[FEA] Add a Future AGI OTLP telemetry exporter (futureagi)
Maintainers usually reply within 1 day
@nik13 is already working on this.
Since Oct 29, 2026.
Assessment
This issue has not been assessed yet.
Description
Is this a new feature, an improvement, or a change to existing functionality?
New Feature
How would you describe the priority of this feature request
Medium
Please provide a clear description of problem this feature solves
Teams sending NeMo Agent Toolkit traces to Future AGI currently need to configure the generic exporter themselves: an OTLP/HTTP endpoint, two authentication headers (X-Api-Key and X-Secret-Key), and a project_name resource attribute. A named exporter would make that setup discoverable alongside the other observability backends.
Describe your ideal solution
Add a futureagi exporter to nvidia_nat_opentelemetry, following the existing Arize AX and MLflow exporter patterns:
- project name, API key, secret key, and optional endpoint configuration, with environment-variable fallbacks;
- uncompressed OTLP/HTTP to the Future AGI
/tracer/v1/tracesendpoint, withproject_nameon the resource; - an observe guide, a calculator-observability example, a telemetry-exporters table entry, and tests.
Would this be welcome? We will wait for agreement on scope before opening the upstream PR. No additional Future AGI instrumentor dependency is proposed.
Additional context
This follows the earlier request #972, which is closed. We would address the feedback on #1090 rather than reopen the old PR: consistent configuration fields, no unrelated version/evaluation attributes, and the missing example and documentation entries. The eventual commits must satisfy the repository's DCO requirement; this issue does not assert that the prepared branch already does.
I work at Future AGI. AI assistance was used to research and draft this proposal.
Code of Conduct
- I agree to follow this project's Code of Conduct.
- I have searched the open feature requests and found no open duplicate; the closed predecessor is linked above.
- Dominant language
- Python
- Stars
- 2.7k
- Forks
- 814
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 131
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from NVIDIA/NeMo-Agent-Toolkit
-
Alert triage agent: the HTTP server (run.py) starts every triage with a config file that does not existPossibly taken @trackoor claimed this today. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
NVIDIA/NeMo-Agent-Toolkit#2536 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
NVIDIA/NeMo-Agent-Toolkit#2534 · 1 comment ·
Maintainers usually reply within 1 day
-
[BUG]: HuggingFace embedder remote mode fails to initialize (endpoint_url rejected as model and timeout dropped)Possibly taken @Bhumit267 claimed this today. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 25/100
NVIDIA/NeMo-Agent-Toolkit#2541 ·
Maintainers usually reply within 1 day
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 45/100
NVIDIA/NeMo-Agent-Toolkit#2539 ·
Maintainers usually reply within 1 day
-
MCP client: let tool errors reach agent error handling, and keep structured-only resultsPossibly taken @Sushmit404 claimed this 17 days ago. Openfeature request Needs Triage
Difficulty 4/5 3-5 days Newbie friendliness 25/100
NVIDIA/NeMo-Agent-Toolkit#2362 ·
Maintainers usually reply within 1 day
All issues in NVIDIA/NeMo-Agent-Toolkit
Similar issues
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
aws/sagemaker-python-sdk#6554 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
huggingface/diffusers#15170 ·
Maintainers usually reply within 1 day
-
[BUG] LLM conflict check ignores MNEMOSYNE_LLM_MAX_TOKENS, so reasoning models return empty repliesOpen
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
mnemosyne-oss/mnemosyne#1325 ·
Maintainers usually reply within 1 day
-
enhancement meshtastic-2.8
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
pskillen/meshflow-api#459 ·