notebook setup is optional; Notebook and data-location settings can be changed later.

Host compatibility, storage, and network checks	Provider, API Key, endpoint, and model validation

3. Start a research project

1. Click New project, open a session, and describe your research goal, inputs, and expected outputs.
2. Attach files, select a model and approval mode, then send the task. Use @ to reference project files or / to choose a skill.
3. Review tool activity and any approval requests, preview the results, and check their available evidence in Provenance.

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

Product Tour

From a research request to a traceable result

Consider a representative bioinformatics task: reproduce a published differential-expression analysis, compare the regenerated results with the paper, and deliver the report, tables, and figures needed for review. The screenshots below are representative views from documented AIPOCH Open-Science workflows; they illustrate each stage rather than one continuous session.

1. Define the research task and evidence

Describe the research question, source paper and datasets, required methods or thresholds, expected outputs, and acceptance criteria. Upload supporting files or reference an existing project artifact with @, so the agent starts from explicit inputs instead of hidden context.

2. Execute with inspectable scientific tools

The agent can combine scientific skills, permissioned research connectors, searches, file operations, and Python or R code in the shared Notebook. Generated figures can be reviewed beside the research summary, while the artifact record exposes captured producer code and execution evidence for inspection.

3. Review reports, tables, and figures in place

The final response summarizes what reproduced, what differed, and which limitations matter. Generated Markdown reports, CSV tables, images, and other research artifacts remain attached to the session and are collected in the project file library, where they can be previewed beside the conversation and reused in follow-up work.

4. Trace every artifact back to its evidence

Each generated artifact is stored as an immutable, checksummed version. Its Provenance view can expose the producing code and execution history, referenced inputs, observed environment inventory, producing conversation branch, and version-scoped Reviewer findings. Evidence that could not be verified is marked unavailable rather than inferred.

AIPOCH Open-Science .science Research Packages

Export a completed research session as a portable .science package for review, handoff, and archiving. Choose the conversation branches, file versions, Notebook records, and verification evidence to include, then import the package into another project or computer.

Export → transfer → inspect

1. Export a completed session and choose the contents to include.
2. Move the .science file to a collaborator or another computer.
3. Import it into a project. The right-hand Research replay shows the recorded process; the left-hand conversation lets you ask about it and follow fixed step references.

Side Chat conversations, private reading bookmarks, and credentials are excluded; included files depend on export selection. Received verification records describe the sender’s checks, not a rerun on this computer. See the .science package guide.

AIPOCH Open-Science Paper and Citation

AIPOCH Open-Science: An Open-Source AI Research Workbench with Reproducible .science Packages

arXiv preprint · v1 · Submitted October 12, 2026.

Our preprint introduces AIPOCH Open-Science, an open-source AI research workbench with portable .science packages for sharing research context, artifact versions, and verification records. Read the paper for the package exchange design and controlled evaluation.

If you use AIPOCH Open-Science in your research, you can cite the preprint:

@misc{ouyang2026aipochopenscienceopensourceai,
      title={AIPOCH Open-Science: An Open-Source AI Research Workbench with Reproducible .science Packages},
      author={Wen Ouyang and Bocheng Huang and Qianyu Yao and Fei Sun and Minying Deng and Haoyue Cheng and Wenwen Zhou and Lei Mou and Yusi Wei and Jiang Li and Kun Zhu and Lei Wang and Yi Feng and Jiaheng Dai and Ke Qian and Dan Wang and Yahui Wang and Chenyi Wang and Mingsheng Lyu and Yaqiang Zhang and Ping Zheng and Chunhua Tang and Xinge Ma and Xu Zhang and Youjia Fan and Can Lu and Zhijun Dai and Man Hu and Qiqi Xie and Beinan Liu and Yuanning Guo and Yunze Liu and Jinhong Jiang and Xianjun Fu and Mingwei Zhang and Yuanji Xu and Shilin Xia and Bowen Yang and Mingjun Yu and Jingdun Xie and Xuwei Chen and Xia Zou and Yuzhou Xue and Jianguo Zhou and Chunhao Cao and Donghao Tian and Lei Huang and Jinxiao Li and Shengrong Long and Zefeng Song and Honglin Li and Jiang Luo and Wenying Jiang and Shanshan Li and Lei Dai and Ning Jiang and Ying Cai and Chaohui Li and Chunyan Peng and Hetong Zhao and Angqing Li and Chunyan Yang and Chongyang Sun and Yong Li and Xinyu Shi and Wei Dai and Ming Peng and Chen Sang and Yuanyuan Han and Desong Qiu and Haixin Miao and Jian Xu and Yi Chen and Xiaoliang Shi and Tian Shen and Teng Hu and Shuhao Wang and Yingyong Hou and Huimei Wang},
      year={2026},
      eprint={2610.17110},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2610.17110},
}

