Tamarind Bio

What Tamarind Bio does

Tamarind Bio is a privately held, venture-backed software company founded in 2023 by Sherry Liu and Deniz Kavi out of Stanford School of Medicine and incubated by Y Combinator. It provides a no-code, cloud-hosted computational biology platform that integrates more than 200 published AI/ML and physics-based models — including AlphaFold, RFdiffusion, ProteinMPNN, GROMACS, Boltz-2, Chai-1, BoltzGen, and ESM-C — behind a unified web interface, REST API, and Model Context Protocol (MCP) Server. The platform supports protein structure prediction, antibody and nanobody design, peptide and macrocyclic peptide discovery, enzyme engineering, and small-molecule work (docking, virtual screening, ADMET, binding affinity), and handles managed high-performance compute, parallelization, and GPU orchestration so that scientists can run hundreds of thousands of inputs without local infrastructure or ML engineering. It is SOC 2 compliant with data isolation and IP ownership for customers, and is offered alongside a closed-loop integration to A-Alpha Bio's AlphaSeq experimental validation platform and co-built inference infrastructure with NVIDIA.

The company sells through a freemium product-led growth motion (a free tier with 10 jobs per month and a free Academic Plan) supplemented by quote-based Premium and Enterprise subscription tiers. The Premium tier targets small-to-medium throughput commercial workloads with API access, org-wide admin controls, and high-priority support; the Enterprise tier adds custom model hosting, custom security audits, SLAs, and SAML SSO under multi-year contracts. Tamarind Bio reports it has been cash-flow positive since inception, grew 700% year-over-year without a dedicated sales staff, supports 10,000+ scientists globally, and is used by approximately 100 biotech organizations including eight of the top 20 pharmaceutical companies (named customers include Bayer, Boehringer Ingelheim, Eli Lilly, Mammoth Biosciences, and Adimab). In February 2026 it closed a $13.6 million Series A led by Dimension Capital with Y Combinator participation, and has since announced technology partnerships with Eli Lilly (TuneLab 2.0), A-Alpha Bio, and NVIDIA, plus product launches including the Tamarind MCP Server and the Tamarind Bio Assay Portal.

Name

Tamarind Bio

Legal name

Tamarind Bio, Inc.

Website

https://tamarind.bio

Company type

Private

Founded year

2023

Operating status

Operating

Headcount range

11–50 employees

Short description

Tamarind Bio provides a no-code, cloud-hosted computational biology platform that integrates 200+ AI/ML and physics-based models for protein structure prediction, antibody/peptide design, enzyme engineering, and small-molecule discovery, serving biotech and pharmaceutical companies including eight of the top 20 global pharma.

Ownership category

akta.pro rank

Product category

Computational Biology Platform

NAICS

Research and Development in Biotechnology (except Nanobiotechnology) (541714)

SIC

Services-Commercial Physical & Biological Research (8731)

akta.pro primary industry

Bioinformatics & Multi-omics Analysis Software (HLAGAJAD)

akta.pro secondary industries

AI/ML-Enabled Biologic Discovery Platforms (computational design, in silico screening) (HLAAAIAE), Protein Engineering & Directed Evolution Platforms (enzyme/therapeutic protein optimization) (HLAAAIAC), Target Identification & Validation Platforms (omics-driven, chemoproteomics, genetic validation) (HLAAAIAI), Multiplex & High-Throughput Diagnostics Platforms (microarrays, digital PCR, lab automation-enabled assays) (HLAAALAL), Proteomics & Mass Spectrometry Services (HLAGANAB), Synthetic Biology & Genetic Circuit Design Platforms (pathway engineering, chassis development) (HLAAAIAD)

Keywords

• Computational biology platform
• AI drug discovery
• Protein structure prediction
• Antibody design software
• Biotech research infrastructure

Headquarters

HQ city

San Francisco

HQ country

United States

HQ region

North America

Markets served

GTM type

B2B

Offering type

Software

Cost components

Infrastructure, Technology or R&D, Personnel, Marketing or Sales, Operations

Revenue model

1. Subscription (Premium tier): Recurring subscription for companies with small-medium throughput workloads, expanding their computational tooling. Includes massive scale, unlimited job runtime, open API access, rigorous data security, org-wide admin controls, and high-priority support. Pricing is quote-based.
2. Enterprise contracts: Quote-based enterprise agreements for high throughput computational workloads with custom model hosting, custom security audits, SLA agreements, and SAML SSO. Multi-year style enterprise contracts with custom terms.
3. Freemium (Free tier): Free plan for academics, individual scientists and those wanting to try running industry leading models without proprietary data. Includes 10 jobs per month, access to all models, unlimited job data storage, email support, with job runtime limits. Functions as a top-of-funnel acquisition tool.

