hubify agent

Manage the multi-agent team in your lab. Agents are organized in a hierarchy: orchestrator, leads, and workers.

Commands

hubify agent list

List all agents in the active lab:

hubify agent list

AGENT             ROLE      MODEL         STATUS   TASKS   QC RATE
Orchestrator      orch      claude-opus   active   342     N/A
Research Lead     lead      claude-opus   active   128     94%
Paper Lead        lead      claude-opus   active   87      97%
Analysis Worker   worker    claude-sonnet active   203     91%
Figure Worker     worker    claude-haiku  active   156     88%
Data Worker       worker    claude-haiku  active   189     95%

Show the agent hierarchy as a tree:

hubify agent list --tree

Orchestrator (claude-opus)
├── Research Lead (claude-opus)
│   ├── Analysis Worker (claude-sonnet)
│   └── Data Worker (claude-haiku)
└── Paper Lead (claude-opus)
    └── Figure Worker (claude-haiku)

hubify agent add

Add a new agent:

hubify agent add \
  --role lead \
  --name "Cosmology Lead" \
  --model claude-opus \
  --specialty "MCMC analysis, CMB power spectra, bounce cosmology"

Option	Required	Description
--role	Yes	lead or worker
--name	Yes	Descriptive name
--model	Yes	AI model (claude-opus-4-6, claude-haiku-4-5-20251001, gpt-5.4, gemini-2.5-pro)
--specialty	No	Free-text description of the agent's expertise
--parent	No	Parent agent name (defaults to Orchestrator)

hubify agent update

Update an agent's configuration:

# Change model
hubify agent update "Analysis Worker" --model claude-sonnet

# Update specialty
hubify agent update "Research Lead" --specialty "Galaxy surveys, anomaly detection"

# Disable temporarily
hubify agent update "Figure Worker" --status inactive

hubify agent remove

Remove an agent from the team:

hubify agent remove "Data Worker"

Pending tasks assigned to the removed agent are reassigned by the orchestrator.

hubify agent metrics

View performance metrics for an agent:

hubify agent metrics "Research Lead"

Agent: Research Lead
Model: claude-opus
Tasks completed:    128
QC pass rate:       94%
Avg task duration:  12m
Tokens used (30d):  2.4M
Cost (30d):         $18.40
Active since:       2026-03-15

hubify agent review-config

Configure cross-model peer review:

# Add a reviewer
hubify agent review-config --add-reviewer gpt-5.4 --api-key $OPENAI_API_KEY

# Show current config
hubify agent review-config --show

# Remove a reviewer
hubify agent review-config --remove-reviewer grok-2

hubify agent logs

View recent activity for an agent:

hubify agent logs "Research Lead" --limit 20

Examples

# Add a specialized worker for a new research branch
hubify agent add --role worker --name "PTA Worker" --model claude-sonnet \
  --specialty "Pulsar timing arrays, gravitational wave backgrounds"

# Check which agent is most productive
hubify agent list --json | jq 'sort_by(.tasks) | reverse | .[0]'

# Rotate models for cost optimization
hubify agent update "Data Worker" --model claude-haiku