random-agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_OS_BASE_PATH | No | Base path for all agent data | C:\agent-os |
| AGENT_OS_MAX_WORKERS | No | Max concurrent worker processes | 5 |
| AGENT_OS_LOOP_INTERVAL | No | Coordinator loop interval (seconds) | 5 |
| AGENT_OS_STALL_THRESHOLD | No | Seconds before worker is considered stuck | 90 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| statusA | Get live status: coordinator, queue counts, workers |
| logsB | Read real log files from the agent-os system |
| metricsB | Read real metrics from the metrics database |
| injectC | Inject a task into the pending queue |
| handle_stuckA | Detect stuck/failed workers, kill them, and retry |
| coordinatorB | Start, stop, or restart the coordinator |
| orchestrateB | Orchestrate a complex task: decompose, inject subtasks, monitor, return results |
| assertB | Run output comparison assertions on tasks or arbitrary text |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Tools are mostly distinct: metrics, status, and logs each read different data sources (DB, live coordinator state, files), while inject, orchestrate, handle_stuck, and coordinator manage different aspects of the system. However, metrics and status could be confused for overlapping system information.
Tool names mix nouns (metrics, status, logs, coordinator) with imperative verbs (inject, handle_stuck, orchestrate, assert). There is no consistent verb_noun or noun_verb pattern, making the set feel ad hoc.
Eight tools is well within the ideal 3-15 range for this domain. Each tool serves a distinct operational purpose without redundancy or bloat.
The set covers core operations: observability (metrics, status, logs), task injection, failure recovery, coordinator control, high-level orchestration, and assertion. Minor gaps exist (e.g., no direct task result retrieval outside orchestrate), but workflows are largely complete.