Use cases
Observe, diagnose, and improve real agent runs.
Inspect model activity, processes, files, network effects, resources, repeated failures, and the evidence used to evaluate later improvements.
Explore use cases →Product
One product from local agent runs to distributed fleets.
AgentSight combines runtime evidence, a distributed local-first data plane, supported agent integrations, and a hosted coordination layer in one product. Start on one machine and keep the same Node and data model as the fleet grows.
Product map
Use one entry point for the product, then go deeper where needed.
Use cases, architecture, integrations, and comparisons remain focused pages, but they now sit under one Product entry instead of competing as separate primary navigation items.
Architecture
A distributed, local-first data plane.
Keep detailed runtime evidence on customer-controlled Nodes and Site Gateways while the hosted coordination plane handles identity, connectivity, fleet access, policy, and collaboration.
See the architecture →Integrations
Use the agents and runtimes you already have.
Connect AgentSight to supported coding agents, local CLIs, process families, containers, and existing observability workflows without rebuilding the agent around an SDK.
Browse integrations →Compare
Understand where AgentSight sits in the stack.
Compare system-boundary runtime evidence with application traces, OpenTelemetry, gateways, hosted LLM observability, and other adjacent approaches.
Compare approaches →Distributed by architecture
Keep execution evidence close to the agents that produced it.
AgentSight scales by coordinating customer-owned Nodes and Site Gateways rather than requiring every detailed session to become a second copy in a centralized telemetry warehouse.
- 01Observe locally
Capture and query detailed runtime evidence on the Node.
- 02Coordinate fleets
Use identity, discovery, connectivity, policy, and collaboration across machines.
- 03Federate at scale
Use Site Gateways for large customer-controlled deployments.