Ivy Biosciences Docs
Ask a biology question or call a tool directly. .bloom* runs the tools that answer it and returns results you can cite, export, and check.
.bloom* is the Ivy Biosciences drug discovery platform. Ask a question in plain language, and it runs the tools that answer it: protein structure, docking, ADMET, omics, synthesis, and scientific databases.
Every run returns structured results and a record you can check. Re-query it, export it, or feed it into the next step.
Four ways in
curl and chat need no account for the public guest path. MCP and the CLI add saved sessions, higher quota, and the tools your plan allows once you sign in. All four reach the same .bloom* registry, so choose the one that fits how you work.
Start here
Pick the closest; the sidebar carries the rest.
Run one tool without an account
Paste a curl request and read the result. No key, no install.
Put the tools in your coding agent
Connect an MCP client so your agent can call the same tools.
Script a batch from your terminal
Submit jobs, follow them, and download results with the CLI.
Find the tool for a question
Match a scientific goal to the tool or workflow that answers it.
See what happens during a run
How a question becomes a plan, tool calls, and results.
Decide which plan you need
Credits, models, and compute tools by plan.
Quickstart
Start without an account. Try guest chat, or paste the public curl request for an allowlisted run.
Pick your entry point. Use chat for a question, curl for a quick request, CLI for batch work, or MCP when an AI coding agent should call the tools.
Run your first job. Try the ESMFold quickstart to fold a sequence, or the DiffDock quickstart to dock a ligand.
Keep the result. Sign in when you need saved sessions, higher quota, project history, or the tools your plan allows; then chain tools through workflows or the API.
Install the CLI
Full install reference: CLI install guide.
Explore by domain
Know the outcome but not the tool? What you can achieve maps each goal to the tools that serve it.
Explore
Search literature, compounds, proteins, genes, clinical data, and public repositories.
Analyze
Profile compounds, assess safety, run cheminformatics, and analyze data.
Predict
Fold proteins, dock molecules, refine binding, and simulate structure.
Design
Generate molecules and engineer proteins, antibodies, and biologics.
Omics
Work across genomics, single-cell, spatial, proteomics, and translational data.
Reports
Turn a run into passports, citations, exports, and a record someone else can check.
Workflows you can chain
Target → Hit
Sequence → ESMFold → P2Rank → DiffDock → MM-GBSA → triage.
Hit → Lead
Hit → REINVENT → ADMETLab3 → AiZynthFinder → cost-aware ranking.
Disease → Target
Expression atlas → DESeq2 → causal genomics → druggable targets.
Passport assembly
Auto-generate compound / target / safety / literature passports.
Reach it with curl or the API
The public orchestrator accepts a natural-language prompt over curl with no account. Authenticated API access adds persistent sessions, higher quota, and the full programmatic surface. The API overview explains both paths.
Guest curl quickstart
Run an allowlisted prompt without an account, then read the named SSE events.
API overview
Guest requests, authenticated REST, sessions, SDKs, and real-time streams.
Auto-generated reference
Every endpoint, grouped by lifecycle, with curl, JavaScript, and Python samples.
Access and plans
Start free, then add persistence
The guest path starts with up to $1 in compute per day and does not need an account or card. Sign in for saved sessions and your own quota; see Plans and tiers for current credits, model families, tool catalog, and API/MCP access.
For current rates, see pricing.
Common questions
Read next
Reading a result against the bench
What each tool's numbers were graded against, and where the published figures stop.
Get started
Guest access, what an account adds, and which entry point to use.
Ivy
Run tools from the browser and read results as canvas cards.
MCP server
Put the .bloom* registry in an AI coding agent.
CLI quickstart
Install, authenticate, submit jobs from the terminal.
API reference
REST endpoints, authentication, rate limits.
Troubleshooting
Common job failures and how to recover.
Workflows
End-to-end pipelines stitched from individual tools.
Was this page helpful?