BioDeepagents CLI

Skills

Skills are sourced from BioClaw. The following skills are sourced from claude-scientific-skills:

• Bioinformatics & Genomics
• Sequence Analysis: Process DNA/RNA/protein sequences with BioPython and pysam
• Single-Cell Analysis: Analyze 10X Genomics data with Scanpy, identify cell types, infer GRNs with Arboreto
• Variant Annotation: Annotate VCF files with Ensembl VEP, query ClinVar for pathogenicity
• Variant Database Management: Build scalable VCF databases with TileDB-VCF for incremental sample addition, efficient population-scale queries, and compressed storage of genomic variant data
• Gene Discovery: Query NCBI Gene, UniProt, and Ensembl for comprehensive gene information
• Network Analysis: Identify protein-protein interactions via STRING, map to pathways (KEGG, Reactome)

This project is basing on deepagents CLI, an open source coding assistant that runs in your terminal, similar to Claude Code.

Key Features:*

• Built-in Tools: File operations (read, write, edit, glob, grep), shell commands, web search, and subagent delegation
• Customizable Skills: Add domain-specific capabilities through a progressive disclosure skill system
• Persistent Memory: Agent remembers your preferences, coding style, and project context across sessions
• Project-Aware: Automatically detects project roots and loads project-specific configurations

🐳 Docker

Build the CLI image from the repository root so both the CLI sources and the shared deepagents package are available to Docker:

This project is a docker-compose hosted a deepagents-cli, and inside container some other agents(e.g. dsl) were also hosted.

docker compose run --rm --service-ports --build flask-app

Copy the sample configuration into place and edit the credentials or tracing toggles you need:

docker run --rm -it -P \
  -v "$(pwd)/workspace/:/workspace/project" \
  --env-file ./.env \
  deepagents-cli

Type naturally as you would in a chat interface. The agent will use its built-in tools, skills, and memory to help you with tasks.

[!WARNING] Human-in-the-Loop (HITL) Approval Required

Potentially destructive operations require user approval before execution:

• File operations: write_file, edit_file
• Command execution: shell, execute
• External requests: web_search, fetch_url
• Delegation: task (subagents)

Each operation will prompt for approval showing the action details. Use --auto-approve to skip prompts:

deepagents --auto-approve