Completely Free, Open-Source Alternative to Claude Science, Use DeepSeek/GLM as You Like

marsbitPublicado a 2026-07-07Actualizado a 2026-07-07

Resumen

Free, Open-Source Alternative to Claude Science: OpenScience Lets Researchers Use Any AI Model Like DeepSeek or GLM Shortly after Anthropic launched Claude Science, a specialized AI workbench for scientific research, the open-source community responded with its own solution: OpenScience. Developed by YC-backed Synthetic Sciences, this platform offers a full AI research workflow covering literature review, hypothesis generation, code experimentation, and paper writing. Unlike Claude Science, which is restricted to macOS/Linux, paid users, and only Claude models, OpenScience is model-agnostic and free. Researchers can use any AI model—DeepSeek, GLM, Claude, GPT, or local models via Ollama—simply by providing their own API keys, keeping data private. OpenScience features over 250 editable research skill packs, more than four times Claude Science's initial offering, and supports one-command installation. It emphasizes openness, arguing that scientific AI tools should not be controlled by a single company. The project includes a clear disclaimer of no affiliation with Anthropic, reflecting caution in the open-source community.

Researchers are ecstatic!!

Less than a week after Anthropic's Claude Science launched, the open-source community has presented its own answer.

An AI research team incubated by YC, has delivered 'the open-source alternative to Claude Science' — OpenScience.

It's also a full-process AI research workbench covering literature search, hypothesis generation, code experiments to paper writing, but it is not tied to any single model provider.

DeepSeek, GLM, Claude, GPT... regardless of domestic or international, use whichever one you want.

Moreover, the project adopts the developer-friendly Apache 2.0 license and can be installed with just one command.

Once the news broke, the project directly trended on X. People bluntly stated:

This is what scientific AI should look like. (Anthropic: Just say my name.)

Claude Science is powerful, but it's unusable...

About 5 days ago, Anthropic officially launched Claude Science at a closed-door event by MIT Technology Review.

This is an AI workbench specifically for scientists, providing various tools and software packages most commonly used by researchers.

For example, previously, a researcher completing a study had to search literature on PubMed, write code in Jupyter, run statistics in R, connect to a cluster via SSH to submit tasks, and then use various tools to create charts and write papers.

Switching between a dozen windows, the mere 'transitions' between tools consumed a huge amount of energy.

What Claude Science aims to do is bundle all of this into the same workbench.

Specifically, it achieves several key integrations:

At the database and toolchain level, it comes with built-in connectors to over 60 scientific databases and pre-configured skill packages, covering common research fields like genomics, single-cell analysis, proteomics, structural biology, chemoinformatics, etc.

You ask in natural language, and specialized Agents automatically perform cross-database queries — no need to manually search databases like UniProt, PDB, Ensembl, ChEMBL, GEO one by one.

It also integrates with NVIDIA's BioNeMo Agent Toolkit, allowing direct connection to life science models like Evo 2, Boltz-2, OpenFold3.

At the execution level, it introduces a multi-agent architecture.

The main Agent handles overall planning, sub-agents process different tasks in parallel, and there is a Reviewer Agent specifically responsible for fact-checking, such as verifying citations, validating calculation results, and flagging potential errors.

The generated output is not just text. It can natively render content like 3D protein structures, genome browser tracks, chemical structure formulas.

Moreover, each chart retains the generation code, runtime environment, natural language description, and complete conversation history.

In some scenarios, scientists can even modify charts with a single sentence, and the system automatically rewrites the underlying code.

At the computing power level, Claude Science can directly interface with your lab's existing infrastructure.

Be it notebooks, Linux servers, or HPC cluster login nodes, it can connect via SSH or use a Modal account to call cloud GPUs on demand, scaling from a single GPU to hundreds.

Large-scale datasets only need to be loaded once; sensitive data never leaves your own system. Only the context needed for each step of analysis is sent to Claude.

Early beta users have already produced some practical cases.