Pricing tiers

Go-to-market motion4 records

Distribution channels1 record

Marketing channels5 records

Core offering

Tamarind Bio is a no-code, cloud-hosted computational biology platform that hosts 200+ published AI/ML and physics-based models (AlphaFold, RFdiffusion, ProteinMPNN, GROMACS, Boltz-2, Chai-1, BindCraft, etc.) behind a unified web interface, REST API, and MCP server for biotech and pharmaceutical R&D. It provides managed GPU orchestration, batch pipelines, and enterprise-grade security so scientists can run protein structure prediction, antibody design, peptide discovery, enzyme engineering, and small-molecule work at hundreds-of-thousands-of-inputs scale without local infrastructure or ML engineering.

Product overview

Tamarind Bio is a single unified no-code computational biology platform — a managed cloud inference layer for biotech R&D — that hosts 200+ state-of-the-art AI and physics-based models behind a common web UI, REST API, and MCP Server. Its portfolio is organized around four therapeutic and industrial use case modules — Antibody Design (including nanobodies and miniproteins), Peptide Discovery (including macrocyclic peptides via AfCycDesign and CyclicMPNN), Enzyme Engineering (via CatPred, EnzyGen2, COMPSS), and Small Molecule (via Boltz-2, BoltzMol-1, AutoDock Vina) — plus two cross-cutting products: the Tamarind Bio API for programmatic job submission and the Tamarind MCP Server for agentic AI integrations. Supplementary offerings include the Tamarind Bio Assay Portal (with a direct integration to A-Alpha Bio's AlphaSeq for closed-loop experimental validation), NVIDIA-powered inference infrastructure, and three commercial pricing tiers (Free, Premium, Enterprise) plus an Academic Plan. Proprietary data ownership, SOC 2 compliance, and SAML SSO (Enterprise) round out the platform.

Differentiator

Problem solved

Functional benefit

Products and services

• Tamarind Bio Platform No-code, cloud-hosted computational biology platform that hosts 200+ state-of-the-art AI/ML and physics-based models (AlphaFold, RFdiffusion, ProteinMPNN, GROMACS, Boltz-2, Chai-1, BindCraft, etc.) behind a unified web interface. Handles high-performance compute, parallelization, and GPU orchestration for protein structure prediction, antibody design, peptide discovery, enzyme engineering, and small-molecule work. Designed for biotech and pharmaceutical R&D teams that need to run models at hundreds-of-thousands-of-inputs scale without standing up local infrastructure or ML engineering.
• Tamarind Bio API Public REST API for programmatically submitting computational biology jobs to Tamarind Bio's hosted models. Uses x-api-key authentication and supports batch job submission via the /api/submit-job endpoint, allowing scientists and developers to integrate leading protein design models into their own pipelines. Available with Open API Access on Premium and Enterprise plans; custom model hosting available on Enterprise.
• Tamarind MCP Server Model Context Protocol (MCP) server that exposes Tamarind Bio's protein design and structure prediction tools to external AI agents, enabling agentic biology workflows and integration with third-party AI systems.
• Tamarind Bio Assay Portal Assay portal that streamlines experimental assay workflows and integrates with the computational platform to support closed-loop AI-driven antibody discovery, including direct integration with A-Alpha Bio's AlphaSeq experimental validation platform for quantitative binding affinity measurements of AI-designed sequences.

Quantifiable outcome

• 700% YoY growth achieved without a sales staff
• +5 more outcomes

Named customers5 records

Segments3 records

Ideal customer profiles3 records

Technology focussed Yes

API detail

Has API

Yes

API docs

API detail

Core technology

AI maturity

App detail

Integration3 records

AI capability11 records

Feature7 records

Partnerships

Four partnerships are on record, tiered core and minor.

