Life sciences & lab workflows

Analysts and researchers get the same multi-agent workspace as engineering teams — with BiologyExpert, domain-tuned models, and sequence tools running locally when you choose Ollama. Install the official Life sciences pack from the store; organizations with proprietary instruments or QC pipelines can add a customer sideload pack on top.

Who this is for

Official Life sciences pack

Install from Domain packs (⌘⇧K) → Store → Life sciences. Or pick Life sciences & lab work in the first-run wizard.

ComponentWhat it does
BiologyExpertPreset agent with bio MCP tools and OpenBio-tuned chat
OpenBioLLM 8Bkoesn/llama3-openbiollm-8b:latest — recommended Ollama pull
Tool runnerqwen2.5:7b routes MCP tools when the chat model has no native tools API
analyze_sequenceDNA/RNA/protein checks, length, reverse complement
fold_proteinESMFold via Hugging Face Inference → PDB artifacts under hub data
Sequence review runbookImportable template for structured review workflows

Typical workflow

  1. Download Neural Junkie and complete the wizard with local models or cloud HF token for folding.
  2. Enable Life sciences pack; pull OpenBioLLM + qwen via Model library (⇧⌘M).
  3. DM BiologyExpert or @mention in a channel for sequence questions.
  4. Use /collaborate for multi-step analysis write-ups with review and approval phases.
  5. Configure HF token under Settings → AI Providers when using ESMFold or GGUF import.

Customer & instrument packs

The public Life sciences pack covers general biology tooling. Organizations with proprietary formats (e.g. plate readers, multiplex QC, TIM imports, custom scan viewers) can build a customer pack with Pack Dev Studio and install via sideload zip — same hub, private specialists and viewers, no public store listing. See Domain packs and PACKS_CUSTOM.md.

Privacy & data locality

With local Ollama, chat and tool routing stay on your workstation. ESMFold and Hugging Face downloads require network access and your HF token. Slack, Jira, and cloud LLM providers are optional. Read Security & privacy before deploying on shared lab machines.

Hardware notes

OpenBio 8B + qwen2.5:7b fit comfortably on 16 GB RAM machines; see Hardware requirements. Multi-agent chat shares one Ollama backend — you do not load six separate 14B models.