docs: list Agent Action Capsule (capsule-emit) in the observability integrations
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 58.8k
- Forks
- 8.5k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 109
Description
Feature Area
Documentation
Is your feature request related to an existing bug?
Not a bug. This is a documentation/integration request, opened per the first-time-contributor process to accompany PR #7113.
Describe the solution you'd like
Add a short page to the observability integrations docs for capsule-emit (CapsuleEventListener), an open-source event-bus listener that records each CrewAI step as a signed, content-addressed Agent Action Capsule — audit evidence that a third party can verify offline, complementary to tracing. The listener attaches via CrewAI's standard event bus (no core changes), sealing a planned/executed/failed chain per step.
It sits alongside the other observability vendors already listed (AgentOps, Langfuse, etc.) — same shape: a short page pointing at the integration's own docs. PR #7113 has the page, executed against the released package.
Additional context
Disclosure: the page and this issue were drafted with AI assistance under human review — please apply the llm-generated label (I don't have permission to set it as a first-time contributor). I co-maintain capsule-emit and am engaged by its sponsoring project; that's stated in the PR.
Willingness to contribute
Yes, I'd be happy to submit a pull request (already open as #7113).
Contributor 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.
Research direction
Start with PR #7113 and the existing observability integrations pages. Confirm that the capsule-emit page follows the same short-page format and links to the integration's own documentation; done means the integration is listed alongside vendors such as AgentOps and Langfuse.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 25/100