• A-Alpha BiocoreStrategic or Co-development Partner · 2 April 2026Partnership to integrate A-Alpha Bio's AlphaSeq experimental validation platform directly into Tamarind Bio's AI molecular design tools, enabling a closed-loop workflow from in silico design (e.g., RFdiffusion, ProteinMPNN) to quantitative binding affinity measurements.
• Eli LillycoreStrategic or Co-development Partner · 1 January 2026Tamarind Bio was selected by Eli Lilly as a technology partner for the TuneLab 2.0 program, enabling biotech access to Lilly's AI tools through Tamarind's platform.
• NVIDIAcoreTechnology or Integration · 1 January 2026Co-published blog post 'Building the Inference Layer for Agentic Biology with NVIDIA', indicating collaboration on GPU-accelerated inference infrastructure for biology AI workloads.
• Stanford School of MedicineminorOthers · 1 January 2023Tamarind Bio's co-founders Deniz Kavi and Sherry Liu spun the company out of Stanford School of Medicine, which is the academic origin of the platform.

Scale indicators10 records

Recent moves6 records

Expansion highlights6 records

Broad incumbents

• Schrödinger: Public computational chemistry and molecular simulation platform (LiveDesign) widely used by pharma for structure-based drug design. Overlaps with Tamarind on protein structure prediction, docking, and FEP-style binding affinity, but operates across broader chemistry use cases and at much larger scale.
• Recursion: AI-driven drug discovery company that combines high-throughput biology with proprietary models (notably co-developed Boltz/Boltz-2). Directly comparable on the AI-for-biology thesis and as a partner/competitor on Boltz-2 model distribution; much larger, publicly listed, and vertically integrated into pipeline ownership.
• Isomorphic Labs: Alphabet-backed drug discovery company building on DeepMind's AlphaFold. Competes with Tamarind on protein structure prediction and design, with substantially deeper R&D funding and proprietary foundation-model IP.
• Benchling: Cloud R&D platform for life sciences (notebook, registry, inventory, workflows). Overlaps with Tamarind at the lab/scientist software layer and competes for biotech IT budgets, though it is not focused on AI model orchestration.
• Dotmatics: Enterprise scientific R&D informatics platform (acquired by Siemens-backed Insightful Science, later part of Revvity). Competes with Tamarind for biotech IT spend across data management, ELN, and computational workflows.
• Ginkgo Bioworks: Synthetic biology platform serving biotech R&D with codeable organisms and AI-assisted design. Broad incumbent in AI-for-biology with deeper wet-lab infrastructure and substantially larger scale than Tamarind.

Emerging players

• Genesis Therapeutics: AI-native drug discovery company with its own protein/ligand foundation models. Comparable in size and stage to Tamarind, focused on small-molecule and protein design; competes for similar early-design-stage pharma budgets.
• Chai Discovery: Developer of Chai-1, a state-of-the-art protein structure prediction model that Tamarind itself hosts. Direct competitor on model quality and a potential partner/alternative for biotech customers evaluating model access.
• Cradle: AI platform for protein engineering with a no-code interface and proprietary models. Closest peer in terms of PLG motion and protein-design use case; comparable in stage and customer profile.
• Valence: AI platform for protein design and antibody discovery aimed at biotech R&D teams. Competes for the same antibody-engineering and design-for-manufacturing use cases Tamarind serves.

Market position

Strengths5 records

Weaknesses5 records

Competitive moat5 records

Key risks6 records

Key highlights7 records

Customer concentration

• Xx.com/tamarindbio
• LinkedInlinkedin.com/company/tamarind-bio

Compliance1 record

Revenue estimate

Valuation estimate

Number of profiles

Profiles2 records

Funding overview

Funding rounds2 records

Investors5 records

Funding detail is available on the Subscription and Enterprise plan.Contact sales →

M&A

Investments

M&A and investment is available on the Subscription and Enterprise plan.Contact sales →

Frequently asked questions about Tamarind Bio