redhat-et / redhat-et/docsclaw
demo: A2A interop test with Google ADK-Go agent
Nobody has claimed this yet.
- Dominant language
- Go
- Stars
- 2
- Forks
- 1
- Avg merge
- 6h 9m
- Merged PRs (30d)
- 1
Description
Summary
Compile and run a Google ADK-Go example agent alongside DocsClaw to validate A2A interoperability between the two runtimes. This demonstrates that DocsClaw works seamlessly in heterogeneous multi-agent environments.
Motivation
Customer questions arise about why DocsClaw isn't built on Google ADK. The strongest counter-argument is model independence (ADK is Gemini-only), but we should also show concrete A2A interop: DocsClaw can delegate to ADK agents and vice versa.
Tasks
- Clone https://github.com/google/adk-go and pick a simple example agent
- Compile and run the ADK agent on one port
- Run DocsClaw on another port
- Test bidirectional A2A delegation using
a2aCLI - Document the setup in
docs/as an interop guide
Context
- DocsClaw and ADK-Go both use
a2a-gov2 for the A2A protocol - ADK-Go ships only Gemini provider; DocsClaw supports Anthropic + OpenAI
- This validates DocsClaw's positioning as a model-independent runtime that interoperates with framework-specific agents
Contributor guide
No contributing guide indexed for this repository
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 by cloning the Google ADK-Go repository and selecting a simple example agent, then run it and DocsClaw on separate ports. Use the a2a CLI to test delegation in both directions, and document the working setup and commands in docs/ as the interop guide.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- go
- Domain
- distributed-systems, documentation
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100