Skip to content

docs(observability): add Future AGI as a supported OTLP backend #2621

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SuhaniNagpal7 wants to merge 1 commit into
base: main
Choose a base branch
from
+96 −0
Open

docs(observability): add Future AGI as a supported OTLP backend #2621

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 48 additions & 0 deletions docs/development/agent-integration/observability.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,10 +192,58 @@ Check your Langfuse project dashboard for incoming traces and metrics.

</Steps>

### Enable Future AGI Observability

[Future AGI](https://futureagi.com) is an open-source e2e agent engineering and optimization platform that helps you ship self-improving AI agents. Its tracer endpoint accepts OpenTelemetry OTLP/HTTP, so you can route Agent Stack traces to it through the same collector config used for Langfuse.

<Steps>

<Step title="Get Future AGI credentials">
1. Sign up at [app.futureagi.com](https://app.futureagi.com)
2. From your dashboard, copy your `FI_API_KEY` and `FI_SECRET_KEY`
</Step>

<Step title="Create a configuration file (config.yaml):">
```yaml
collector:
exporters:
otlphttp/futureagi:
endpoint: "https://api.futureagi.com/tracer/v1/traces"
headers:
x-api-key: "${FI_API_KEY}"
x-secret-key: "${FI_SECRET_KEY}"
pipelines:
traces:
receivers: [ otlp ]
processors: [ memory_limiter, batch ]
exporters: [ otlphttp/futureagi ]
Comment on lines +208 to +219
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot May 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For consistency with the Langfuse section and to avoid potential issues with environment variable propagation to the collector container, it is recommended to use literal placeholders for credentials. Additionally, the filter/phoenix processor should be included in the pipeline to filter out internal instrumentation noise, ensuring cleaner traces in the Future AGI dashboard.

collector:
  exporters:
    otlphttp/futureagi:
      endpoint: "https://api.futureagi.com/tracer/v1/traces"
      headers:
        x-api-key: "<YOUR_FI_API_KEY>"
        x-secret-key: "<YOUR_FI_SECRET_KEY>"
  pipelines:
    traces:
      receivers: [ otlp ]
      processors: [ memory_limiter, filter/phoenix, batch ]
      exporters: [ otlphttp/futureagi ]

```
</Step>

<Step title="Start the platform with the configuration">
```bash
FI_API_KEY=your_api_key \
FI_SECRET_KEY=your_secret_key \
agentstack platform start -f config.yaml
Comment on lines +225 to +227
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot May 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Since the configuration file now uses placeholders for credentials (matching the Langfuse example), the environment variables can be removed from the start command.

agentstack platform start -f config.yaml

```
</Step>

<Step title="Run and View">

Execute an agent to generate data:
```sh
agentstack run chat "Hello"
```
Open your project in the [Future AGI dashboard](https://app.futureagi.com) to inspect traces, prompts, completions, and tool execution details.
</Step>

</Steps>

## Additional Resources

- **OpenTelemetry Docs**: https://opentelemetry.io/docs/
- **Langfuse Docs**: https://langfuse.com/docs
- **Phoenix Docs**: https://docs.arize.com/phoenix
- **Future AGI Docs**: https://docs.futureagi.com
- **Prometheus Docs**: https://prometheus.io/docs/
- **Grafana Docs**: https://grafana.com/docs/
48 changes: 48 additions & 0 deletions docs/stable/agent-integration/observability.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,10 +192,58 @@ Check your Langfuse project dashboard for incoming traces and metrics.

</Steps>

### Enable Future AGI Observability

[Future AGI](https://futureagi.com) is an open-source e2e agent engineering and optimization platform that helps you ship self-improving AI agents. Its tracer endpoint accepts OpenTelemetry OTLP/HTTP, so you can route Agent Stack traces to it through the same collector config used for Langfuse.

<Steps>

<Step title="Get Future AGI credentials">
1. Sign up at [app.futureagi.com](https://app.futureagi.com)
2. From your dashboard, copy your `FI_API_KEY` and `FI_SECRET_KEY`
</Step>

<Step title="Create a configuration file (config.yaml):">
```yaml
collector:
exporters:
otlphttp/futureagi:
endpoint: "https://api.futureagi.com/tracer/v1/traces"
headers:
x-api-key: "${FI_API_KEY}"
x-secret-key: "${FI_SECRET_KEY}"
pipelines:
traces:
receivers: [ otlp ]
processors: [ memory_limiter, batch ]
exporters: [ otlphttp/futureagi ]
Comment on lines +208 to +219
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot May 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For consistency with the Langfuse section and to avoid potential issues with environment variable propagation to the collector container, it is recommended to use literal placeholders for credentials. Additionally, the filter/phoenix processor should be included in the pipeline to filter out internal instrumentation noise, ensuring cleaner traces in the Future AGI dashboard.

collector:
  exporters:
    otlphttp/futureagi:
      endpoint: "https://api.futureagi.com/tracer/v1/traces"
      headers:
        x-api-key: "<YOUR_FI_API_KEY>"
        x-secret-key: "<YOUR_FI_SECRET_KEY>"
  pipelines:
    traces:
      receivers: [ otlp ]
      processors: [ memory_limiter, filter/phoenix, batch ]
      exporters: [ otlphttp/futureagi ]

```
</Step>

<Step title="Start the platform with the configuration">
```bash
FI_API_KEY=your_api_key \
FI_SECRET_KEY=your_secret_key \
agentstack platform start -f config.yaml
Comment on lines +225 to +227
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot May 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Since the configuration file now uses placeholders for credentials (matching the Langfuse example), the environment variables can be removed from the start command.

agentstack platform start -f config.yaml

```
</Step>

<Step title="Run and View">

Execute an agent to generate data:
```sh
agentstack run chat "Hello"
```
Open your project in the [Future AGI dashboard](https://app.futureagi.com) to inspect traces, prompts, completions, and tool execution details.
</Step>

</Steps>

## Additional Resources

- **OpenTelemetry Docs**: https://opentelemetry.io/docs/
- **Langfuse Docs**: https://langfuse.com/docs
- **Phoenix Docs**: https://docs.arize.com/phoenix
- **Future AGI Docs**: https://docs.futureagi.com
- **Prometheus Docs**: https://prometheus.io/docs/
- **Grafana Docs**: https://grafana.com/docs/