Jerome Lecoq, a neuroscientist at the Allen Institute, used it to build a multi-agent 'computational review template' containing about 20 custom skills, letting sub-agents read thousands of papers, extract core viewpoints and quantitative data, and then generate review chapters one by one.

To put it simply, writing a review used to take two years; now he has about 10 drafts in hand —

Many exceed 100 pages, and all citations have been verified by the Reviewer Agent.

Stephen Francis from the UCSF Brain Tumor Center used it for molecular epidemiological studies of glioma, running germline variant analysis.

He said Claude Science compressed the previously required time to one-tenth, and his team independently validated the results, confirming the analysis was both fast and reliable.

Combined with the evaluation of AI research capabilities by Harvard physicist Matthew Schwartz this past March, Claude's current level is roughly equivalent to a second-year graduate student.

He published a guest post titled "Vibe Physics: The AI Grad Student" on the Anthropic official blog, documenting his entire process of using Claude Opus 4.5 to complete a theoretical physics paper.

His conclusion at the time was:

Current AI research capability is roughly equivalent to a second-year grad student — can work, doesn't complain about being tired, but needs a supervisor to monitor every step.

This assessment was later incorporated by Anthropic into the Claude Science technical documentation as a calibration point for the product's positioning.

However, Claude Science currently has several hard limitations:

Only supports macOS and Linux

Only available to Pro/Max/Team/Enterprise paying users

Only Claude's own models can be used on the platform

These thresholds stacked together, especially for domestic research teams in China, make Claude Science something "visible but out of reach."

Good News: An Open-Source Alternative is Here

Targeting the above limitations, the open-source project OpenScience emerged.

The team behind it is called Synthetic Sciences, founded in San Francisco in 2025, and just graduated from the YC Winter 2026 batch this year.

The founding team's ambition is not small: to build a platform that lets scientists directly delegate complex research tasks to "AI co-scientists," enabling AI to autonomously run the entire chain from literature review to hypothesis generation to experiment execution to paper writing.

They have an internal core belief:

Scientific foundation models need to possess genuine 'research taste,' and this taste cannot be achieved by simply scaling parameters. It must be a two-pronged approach: product and model. Use the product to collect high-quality scientific process data, then use this data to train models with taste.

OpenScience is the first product landing on this path.

Although OpenScience's mission is the same as Claude Science's, they have a fundamental difference:

Model-agnostic.

In Synthetic Sciences' own words:

Scientific AI should be open. The tools humans use for exploration and discovery should not be monopolized by one company, nor should that company decide who is qualified to use them.

Therefore, on this platform, Anthropic, OpenAI, Google, DeepSeek, GLM... as long as you have an API Key, you can connect directly.

You can even run local models, deploy via Ollama, without a single byte of your data leaving your machine.

Your Key stays locally, requests go directly to the model provider, not passing through any intermediate server.

Moreover, OpenScience supports switching models per request.

Within the same workbench, you can use Claude for this step, then switch to DeepSeek for the next, without changing any configuration.

Feature-wise, OpenScience is even more aggressive than Claude Science —

Built-in with over 250 research skill packages, more than 4 times that of Claude Science, covering ML, computational biology, chemoinformatics, etc., and all are readable, editable, and extensible.

Installation is also simple, just one command in the terminal:

Open and use immediately, the workbench automatically pops up in the browser. On first run, select a model source, fill in the API Key, and you can start working.

You can also install it globally:

If configuring Keys is troublesome, the team also provides a hosted platform called Atlas —

Top up a wallet to directly call various cutting-edge models without configuring Keys one by one, plus persistent research graphs and cloud computing power.

But Atlas is not mandatory. You can use OpenScience fully for free with your own Keys, no barrier.

One More Thing

Interestingly, if you scroll to the very bottom of OpenScience's GitHub page, you'll see a statement added specifically:

OpenScience is an independent project. It is not affiliated with, endorsed by, or sponsored by Anthropic. “Claude” is a trademark of Anthropic, PBC, used here only to describe compatibility.

