Skip to main content
How-To Guide

Agent Management Guide

Step-by-step guide to configuring, running, and monitoring ACE's 10 autonomous agents

1
Configure an AI Provider
9 of 10 agents require an LLM provider to reason

Before agents can run their observe/reason/act/reflect loop, they need access to an LLM. ACE supports Anthropic (Claude), OpenAI (GPT-4), and Google (Gemini).

# Option 1: Set via Dashboard
Dashboard → Settings → AI Configuration → Add API Key

# Option 2: Set via environment variable
export ANTHROPIC_API_KEY="sk-ant-..."  # or OPENAI_API_KEY, GOOGLE_API_KEY
Tip: Only Graph Maintenance runs without an AI provider. It uses deterministic validation rules.
2
View Agent Status
Check which agents are running and their health

Dashboard

Open the Agent Command Center to see all 10 agents with live status, last run time, and error counts.

MCP Tool

ace_agent_status()
# REST API — get all agent statuses
curl http://localhost:7777/api/v1/agents/status \
  -H "Authorization: Bearer $ACE_JWT_TOKEN"

# Response shows each agent's enabled state, last run, and error count
3
Trigger an Agent Manually
Run any agent on-demand instead of waiting for its interval
# Trigger the Knowledge Guardian
curl -X POST http://localhost:7777/api/v1/agents/guardian/run \
  -H "Authorization: Bearer $ACE_JWT_TOKEN"

# Trigger via MCP
ace_trigger_agent({ agent_name: "guardian" })
When to trigger manually: After bulk imports, after resolving issues, before a code review session, or after major architecture changes.
4
Customize Agent Configuration
Adjust intervals, enable/disable, and choose LLM providers per agent
# Update Knowledge Guardian config
curl -X PUT http://localhost:7777/api/v1/{namespace}/agents/guardian/config \
  -H "Authorization: Bearer $ACE_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "enabled": true,
    "interval_hours": 2,
    "llm_provider": "anthropic"
  }'

# Via MCP
ace_agent_config({
  agent_name: "guardian",
  enabled: true,
  interval_hours: 2,
  llm_provider: "anthropic"
})

Configurable Options

  • enabled — turn agent on/off
  • interval_hours — how often it runs
  • llm_provider — anthropic, openai, or google

Cost Management

Lower intervals = more LLM calls = higher cost. Start with default intervals and adjust based on the cost tracking in the Command Center.

5
Review Agent Insights
See what agents have discovered and act on their findings

The Knowledge Guardian, Risk Engine, and Pattern Detector surface actionable findings. Review these regularly in the Insights Panel.

# Get agent insights
curl http://localhost:7777/api/v1/{namespace}/agents/insights \
  -H "Authorization: Bearer $ACE_JWT_TOKEN"

# Via MCP
ace_agent_insights()

Guardian

Contradictions, stale data, knowledge drift

Risk Engine

Actionable risks, causal chains, temporal patterns

Pattern Detector

Recurring patterns in work logs and decisions

6
Audit Execution Traces
See exactly what each agent observed, reasoned, acted on, and reflected
# View last 10 runs for the Guardian
curl "http://localhost:7777/api/v1/{namespace}/agents/guardian/history?limit=10" \
  -H "Authorization: Bearer $ACE_JWT_TOKEN"

# Each run includes a full trace:
# - observe: what entities were scanned
# - reason: what the LLM decided (with token count)
# - act: what actions were taken
# - reflect: confidence score and self-evaluation
Dashboard shortcut: Click any agent card in the Command Center to see its full trace history with expandable details.
Common Recipes
Practical workflows for agent management

After a bulk data import

Trigger graph_maintenance → then consolidator → then guardian. This validates relationships, deduplicates memories, and checks for contradictions.

Start-of-day routine

Check ace_agent_insights() for overnight findings. Review any contradictions flagged by the Guardian. Clear resolved items.

Before a code review

Trigger quality_governor to check for incomplete entities, then risk_engine to surface any risks related to the changes.

Reduce agent costs

Increase intervals for Discovery agents (6h → 12h), keep Protection agents frequent. Use ace_agent_health() to monitor token spend per agent.

Related Guides