--- title: "Instrument coding agents | Grafana Cloud documentation" description: "Forward coding-agent sessions to Agent Observability without writing SDK code." --- > For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt). # Instrument coding agents Coding-agent plugins forward sessions from the coding agent you already use into Agent Observability. Each session shows up there as generations, tool calls, and metrics. ## Supported coding agents For the full list of supported coding agents and per-plugin install instructions, refer to [`grafana/agento11y/plugins`](https://github.com/grafana/agento11y/tree/main/plugins). ## Before you begin - AI Observability is enabled on a Grafana Cloud stack. Refer to [Use AI Observability on Grafana Cloud](/docs/grafana-cloud/machine-learning/agent-observability/get-started/grafana-cloud) to enable the plugin and collect credentials. - The `agento11y` CLI is installed and on your `PATH`: - On Linux and macOS, use the install script: Bash ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```bash curl -fsSL https://raw.githubusercontent.com/grafana/agento11y/main/plugins/agento11y/scripts/install.sh | sh ``` The script downloads the latest release for your OS and architecture, verifies its SHA-256 checksum, and installs the binary to `~/.local/bin`. Make sure that directory is on your `PATH`. - On macOS, you can also use Homebrew: Bash ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```bash brew install grafana/grafana/agento11y ``` - On Windows, download the `windows_amd64` or `windows_arm64` zip from the [releases page](https://github.com/grafana/agento11y/releases), extract `agento11y.exe`, and put it on your `PATH`. - On any platform with Go 1.25 or later, you can use `go install`: Bash ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```bash go install github.com/grafana/agento11y/plugins/agento11y/cmd/agento11y@latest ``` `go install` puts the binary in `go env GOPATH`/bin (or `GOBIN`). Make sure that directory is on your `PATH`. ## Configure credentials Run `agento11y login`, or run the launcher for your coding agent (such as `agento11y pi`, `agento11y claude`, or `agento11y codex`). On the first launch, the launcher runs the same login flow automatically. Both write to `~/.config/agento11y/config.env`, the shared configuration file that every coding-agent plugin reads. Later launches reuse it, and you can re-run `agento11y login` any time to change a value. The interactive prompt has two steps: 1. **Connection details**: your Grafana Cloud endpoint (the plugin’s **API URL**), tenant ID (the **Instance ID**), token, and OTLP endpoint. Find these in Grafana Cloud at `https://.grafana.net/plugins/grafana-agento11y-app`. 2. **Preferences**: content capture mode, session tags, and guards. Every field defaults to the plugin’s current behavior, so press Enter through this step to keep the defaults. If you can’t run an interactive prompt (for example, in CI, a container, or a scripted setup), write the configuration file directly instead. Refer to [Configure without the prompt](#configure-without-the-prompt). ## Content capture By default, plugins send only metadata: model, token usage, tool names, and timing. Prompts, responses, and tool I/O stay on your machine. To also send prompts and responses, with automatic secret redaction, set the **Content capture** field to **Full** when you run `agento11y login`. The modes are `metadata_only` (default) and `full`. You can also set `AGENTO11Y_CONTENT_CAPTURE_MODE` directly. Refer to [Configure without the prompt](#configure-without-the-prompt). ## Enable guards Guards run synchronous checks on tool calls before they execute. When guards are enabled, tool calls that fail evaluation are blocked. Refer to [Set up guards](/docs/grafana-cloud/machine-learning/agent-observability/guides/guards) for guard rule configuration. Guards are off by default. To turn them on, set the **Guards** field in `agento11y login`: - **Enabled, fail-open**: transport errors and timeouts let the tool call through. This is the safer choice when you first turn guards on. - **Enabled, fail-closed**: a guard error or timeout blocks the tool call. The **Guard timeout** field sets how long to wait for a guard before applying the fail mode (default `1500` ms). Raise it to tolerate slow evaluators, or lower it to cap per-call latency. The timeout applies only when guards are enabled. ## Configure without the prompt `agento11y login` is interactive and needs a terminal. For non-interactive setups, such as CI, containers, or dotfiles, write `~/.config/agento11y/config.env` directly. Each prompt maps to an environment variable: dotenv ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```dotenv # Connection (required) AGENTO11Y_ENDPOINT=https://agento11y-prod-.grafana.net AGENTO11Y_AUTH_TENANT_ID= AGENTO11Y_AUTH_TOKEN=glc_ # OTLP endpoint for SDK traces and metrics (optional) AGENTO11Y_OTEL_EXPORTER_OTLP_ENDPOINT=https://otlp-gateway-prod-.grafana.net/otlp # Preferences (optional; defaults shown) # Modes: metadata_only | full AGENTO11Y_CONTENT_CAPTURE_MODE=metadata_only AGENTO11Y_TAGS=team=ai,project=demo # applied to every generation AGENTO11Y_GUARDS_ENABLED=false AGENTO11Y_GUARDS_FAIL_OPEN=true # only used when guards are enabled AGENTO11Y_GUARDS_TIMEOUT_MS=1500 # only used when guards are enabled ``` Find the connection values in Grafana Cloud at `https://.grafana.net/plugins/grafana-agento11y-app`. ## Verify Run a turn in your coding agent, then open **Conversations** in the Agent Observability plugin. The generation appears within a few seconds. If nothing appears, enable debug logging and tail the log. For example, for Pi: Bash ![Copy code to clipboard](/media/images/icons/icon-copy-small-2.svg) Copy ```bash AGENTO11Y_DEBUG=true agento11y pi tail -f ~/.local/state/agento11y/logs/agento11y.log ``` Check the following: - `agento11y --version` resolves on your `PATH`. - The endpoint, tenant ID, and token are set in `~/.config/agento11y/config.env`. - The access policy token has the `sigil:write` scope. ## Next steps - [Browse conversations](/docs/grafana-cloud/machine-learning/agent-observability/guides/conversations) - [Set up guards](/docs/grafana-cloud/machine-learning/agent-observability/guides/guards) - [Use the agent catalog](/docs/grafana-cloud/machine-learning/agent-observability/guides/agent-catalog) - [Use built-in dashboards](/docs/grafana-cloud/machine-learning/agent-observability/guides/dashboards)