Open Source Monitoring

The Command Center
for AI Agents

Real-time monitoring dashboard for your entire AI fleet. Track agent status, token usage, heartbeat, memory, and live output — all in one place.

Up and running in minutes

Three steps to full visibility into your AI agent fleet. No complex setup, no vendor lock-in.

1

Install

One command to install NerveCenter globally. Works with any Node.js environment — local, cloud, or CI.

2

Configure

Point NerveCenter to your agents with a simple YAML config. Define names, endpoints, and monitoring intervals.

3

Monitor

Open the dashboard and watch your agents in real time. Status, tokens, heartbeats, memory, and live output — all at a glance.

Everything you need to
manage your AI fleet

Purpose-built for AI agent monitoring. Every feature designed around how agents actually work.

Agent Status

See which agents are online, idle, or offline at a glance. Real-time status updates with automatic health detection and alerting when agents go dark.

Token Tracking

Monitor token consumption across all agents in real time. Track input/output tokens, cost estimates, and usage trends over time to optimize your spend.

Heartbeat Monitoring

Continuous heartbeat checks ensure you know the moment an agent stops responding. Configurable intervals, grace periods, and escalation rules.

Live Output

Stream agent output in real time. Watch tool calls, reasoning traces, and responses as they happen — like tailing logs, but for AI agents.

Memory Viewer

Inspect agent memory and context. See what your agents remember, how context is managed, and debug memory-related issues without guessing.

Activity Feed

A unified timeline of everything happening across your agent fleet. Filter by agent, event type, or severity to find exactly what you need.

Agent History

Full audit trail of every agent session. Review past conversations, tool usage patterns, error rates, and performance metrics over any time range.

See it in action

A glimpse of the NerveCenter dashboard monitoring a live agent fleet.

NerveCenter — localhost:3000

Agents

TitanOrchestrator
ForgeBackend
PixelFrontend
SentinelQA
ScoutResearch
MuseCreative
BoltDevOps
Agents Online
4/7
Tokens (24h)
1.2M
Avg Latency
142ms
10:23:01 titan Spawned sub-agent for task #247
10:23:03 forge ✓ API endpoint deployed
10:23:05 pixel Building component library...
10:23:08 sentinel ✓ QA pass: 47/47 tests
10:23:12 titan Processing heartbeat responses
10:23:15 forge Database migration complete
10:23:18 pixel ✓ Dashboard render: 16ms
10:23:22 scout Indexing 3 new sources...
10:23:25 titan ✓ All agents healthy
10:23:28 sentinel Running integration suite
10:23:01 titan Spawned sub-agent for task #247
10:23:03 forge ✓ API endpoint deployed
10:23:05 pixel Building component library...
10:23:08 sentinel ✓ QA pass: 47/47 tests
10:23:12 titan Processing heartbeat responses
10:23:15 forge Database migration complete
10:23:18 pixel ✓ Dashboard render: 16ms
10:23:22 scout Indexing 3 new sources...
10:23:25 titan ✓ All agents healthy
10:23:28 sentinel Running integration suite

Built different, on purpose

Monitoring designed from the ground up for AI agent architectures.

🔓

Open Source

Fully open source under MIT license. Inspect the code, contribute features, fork it — your monitoring, your rules. No black boxes, no vendor lock-in.

🏠

Self-Hosted

Your data stays on your infrastructure. Deploy on a VPS, bare metal, or your local machine. Zero telemetry, zero external dependencies, full control.

🔌

Framework Agnostic

Works with any AI framework — LangChain, CrewAI, AutoGen, OpenClaw, or your custom setup. If it speaks HTTP, NerveCenter can monitor it.

Ready to take control?

Join the community building the future of AI agent monitoring. Star the repo, contribute, or just get started.