Translation: We are an independent project, with no relation to Anthropic whatsoever. Mentioning "Claude" is purely about describing compatibility, don't read too much into it.

It seems the impression left by the "lobster" incident on the entire open-source community is still too profound.

With OpenClaw changing names several times before, OpenScience this time directly welded the disclaimer onto the first version of the README.

Nothing else — survive first, then talk about being an alternative (doge).

Open-source address:

https://x.com/i/trending/2073904804829741364?s=20

Reference links:

[1]https://x.com/SynScience/status/2073829478393086311?s=20

[2]https://x.com/i/trending/2073904804829741364?s=20

[3]https://www.openscience.sh/

[4]https://www.anthropic.com/news/claude-science-ai-workbench

This article is from WeChat official account "QbitAI", author: Yi Shui

Criptos en tendencia

CitreaCTR

wrapped stUSDTWSTUSDT

Velodrome FinanceVELODROME

BrevisBREV

PancakeSwapCAKE

Preguntas relacionadas

QWhat is OpenScience and how does it compare to Claude Science?

AOpenScience is an open-source AI scientific research workbench that serves as a free alternative to Anthropic's Claude Science. Unlike Claude Science, which is proprietary and limited to Claude models for paid users, OpenScience is model-agnostic, allowing users to freely choose and switch between various AI models like DeepSeek, GLM, Claude, or GPT via API keys or local deployments. It is released under the Apache 2.0 license and offers more than 250 research skill packages, significantly more than Claude Science's 60+.

QWhat are the key limitations of Claude Science mentioned in the article?

AClaude Science has several key limitations: 1) It only supports macOS and Linux operating systems. 2) It is exclusively available to Pro, Max, Team, and Enterprise paying users. 3) Users are restricted to using only Anthropic's proprietary Claude models on the platform. These restrictions, especially the payment requirement and model lock-in, make it inaccessible to many researchers, particularly in certain regions.

QHow does OpenScience address data privacy and local deployment?

AOpenScience prioritizes data privacy and flexibility by supporting local model deployment. Users can run models locally using tools like Ollama, ensuring that sensitive research data never leaves their own machines. API keys are also stored locally, and requests are sent directly to the model provider without passing through any intermediate servers, giving researchers full control over their data and computational environment.

QWhat was the early user feedback on Claude Science's capabilities?

AEarly internal testers reported positive results. A neuroscientist at the Allen Institute used Claude Science to create a multi-agent computational review template, enabling the generation of lengthy, citation-verified review papers in a fraction of the traditional time (e.g., producing ~10 papers over 100 pages each that previously would have taken years). A researcher at UCSF's Brain Tumor Center used it for molecular epidemiology studies, reducing the required time for germline variant analysis to one-tenth while maintaining result accuracy verified by his team.

QWhat is the stated long-term vision of the Synthetic Sciences team behind OpenScience?

AThe Synthetic Sciences team aims to build a platform where scientists can delegate complex research tasks to 'AI co-scientists' that autonomously handle the entire research pipeline from literature review to hypothesis generation, experiment execution, and paper writing. They believe that truly capable scientific foundation models require 'research taste,' which cannot be achieved by merely scaling model parameters. Instead, it requires a product-model co-development approach, where the product collects high-quality research process data to train models with genuine scientific intuition.

Lecturas Relacionadas

‘Incentivize democracy’ at the cost of security? Inside Bonk’s $20M exploit

BonkDAO, the governance body for the memecoin BONK, suffered a $20 million exploit due to a malicious governance proposal. The attacker acquired enough BONK to create a proposal with a 1% vote threshold, which then authorized transferring 4.4 trillion BONK to their wallet. Security analysts criticized the low approval threshold and lack of safeguards like lock periods for treasury transfers, calling it an operational security failure. The incident fueled debate about balancing decentralized governance with security. Following the news, BONK's price dropped 10%, though on-chain data indicated continued accumulation by large holders since June. The project is collaborating with law enforcement and exchanges to mitigate the situation.

ambcryptoHace 33 min(s)

