Skip to main content

THE SYSTEM

An evidence-first AI system for life sciences.

Claude composes five reasoning plugins with twenty-eight specialized DomainOS products over a hash-verified MCP data layer. Claims are grounded in artifacts. Artifacts carry provenance. Critical decisions route through human gates.

1,062+ skills · 185+ agents · 28 DomainOS · 16+ MCP tools

THE CO-WORK SYSTEM

How a request flows.

A request passes through seven stages — intent routing, plugin dispatch, parallel agents, evidence verification, human gates, adversarial review, canonical artifacts — with typed contracts at each boundary.

REQUEST FLOW

  1. 01

    User intent

    classify_intent() → 13 categories, confidence score

  2. 02

    Engine dispatch

    EngineRouting contract, HITL level, evidence mode

  3. 03

    Parallel execution

    DomainOS + MCP + KG (validated | exploratory | degraded)

  4. 04

    HITL gates

    Hypothesis, design, execution, publish checkpoints

  5. 05

    Evidence Guardian

    Grounding + provenance + contradiction detection

  6. 06

    Swiss Cheese review

    Adversarial A (Opus) + B (Sonnet) before merge

  7. 07

    5 canonical artifacts

    result, report, provenance, gate_status, session

4-TIER ARCHITECTURE

TIER 1 · ORCHESTRATOR

hordago core

Intent router + evidence contracts

TIER 2A · MCP SERVERS

10 servers, 16+ tools

PubMed, ChEMBL, bioRxiv, Knowledge Graph…

TIER 2B · REASONING PLUGINS

Five composed plugins

co-writer, co-scientist, sophia, paper-intel, knowledge-graph

TIER 2C · DOMAINOS

28 specialized domains

CRISPRos, GWASos, BIOos, onco-os…

THE REASONING LAYER

Five plugins Claude composes.

Each plugin is an evidence-first reasoning system with its own skills, agents, and MCP tools. Claude composes them together for any workflow — writing, hypothesizing, reasoning, tracking claims, connecting knowledge.

co-writer

34 skills · 5 agents

Compiles scientific writing

Compiles submission-grade papers, grants, biosketches, and CVs from structured intent and lab data. Every output compiled from artifacts, with claim-to-evidence tracking and venue formatting.

  • — compile-manuscript
  • — evidence-audit
  • — scientific-writing
  • — peer-review
  • — compliance-lint

co-scientist

8 skills · 7 agents

Generates and critiques hypotheses

Hypothesis-driven research assistant. Generates, critiques, and evaluates hypotheses using the Swanson ABC model across a 6-phase pipeline — Scout → Generate → Critique → Scan → Plan → Review — with Elo tournament ranking.

  • — hypothesis-generate
  • — hypothesis-critique
  • — analysis-plan
  • — novelty-scan
  • — gap-detect

sophia-claudette

7 skills · 9 agents

Audits scientific reasoning

Scientific reasoning plugin for Claude Code. Runs as automatic background observations and an explicit deep mode — uncertainty calibration, causal skepticism, drift auditing, epistemic diagnostics.

  • — uncertainty-calibration
  • — causal-skepticism
  • — drift-audit
  • — epistemic-math
  • — decision-audit

paper-intelligence

12 skills · 3 agents · 5 MCP

Extracts and tracks claims

Extracts structured claims from scientific papers, builds evidence graphs, and queries claim relationships. Seven-stage ingestion: ingest → extract → normalize → dedup → link → tag → upsert. Provenance is never fabricated.

  • — paper-ingest
  • — claim-extract
  • — claim-graph-query
  • — contradiction-detection
  • — claim-provenance

knowledge-graph

5 skills · 1 agents · 11 MCP

Unifies biomedical knowledge

Universal biomedical knowledge graph infrastructure. Neo4j graph + DuckDB columnar + SQLite FTS5 text search, Biolink Model schema, namespace-isolated across pi, t1d, gwas, crispr, tools, hyp, skill.