Benchmark Performance

These results are historical reports from August–October 2026, not a new evaluation of v1.0.0.

Source reports: September 29, October 12 (access may be required).

🏆 AstaBench LitQA2-FullText-Search — 10/10 target-paper hits

AIPOCH Open-Science achieved 100% recall@30 on the official 10-query validation split using DeepSeek v4-flash (max) with literature-retrieval specialists and Skills. Every target paper appeared among the first 30 returned results. The score exceeds the three public validation results listed in the report, 20 percentage points above the highest reference of 80%. Three local repeats were reported, demonstrating target-paper retrieval on this set of scientific questions.

!AIPOCH Open-Science achieves 100% recall@30 and 10/10 target-paper hits on AstaBench LitQA2-FullText-Search validation; test and validation records use different questions

The figure includes both test and validation records; its ordering is numerical only. Recall@30 measures target-paper retrieval, not scientific question-answering accuracy.

🏆 ASI-Bench B1–B4 — Highest displayed scores in all four listed comparisons

AIPOCH Open-Science scored 79.35, 56.11, 59.67, and 59.46 on ASI-Bench B1, B2, B3, and B4 using GPT-6 (gpt-6-astra / xhigh) with domain specialists and Skills, the highest displayed values in the respective comparisons retained in the reports. The four conditions evaluate executing a fully specified plan, organizing a workflow, selecting research methods independently, and conducting autonomous research with distracting background information.

The same-model local Codex references scored 74.78, 56.09, 58.12, and 55.45, giving numerical differences of +4.57, +0.02, +1.55, and +4.01 points, respectively. Three local repeats were reported for B1/B2; B3/B4 each average three local runs of 60 tasks.

!AIPOCH Open-Science scores 79.35, 56.11, 59.67, and 59.46 on ASI-Bench B1–B4; the chart distinguishes local results from published references

Local runs used seed31415. AIPOCH's B1 score covers 59 tasks, with one excluded due to the scorer issue described in the report. B3/B4 used v0.32.0 and a substitute judge. Published references differ in task instances, configurations, and judging; B2's 0.02-point margin is a numerical difference only.

🏆 Highest in the collected BiomniBench-DA Public 50 comparison — 79.05

AIPOCH Open-Science achieved 79.05 with gpt-5.6-sol (xhigh) in an internal evaluation on the 50-task set labeled BiomniBench-DA Public 50, the highest displayed score in the collected comparison. The result combines 81.04 from the Gemini 3.1 Pro judge and 77.06 from the DeepSeek v4-pro judge through an equal-weight mean, reflecting this configuration's biomedical data-analysis performance. See the evaluation report.

!AIPOCH Open-Science records a 79.05 dual-judge mean on the internal BiomniBench-DA Public 50 evaluation, combining judge scores of 77.06 and 81.04

The comparison mixes different judge-coverage patterns and should not be interpreted as an official ranking under uniform judging conditions.

Evaluation scope: These are self-reported local/internal results. Leading the listed comparisons does not establish official first-place leaderboard status or statistically significant improvements.