‘Incentivize democracy’ at the cost of security? Inside Bonk’s $20M exploit

ambcryptoHace 33 min(s)

Zoomex X Space Recap With David James and the World Cup Trading Panel

Zoomex hosted a World Cup-themed X Space featuring England goalkeeper David James and a panel of traders. The discussion, part of a charity pledge, drew parallels between goalkeeping and trading, focusing on preparation, psychology, and execution. James emphasized that pressure for a goalkeeper comes during periods of inactivity, not sustained attack, and highlighted the importance of concentration. He described two modes for penalty saves: meticulous preparation using data on shooters, and instinct, which is improved by information—a concept traders directly related to market analysis. He discussed how elite preparation turns instinct into trained execution, making spectacular saves feel like practiced outcomes rather than miracles. Errors are now treated as data for correction, not lingering ghosts. James analyzed tournament threats, noting France's exceptional speed across the pitch and suggesting that teams like Mexico and Spain, yet to concede, face a psychological test. On England's chances, James was unequivocal, predicting they would win and nominating the UEFA Foundation for the associated charity donation. The session consistently linked thorough preparation in both football and trading to controlling emotions and executing under pressure, with the core lesson being that preparation eliminates nervousness by replacing unknowns with a plan.

TheNewsCryptoHace 46 min(s)

Zoomex X Space Recap With David James and the World Cup Trading Panel

TheNewsCryptoHace 46 min(s)

Unitree's IPO Frenzy: The Real Mystery is How It Will Spend the 42 Billion Raised

Unitree, a Chinese robotics company, is set for a public listing after its IPO registration was approved by regulators. The company, which started with quadruped robots and has expanded into humanoids, plans to raise approximately 4.2 billion yuan through its offering. The article traces Unitree's rapid growth from its founding in 2016 to its current status. It highlights key milestones like the 2021 CCTV Spring Festival Gala performance, the 2023 launch of its affordable Go2 robot dog and the H1 humanoid robot, and a series of subsequent product launches. By 2025, the company reported revenue of 1.71 billion yuan, profitability, and sales exceeding 5,500 humanoid robots. As the first publicly-listed humanoid robot company on China's STAR Market, Unitree's main challenges are sustaining growth and deploying its newly raised capital effectively. The humanoid robot sector in China is crowded, with over 140 companies. Competitors include UBTech (focusing on industrial and consumer markets), Fourier, and international players like Tesla Optimus and 1X NEO. The article outlines three critical challenges for Unitree: establishing a strong second product line beyond its quadruped robots, maintaining its price advantage while ensuring quality, and successfully advancing its embodied AI capabilities through partnerships like the one with NVIDIA for the H2 Plus platform. Unitree's likely strategy involves a "developer tools + industry benchmarks" approach: using low-cost models like the R1 and G1 to build developer adoption and volume, leveraging high-end platforms for AI training, and securing pilot projects in sectors like logistics and manufacturing to build case studies. The company's future success hinges on converting its current momentum in shipments and pilot programs into sustainable, large-scale commercial contracts as the broader market evolves.

marsbitHace 1 hora(s)

Unitree's IPO Frenzy: The Real Mystery is How It Will Spend the 42 Billion Raised

marsbitHace 1 hora(s)

Examining the Open USD Partner Lineup: Follow Who's Joining to See Where the Money Flows

