@mrrlin-dev/external-agents
Related Servers
Alternatives to @mrrlin-dev/external-agents
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenancePools 178 enabled chat routes across 23 LLM providers behind a single OpenAI-compatible (plus experimental Anthropic-compatible) endpoint, so coding agents and existing apps can run on free tiers with automatic failover, usage tracking, and no API keys when a keyless route is live. It runs as a CLI, Python library, or local proxy with optional Tailnet serving and per-agent routing.-
- FlicenseNot gradedqualityAmaintenancePools enabled free-tier, keyless, and trial LLM chat routes behind a single OpenAI-compatible endpoint with automatic failover and local usage tracking, so coding agents and OpenAI/Anthropic-compatible tools can run on free models without changing their code. It also exposes provider health, capacity, model inventory, and routing-mode tooling so clients can discover and use whichever chat routes are currently accessible, including some that require no API key.-
- FlicenseNot gradedqualityAmaintenancePools free and keyless LLM providers behind a single OpenAI-compatible endpoint, letting agents send chat requests that automatically fail over across usable routes. Exposes model discovery and pool-status tools so coding agents can pick and query available free models directly.-
- FlicenseNot gradedqualityAmaintenancePools enabled free-tier and keyless LLM chat routes behind a single OpenAI-compatible (plus experimental Anthropic-compatible) endpoint, letting coding agents and existing OpenAI-compatible clients query many providers with automatic failover, latency-aware routing, and local per-day usage tracking, even starting without credentials when a keyless route is up.-
- FlicenseNot gradedqualityAmaintenanceExposes 178 enabled chat routes across 23 cataloged LLM providers behind one OpenAI-compatible endpoint, so agents can query pooled free-tier and keyless models with automatic failover and per-day usage tracking. It can also report live provider capacity and health when a route is rate limited or down.-
- FlicenseNot gradedqualityAmaintenancePools enabled free chat routes across many LLM providers behind a single OpenAI-compatible endpoint, letting coding agents and OpenAI/Anthropic-compatible tools run on free models with automatic failover. It can start without credentials when a keyless route is available, and exposes routing, provider health, and live probing commands.-
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes: probe_agent mutates state via install-check, get_stats reads telemetry, set_credential writes keys, pick_agents selects candidates, dispatch runs them. The one soft overlap is get_state vs list_agents, both returning agent state (one raw state file, one merged with config), which an agent could occasionally conflate.
Consistent snake_case and predominantly verb_noun (get_state, list_agents, probe_agent, set_credential, pick_agents). Minor deviations are bare verbs 'ping' and 'dispatch', which still read naturally in context.
Eight tools is well-scoped for an agent-discovery/dispatch server: health, listing, probing, credentials, selection, execution, telemetry, and a liveness check. Each earns its place with no redundant filler.
Core lifecycle is covered: discover agents, check/probe health, set credentials, select candidates, dispatch, and inspect telemetry. Minor gaps exist—no way to add/remove/disable agents or cancel an in-flight dispatch—but agents can work around these via config files.