Core Capabilities

AIPOCH Open-Science combines project management, multi-model agent execution, Python and R notebooks, scientific data connectors, immutable artifact versions with provenance, and permissioned human-in-the-loop control in one local workspace. The installed app and latest release notes are the source of truth for changing catalogs, packaging details, and newly added options.

| Area | Core capability | | --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Scientific skills | Extend research workflows with 23 built-in skills and 525 skills available from the Skills Marketplace, with one-click installation and updates. Create skills through conversation or completed work, and import packages or GitHub sources. Marketplace contributions are published after review; local imports do not publish skills. | | Connectors | Access scientific resources through 36 built-in connectors, or add custom local and remote MCP connectors. Manage tool-level permissions and import or export connector configurations. | | Specialists and delegation | Install 10 Specialists from the Specialist Marketplace, or create and customize personal specialists for delegation from the main agent. Specialist packages support import and export; marketplace contributions are reviewed before publication, and local imports do not publish them. | | Models and agent backends | Use cloud models, compatible custom gateways, or Claude and Codex subscription logins. Choose Claude Code, OpenCode, Codex, or CodeBuddy as the agent backend, with model connection checks, image input, and reasoning controls. | | Projects, sessions, and research packages | Organize projects with pinned sessions, message branches, side chats, and recoverable history. Export a portable .science research package and import it into another project or computer with conversation branches, selected file versions, Notebook records, and verification evidence. Imports are read-only and do not execute code or restore credentials; side chats and bookmarks are excluded, and included files depend on the export selection. | | Reviewer | Enable optional auto-review to check a completed agent turn's responses, execution logs, and related file evidence in a separate context. Get evidence-backed pass, warning, or failure checks, with a bounded cycle of main-agent corrections and re-review when issues are found. Review logs and issue-resolution states remain available; the review is limited to records available for that turn. | | Python, R, notebooks, and HPC | Run Python, R, Notebook, and shell workloads locally using managed environments or your own interpreters, with background execution and recorded history. Connect to remote hosts through SSH or submit work through Slurm; remote workloads require the host, software, resources, and permissions described in the remote-compute FAQ. | | Literature Library | Import and manage references and PDFs with collections, tags, project links, notes, and duplicate merging. Find open-access full text, read PDFs and extract figures and tables, and use library sources in conversations for AI-assisted analysis. Generate bibliographies in your chosen citation style and export references as BibTeX or RIS. | | Scientific files and previews | Upload individual files up to 10 GiB, organize project files, and preview scientific data, PDFs, Office documents, images, code, and molecular structures. This upload limit does not guarantee that a model can read an entire file: model context, attachment parsing, and previews have separate limits. Large files usually need chunked reading or analysis with code. | | Artifacts and provenance | Keep immutable artifact versions with available producer code, inputs, execution history, environment information, and review evidence. In the desktop app, replay eligible versions with a complete recipe, required inputs, and a usable runtime, then compare outputs and export verification records. Missing evidence may prevent verification, and replay checks do not establish scientific validity. |

Persistent PDF annotations and document notes are available. With a screening model configured, smart collections evaluate references against your inclusion/exclusion criteria; AI decisions remain separate from manual decisions and support human review.

In the desktop app, artifact provenance can also be exported as RO-Crate 1.1. A version-bound environment bundle can create a managed environment only when the captured bundle is complete and compatible with the target platform; this is separate from a full machine backup.