**Title: Deciphering the Open USD Partner Roster: Following the Money** The launch of Open USD is notable less for the stablecoin itself and more for its expansive list of over 140 founding partners, which reads like a "who's who" of global finance and tech. This coalition, including asset managers like BlackRock, card networks Visa and Mastercard, banks (BNY Mellon, Standard Chartered, etc.), tech giants (Google, IBM), merchants (Shopify), and crypto firms (Coinbase, Ripple, Aave, MetaMask), signals a strategic shift. The diverse membership reveals that stablecoins are increasingly viewed not as products to compete over, but as shared infrastructure too critical to be left to any single entity. Each partner category has distinct motives. Asset managers like BlackRock seek to manage the large, sticky cash reserves, a lucrative fee-generating opportunity. Merchants like Shopify aim for lower-cost settlement and potential yield on balances. Banks join defensively to retain custody and settlement roles, fearing deposit outflows to stablecoins. Tech companies bet on programmable money for future machine-to-machine commerce. Crypto firms gain mainstream legitimacy and distribution channels. Remarkably, the consortium includes direct competitors (Visa vs. Mastercard, Coinbase vs. Ripple), indicating that the fear of exclusion from this emerging financial layer outweighs competitive rivalries. However, this shared governance could also lead to slow decision-making. The roster's composition is the real message: it represents a collective bet that a widely accepted, consortium-owned stablecoin is preferable to proprietary versions or having none at all. For incumbents like Circle and Tether, this alliance poses a significant threat, as potential clients have collectively chosen to build their own alternative. The absence of major U.S. retail banks (busy with their own tokenized deposit networks) is equally telling. In essence, the partner list maps where the industry believes value and risk will flow in a tokenized dollar future, marking stablecoin's evolution from a product to a utility.

Foresight NewsHace 1 hora(s)

Examining the Open USD Partner Lineup: Follow Who's Joining to See Where the Money Flows

Foresight NewsHace 1 hora(s)

Solana activity hits 1 billion milestone – Is a SOL price surge next?

Solana achieved a milestone of 1 billion non-vote transactions in a week, demonstrating its high throughput and scalability. This performance is attributed to the Alpenglow upgrade, which reduced finality times significantly. Solana currently processes transactions much faster than Ethereum. However, the article notes that market efficiency and tokenomics are the next key challenges. While network fundamentals are strong, SOL's higher inflation rate compared to other major Layer 1s and the need for a more developed market layer to improve capital efficiency could impact its long-term valuation. The core question remains whether SOL's price will reflect these underlying technical strengths.

ambcryptoHace 1 hora(s)

Solana activity hits 1 billion milestone – Is a SOL price surge next?

ambcryptoHace 1 hora(s)

Trading

Spot

Artículos destacados

Cómo comprar GLM

¡Bienvenido a HTX.com! Hemos hecho que comprar Golem (GLM) sea simple y conveniente. Sigue nuestra guía paso a paso para iniciar tu viaje de criptos.Paso 1: crea tu cuenta HTXUtiliza tu correo electrónico o número de teléfono para registrarte y obtener una cuenta gratuita en HTX. Experimenta un proceso de registro sin complicaciones y desbloquea todas las funciones.Obtener mi cuentaPaso 2: ve a Comprar cripto y elige tu método de pagoTarjeta de crédito/débito: usa tu Visa o Mastercard para comprar Golem (GLM) al instante.Saldo: utiliza fondos del saldo de tu cuenta HTX para tradear sin problemas.Terceros: hemos agregado métodos de pago populares como Google Pay y Apple Pay para mejorar la comodidad.P2P: tradear directamente con otros usuarios en HTX.Over-the-Counter (OTC): ofrecemos servicios personalizados y tipos de cambio competitivos para los traders.Paso 3: guarda tu Golem (GLM)Después de comprar tu Golem (GLM), guárdalo en tu cuenta HTX. Alternativamente, puedes enviarlo a otro lugar mediante transferencia blockchain o utilizarlo para tradear otras criptomonedas.Paso 4: tradear Golem (GLM)Tradear fácilmente con Golem (GLM) en HTX's mercado spot. Simplemente accede a tu cuenta, selecciona tu par de trading, ejecuta tus trades y monitorea en tiempo real. Ofrecemos una experiencia fácil de usar tanto para principiantes como para traders experimentados.

134 Vistas totalesPublicado en 2024.12.10Actualizado en 2026.06.02

Discusiones

Bienvenido a la comunidad de HTX. Aquí puedes mantenerte informado sobre los últimos desarrollos de la plataforma y acceder a análisis profesionales del mercado. A continuación se presentan las opiniones de los usuarios sobre el precio de GLM (GLM).