A marketplace of OpenTelemetry agent plugins in the Agent Plugins format, run by the repository itself: submit a plugin once; the repository checks it, lists it and follows its releases.

Add the marketplace to your client:

claude plugin marketplace add using-system/otelyssey
copilot plugin marketplace add using-system/otelyssey
codex plugin marketplace add using-system/otelyssey
grok plugin marketplace add using-system/otelyssey
apm marketplace add using-system/otelyssey
hermes plugins pack install https://raw.githubusercontent.com/using-system/otelyssey/main/hermes-pack.yaml

Then pick a plugin below: its page has the install line — and the ones for VS Code, Kiro, OpenClaw and Mistral Vibe.

Open a plugin submission — one form, the repository does the rest.

Your plugin needs:

• a public GitHub repository;
• a plugin.json in the Agent Plugins format, at the repository's root or in a subdirectory: the form asks for its URL, everything else is read from it;
• OpenTelemetry as its subject: instrumentation, semantic conventions, the Collector, or a backend that ingests its telemetry.

The repository answers on the issue. Once listed, it follows your releases every night. Bugs, ideas, code: see CONTRIBUTING.

Read it back: observe a run through its telemetry, wherever it lands.

• oddyssey by using-system — CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop. · also in Instrumentation, Backends
        

• save-toolkit by latent-sre — Application-engineering and site-reliability agents and reusable skills. · also in Backends, Instrumentation, Collector
        

Put the telemetry in: SDKs, semantic conventions, instrumentation advice.

• observability by Basti Ortiz — Opinionated guidance for clear and operationally useful OpenTelemetry instrumentation.
        

• opentelemetry-agent-skills by OllyGarden — Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources: SDK setup per language, the Collector and OCB, OTTL, declarative configuration, semantic conventions, upgrades and migrations. · also in Collector
        

• otel-instrumentation-skills by Rob Knight — OpenTelemetry signal quality with durable workflows and fresh, version-correct upstream evidence. · also in Collector
        

• stdtel by amiable-dev — Telemetry for standards-as-skills: attributes token cost and policy outcomes to individual skills across Claude Code and GitHub Copilot. · also in Backends
        

• trogonstack-otel by TrogonStack — OpenTelemetry skills for naming metrics and spans following OTel Semantic Conventions
        

• vllm-on-tap by using-system — Serve vLLM presets on demand - locally, Kubernetes (KServe), Azure (Container Apps), AWS (ECS) or GCP (Cloud Run) - with their traces over OTLP, and tear them down again.
        

Talk to a backend: query it, its dashboards, alerts and issues.

• arize-phoenix by Arize AI — Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.
        

• dynatrace-managed-mcp by Dynatrace — MCP server for Dynatrace Managed (self-hosted): query logs, metrics, events, entities, problems, security vulnerabilities and SLOs across one or more clusters.
        

• langwatch by LangWatch — Records which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.
        

• oneuptime by OneUptime — Work with your OneUptime project from ChatGPT: investigate and respond to incidents and alerts, check monitors and status pages, and query logs, metrics and traces.
        

• pup by Datadog — Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.
        

• respan by Respan — Respan for ChatGPT and Codex: inspect LLM logs and traces, and manage prompts, datasets, evaluators, experiments and monitors in your Respan workspace. · also in Instrumentation
        

• sentry by Sentry — Set up Sentry, debug production issues, and configure application monitoring.
        

• signoz by SigNoz — Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
        

• sumo-logic by Sumo Logic — Query logs, alerts, dashboards, SIEM insights, and detection rules from Sumo Logic for production debugging, incident response, and security investigation
        

• trogonstack-datadog by TrogonStack — Datadog observability skills for designing, redesigning, and auditing dashboards with proper widget selection, layout patterns, template variables, and operational readiness validation using the pup CLI, and for checking metrics against Datadog's no-cost metrics before creating custom ones · also in Instrumentation