Model Providers

AIPOCH Open-Science is model-agnostic at the product level: connect it to major cloud LLM providers, a custom gateway, or reuse an existing Claude or Codex subscription. Provider availability currently depends on the selected agent backend and the API protocols it supports. The following connection options are available:

| Provider mode | How it works | | ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Built-in cloud providers | Choose from the provider list shown by the installed app and authenticate with the requested key. | | Custom Gateway | Supply a Base URL and exact model ID with an API protocol supported by the selected agent backend (Messages, Chat Completions, or Responses), then run the connection test. Remote gateways require HTTPS and an API Key. Loopback endpoints such as localhost, 127.0.0.1, or [::1] may use HTTP without a key; presets include Ollama, LM Studio, llama.cpp, and vLLM. A default API format does not guarantee server or model compatibility. | | Codex Subscription | Select the Codex agent framework, then choose Codex Subscription as the provider type. | | Claude Subscription | Sign in with a Claude subscription in two modes: shared (a browser login that stores credentials in your default ~/.claude profile) or isolated (an app-managed claude setup-token run under an app-owned CLAUDE_CONFIG_DIR, fully isolated from ~/.claude/, with a browser flow plus a paste-a-token fallback). | | xAI (Grok) OAuth | Use the built-in xAI (Grok) OAuth device sign-in. Access depends on your xAI account and the selected backend’s protocol support; validate the connection in the app. |

There are 25 preset provider options, including OpenAI, Anthropic, DeepSeek, NVIDIA Build, and others; available models and regional endpoints depend on the installed version and selected agent backend. Check the provider selector and connection test in the app.

Data, Permissions, and Trust

AIPOCH Open-Science stores project data, settings, artifact versions, and provenance evidence on the local computer. API Keys are kept locally and use the operating system's secure credential storage when it is available. Logs are local and are not uploaded automatically.

External data flow is still possible and should be reviewed:

• Model requests send the prompt and necessary context to the selected model provider.
• Web searches and remote connectors send their displayed parameters to external services.
• Local connectors may execute trusted commands on the computer.
• The application can also contact update servers, marketplace catalogs, and runtime or model download services.
• Attachments, @ references, logs, and generated reports may contain sensitive research data.

| Mode | Behavior | Recommended use | | -------------------- | -------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- | | Ask for approval | Requests approval for actions not already covered by scoped grants or trusted application tool policies | New workflows, sensitive data, unfamiliar scripts | | Auto-approve edits | Uses the backend's native auto review when available; otherwise automatically allows clearly low-risk workspace operations | Trusted file-editing work with controlled external access | | Full access | Automatically allows edits, commands, network, and connectors | Clearly scoped, fully trusted, unattended work |

The effective profile depends on the selected backend and existing grants. Connector, tool, and compute-network policies also apply; check the effective mode shown by the app.

Review connector parameters and tool activity before approving them. Never include API Keys, access tokens, patient identifiers, unpublished data, or sensitive local paths in screenshots or public issue logs.

Development & Packaging

AIPOCH Open-Science has an ordinary Node backend and an Electron desktop client, built with React, TypeScript, Prisma/SQLite, and an ACP-based agent runtime.

Prerequisites for source development:

• Node.js 24 (see .nvmrc) with npm
• Git
• Notebook execution optionally uses app-managed Python/R environments or a compatible interpreter you configure.

git clone https://github.com/aipoch/open-science.git
cd open-science
npm install
npm run dev

See the development command and packaging reference and contribution guide for build commands and the development workflow.

Localhost Web and standalone Node runtime

The same Web UI can run on an ordinary Node backend without Electron or a graphical display. Electron starts or attaches to that same Node service. One runtime owns each data directory.

npm run dev:web       # Build and run the Node backend + Web UI
npm run pack:backend  # Build a target-specific standalone npm tarball

For a published installation, use npm install --global @aipoch/open-science; the commands above are for source development. Install the package or locally built tarball, then run open-science start --no-open and open-science url to open the existing UI. See the standalone runtime guide for installation, secure credential storage, host capability boundaries and data compatibility. The desktop app and browser share that service. Quitting a desktop stops a server it started; quitting a desktop attached to a CLI-started server only disconnects the desktop.

Mobile remote access

The same localhost web UI can be reached from a phone or tablet through Remote.It pairing. Pair a browser with a six-digit AIPOCH Open-Science code, approve it once on the desktop, and the workspace stays reachable without exposing the loopback server directly. Browser trust is revocable, and mode changes or service shutdown immediately invalidate active remote sessions.

