OpenScience: Open-Source AI Workbench for Scientific Research
Give it a goal — it reads the literature, writes and runs code, runs experiments, and writes up the findings.
- Source repo
- synthetic-sciences/openscience
- Stars
- ★ 4.1k
- Last updated
- today
- License
- Apache-2.0
- Primary language
- TypeScript
- FA score
- 45/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- ML researchers quickly exploring new ideas, letting the agent handle literature review and initial experiments.
- Not a fit if
- Teams needing a full jail for hostile code; the sandbox is not one
- Teams on CentOS 7 or other 3.10-kernel hosts
- Users who want no per-provider API keys or accounts to manage
- Source review
- 45/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
OpenScience is an open-source AI workbench for scientific research, providing a complete research environment within a browser. It integrates literature retrieval, code execution, experiment running, and paper writing. It is model-agnostic, supporting Anthropic, OpenAI, Google, and many other providers via your own API keys, with no account required. It includes specialized agents for research, biology, physics, and ML, plus 290+ skills covering training, evaluation, datasets, molecular biology, cheminformatics, and cloud compute. Optional Atlas managed platform adds curated models, a research graph, and cloud compute.
Users set a research goal in the browser workspace; the agent autonomously works through the research loop: reading relevant literature (via UniProt, PDB, Ensembl, ChEMBL, PubChem, arXiv, OpenAlex, etc.), forming hypotheses, writing and running code (using shell, editor, LSP, MCP servers, and other tools), running experiments on real compute, and writing up the result. It is extensible with custom agents, commands, tools, plugins, and a TypeScript SDK.
- ML researchers quickly exploring new ideas, letting the agent handle literature review and initial experiments.
- Biology researchers querying UniProt, PDB, and other databases and running molecular analyses.
- Physics or chemistry researchers using the agent for data analysis and simulation.
- Research teams comparing results across multiple providers (Anthropic, OpenAI, Google).
- Developers integrating the agent into existing workflows via the TypeScript SDK and MCP support.
How do you install or deploy this agent?
- Ensure Node.js and Bun 1.3+ are installed. 2. Install globally via npm:
npm install -g @synsci/openscience. 3. Runopenscienceto open the workspace in your browser.
How do you use this agent?
- Set an API key from a provider, e.g.,
export ANTHROPIC_API_KEY=sk-ant-.... 2. Runopenscienceto start. 3. Select a model from the model selector, and optionally specify a project directory:openscience ~/code/my-project. 4. Set a research goal; the agent will execute the research process.
What are this agent's strengths and limitations?
- Model-agnostic, supporting multiple providers with your own keys, no account needed.
- Built-in scientific database connectors (UniProt, PDB, ChEMBL, etc.) for direct querying.
- Full browser workspace with file tree, editor, terminal, and inline rendering for molecules and structures.
- Highly extensible with LSP, MCP, custom plugins, and a TypeScript SDK.
- Agent is not sandboxed; security risk, recommend running in a container or VM.
- Requires configuring API keys for each provider, potentially multiple accounts and costs.
- Linux kernel 5.1+ required; CentOS 7's 3.10 kernel unsupported, limiting deployment environments.
- Optional Atlas platform requires a prepaid wallet for its managed models, adding cost.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| OpenScience: Open-Source AI Workbench for Scientific Research This agent | 45 · Major gaps | CLIFreemium | ★ 4.1k | today | TypeScript | OpenAI API · Claude API |
| Wisp Science | 71 · Some gaps | Desktop appFree + model costs | ★ 1k | today | Rust | Codex · Claude Code · OpenAI API · Claude API |
| Qinyan Academic Skills | 48 · Major gaps | CLIFree + model costs | ★ 966 | 3mo ago | Python | Codex · Claude Code |
| Luxas Research Colleague | 59 · Major gaps | CLIFree + model costs | ★ 1.2k | 1mo ago | TypeScript | Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows a permission system that prompts users, but explicitly states it is not a sandbox, and no detailed least-privilege mechanism is provided. User confirmation exists (permission prompts) but implementation details are not shown. Data flow transparency: README mentions sessions, skills, artifacts, and provenance stored on disk, but does not detail data flows. Sensitive data handling: mentions credentials are filtered and redacted, but no implementation details. Dependency security: has dependency overrides and patches, but no vulnerability scanning evidence. External effects: explicitly states agent can run shell commands and access web, but no restrictions. Rollback: not mentioned. Source attribution: has NOTICE file, but not detailed.
Self-consistency: README, SECURITY.md, and CI config are consistent on security model, but some descriptions (e.g., sandbox) may conflict with code. Dependency availability: dependencies published via npm and GitHub, but no availability guarantees. Failure messages: tests have error handling, but no user-visible failure message examples.
Audience and scenarios: clearly targets researchers, provides multiple scenarios. Capability boundaries: no explicit limits on agent capabilities. Trigger precision: no details on command or skill triggers. Environment fit: CI for Linux, macOS, Windows, but no detailed system requirements.
Information architecture: README provides clear directory structure. Install notes: provides npm install and npx commands. Naming stability: no mention of API stability. Examples and FAQ: has quickstart, but no FAQ. Known limitations: SECURITY.md clearly states no sandbox. License: Apache-2.0, complete. Versioning changelog: has CHANGELOG.md, but content not provided. Maintenance responsibility: has SECURITY.md and contributing guide, but maintainers not explicit.
Output usability: provides browser workspace, interactive output. Marginal value: provides 290+ skills and database integrations, clear value. Cost benefit: free with own keys, but no performance or cost data.
Claim traceability: README claims lack specific evidence. Cross-source corroboration: has CI and tests, but no independent verification. Fact-inference separation: not explicitly distinguished.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Agent is not sandboxed; permission system is not an isolation boundary; run in container or VM.
- Dependency security lacks vulnerability scanning evidence; review dependencies yourself.
- Rollback mechanism not mentioned; operations may be irreversible.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Core - Find Git Bash in UCRT64 installations (#1003) - Bound decoded streams and cancel incomplete requests (#998) - Add opt-in anonymous Parallel Search preset (#1000) - Add approved Argon and document subscription routes (#999) - Cancel rejected image download streams (#993) (xiaofeilovecoding) - Bump web-tree-sitter from 0.25.10 to 0.27.1 (#990) - Drop the claude-code beta header from Anthropic requests (#996) (Jinho Kim) - Bump vscode-languageserver-types from 3.18.3 to 3.18.4 (#991) - Audit model calls across routes (#973) - Link each model call to its Ace charge (#958) …View on GitHub ↗ -
Release notes excerpt
More reliable research sessions - Keep GPT-6 Sol and GPT-6.1 Sol available through connected ChatGPT/Codex subscriptions, with supported reasoning controls and Fast mode for 6.1. GPT-6 Sol is removed from the Ace roster. - Stop unattended runs from inventing work after a greeting. - Preserve tool availability across retries, restore sessions containing malformed todo history, and keep pagination complete when sessions share a timestamp. - Prevent stale Codex sign-in timers from clearing newer attempts and keep provider web-search events consistent. Workspace and desktop …View on GitHub ↗ -
Release notes excerpt
Models and provider setup - Add OpenAI GPT-6.1 Sol with supported reasoning controls and Fast mode. - Configure custom model Base URLs and OpenAI protocol selection in Settings. - Removing a provider key disconnects its saved connection while retaining endpoint and protocol preferences. - Improve research-search setup guidance and Chinese settings and connection messages. Terminals and Claude Code - Open new terminals in the selected working folder and load the user’s login shell and installed commands. …View on GitHub ↗