  • — graph-query
  • — graph-ingest
  • — graph-search
  • — graph-explore
  • — graph-status

28 DOMAINOS PRODUCTS

One stack, every life-science domain.

Each DomainOS packages the workflows, evidence gates, and provenance requirements of its field, and composes the reasoning plugins for that domain's motions.

Genomics & Variants (8)

  • BIOos

    Alignment, QC, RNA-seq

  • GWASos

    Association, fine-mapping

  • varfx-os

    Variant annotation

  • finemap-os

    Statistical fine-mapping

  • prs-os

    Polygenic risk scores

  • mendel-os

    Mendelian genetics

  • clinvar-os

    ClinVar interpretation

  • longread-os

    ONT, PacBio

Cell & Molecular (4)

Omics (5)

  • onco-os

    Somatic, neoantigen

  • microbiome-os

    16S, metagenomics

  • proteomics-os

    Mass spec

  • metab-os

    Metabolomics

  • immuno-os

    Immune repertoire

Imaging & Structure (2)

  • struct-os

    AlphaFold, docking

  • bioimage-os

    Microscopy

Clinical & Regulatory (3)

  • rare-os

    Rare disease, ACMG

  • clinical-os

    EHR, PyHealth

  • reg-os

    ISO 13485, FDA QMSR

Drug Discovery (3)

  • chem-os

    Cheminformatics

  • admet-os

    ADMET prediction

  • virtual-screen-os

    Virtual screening

Systems & Networks (3)

  • systems-os

    Systems biology

  • pathway-os

    Pathway analysis

  • grn-os

    Gene regulatory networks

MCP DATA LAYER

Ten servers, on demand.

On-demand access to biomedical databases via Model Context Protocol. Servers sit idle until a tool is invoked — only the query and its response consume context.

biocontext7

2,064 deep bioinformatics skills

stdio

PubMed

36M+ biomedical articles

HTTP

ChEMBL

2.4M bioactive compounds

HTTP

bioRxiv

Preprints (bio + med)

HTTP

ClinicalTrials

ClinicalTrials.gov registry

HTTP

Open Targets

Drug target evidence

HTTP

Synapse

Sage Bionetworks data

HTTP

BioRender

Scientific figure generation

HTTP

Knowledge Graph

Neo4j biomedical KG

stdio

Paper Intelligence

Claim graph queries

stdio

COMPOUND WORKFLOW CATALOG

1,062+ skills across 8 capability tiers.

Every skill is a typed contract with inputs, outputs, provenance, and validation. Agents compose them without inventing steps.

Writing & Publication

34

manuscripts, grants, CVs, presentations, posters, slides, lit reviews, peer review, Google Docs

Discovery & Hypothesis

8

co-scientist pipeline, hypothesis-generate/critique, novelty-scan, gap-detect, controversy-map

Reasoning & Epistemics

7

sophia deep mode, uncertainty calibration, epistemic math, causal skepticism, drift audit

Knowledge & Claims

17

paper ingest, claim extraction, graph queries, gap detection, contradiction scan, citation networks

Statistics & Analysis

9

Cox regression, power-analyst, multi-comparison, effect-size, assumption-checker, test-selector, time series

Data Visualization

11

matplotlib-publication, seaborn-stats, interactive-viz, figure-compose, schematics, citation networks

Verification Infrastructure

6

verified-skills (CONTRACT.json), evidence-audit, context-discovery-mcp (GPU embeddings)

Pipeline & External

22

BIOos, Karpathy 6-phase, Benchling, DNAnexus, Ginkgo, LatchBio, Opentrons, OMERO, Modal

BY THE NUMBERS

Current state.

1,062+

Total Skills

185+

Total Agents

28

DomainOS Products

16+

MCP Tools

5

Engine Plugins

56

Repos in Org

10

MCP Data Servers

9

Stats Primitives

Compose the whole system.

Start with a DomainOS, add reasoning engines, plug into the MCP data layer. Every output carries provenance you can audit end-to-end.

Browse products View on GitHub