Remote access requires the host to stay on and online, with AIPOCH Open-Science and the Remote.It agent running, and the host added to a signed-in Remote.It account. Browser approval has an expiry and can be revoked; see the Remote control guide.

Headless CLI and SDK

The headless CLI and zero-dependency Node.js SDK use the same local daemon, projects, sessions, credentials, and permissions as the desktop and web interfaces. Detailed usage lives with the publishable package so there is one command reference to maintain:

• CLI guide - installation, service lifecycle, task automation,

• SDK package overview - Node.js quick start and package entry point

Frequently Asked Questions

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 a Claude subscription, retry the shared browser login or refresh the isolated claude setup-token credential, depending on the selected mode.

Why is Continue disabled during setup?

A: The current step has not met its required condition. Fix any environment row marked Action needed, install or repair the selected agent runtime, or validate the model provider, depending on the active step. Notebook setup is optional and only affects Notebook execution.

How do I run jobs on a remote HPC cluster?

A: Remote Compute (SSH) is always enabled and does not need to be enabled in Settings. Register an SSH compute host under Settings → Compute, make it available to the current session, and then use natural language or /remote-compute-ssh. You need a reachable SSH host, valid authentication, permission for the required directories, and the software, dependencies, and compute resources required by the workload. Direct SSH does not require a scheduler; Slurm mode requires a working Slurm environment and permission to submit jobs. “Always enabled” refers to the skill, not to the availability of every registered host.

Is there a command-line interface?

A: Yes. Install the standalone Node package, or use Settings → General → Command line tool → Install command to control an already running desktop instance. For independent startup, use the standalone package and ordinary Node. The Debian package-owned launcher is an exception: it starts the bundled backend with the bundled Node runtime. Initialize the local profile, then control the service and submit research tasks without opening a browser:

# Initialize the local CLI profile and start the service in the background
open-science init
open-science start --no-open
Create a project and run a task by its exact name
open-science project create "Systematic review"
open-science run --project "Systematic review" \
  --prompt-file ./task.md \
  --approval-profile auto \
  --skill literature-review \
  --wait --json
Download a generated artifact
open-science artifacts list <session-id> --json
open-science artifacts download <artifact-id> --output ./report.md

See the CLI guide for the full command reference, JSON/JSONL output formats, exit codes, and headless service options.

How do I inspect where a generated result came from?

A: Open the generated artifact and choose Provenance. Select a version to inspect the content identity and the available producer code, execution history, inputs, environment inventory, producing conversation context, and reviewer evidence. Evidence AIPOCH Open-Science could not verify is marked unavailable.

Can I revise an earlier request without losing the conversation that followed?

A: Yes. Edit a completed user message and resend it to create a new branch from that point. The original later turns remain available, and the revision arrows beside the message switch between the alternative paths.

Get Involved

AIPOCH Open-Science welcomes bug reports, feature proposals, design discussions, community questions, and contributions through GitHub, Discord, X, and the AIPOCH website. Choose the channel that best matches your goal, then follow the linked contribution guidance and public-posting safety reminder before sharing project details.

| Channel | Use it for | | ------------------------------------------------------------------------ | ----------------------------------------------------------------------- | | GitHub Issues | Bugs, reproducible failures, and concrete feature proposals | | GitHub Discussions | Design questions, roadmap proposals, and longer technical conversations | | Discord | Community help, contributor coordination, and informal discussion | | X / @aipoch_ai | Release announcements and build-in-public updates | | AIPOCH Open-Science website | Official product overview and downloads |

Before opening a public issue, remove API Keys, tokens, private file paths, unpublished data, patient identifiers, and other sensitive material from logs and screenshots. See CONTRIBUTING.md for the development workflow.

⭐ 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.

For remote access setup, see the Remote control guide.

For shipped, partial, and planned capabilities, see the Capability Map.

License

Apache License 2.0 — see LICENSE.

Star History