Add a Smol Machines local and cloud SandboxAgent example
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- Half a day
- Newbie friendliness
- 22/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- python
- Domain
- ai-infra-agents
Research direction
The example is already prepared on the linked fork branch at commit 79c897d, so the work is to review and integrate that branch rather than write it from scratch. Read the provider contract and the example's manifest and shell-capability setup on that branch. Contribution is limited to collaborators and the install command depends on smol-machines/smol#267 being released, so a newcomer cannot finish this alone. Done means a collaborator merges the example after that release.
Written by the indexing model from the issue text.
Description
Smol Machines can run the same SandboxAgent workspace in a local microVM or a cloud microVM. A standalone example shows how to stage a small manifest, enable the shell capability, and switch targets without giving the guest model or cloud credentials.
The example is prepared on my fork branch (commit 79c897d). Its provider contract passed local and Cloud VM runs that materialized and read the example workspace. The full repository format, lint, typecheck, parallel test, and serial test stack passed. The example's model call still needs a host OPENAI_API_KEY for a live end-to-end run.
The published installation command depends on smol-machines/smol#267 being merged and released. The contribution policy limits pull requests to collaborators; the branch is available for a collaborator to pick up after the provider release.
- Dominant language
- Python
- Stars
- 29.9k
- Forks
- 4.8k
- Avg merge
- 22h 17m
- Merged PRs (30d)
- 208
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 openai/openai-agents-python
-
Difficulty 2/5 1-3 hours Newbie friendliness 77/100
openai/openai-agents-python#5348 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
openai/openai-agents-python#5353 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 Half a day Newbie friendliness 70/100
openai/openai-agents-python#5342 · 3 comments ·
Maintainers usually reply within 1 day
-
enhancement
Difficulty 3/5 1-2 days Newbie friendliness 65/100
openai/openai-agents-python#5336 · 1 comment ·
Maintainers usually reply within 1 day
-
Finished tool call is dropped when a parallel tool's guardrail tripsPossibly taken @jbeckwith-oai claimed this 6 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 35/100
openai/openai-agents-python#5327 · 1 comment ·
Maintainers usually reply within 1 day
All issues in openai/openai-agents-python
Similar issues
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
uniswap-python/uniswap-python#487 ·
-
[Bug]: agent_final_response still returns the abandoned branch's answer after navigate moves HEAD backPossibly taken @enyst claimed this today. Openbug priority:low ready-for-dev
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
OpenHands/software-agent-sdk#5822 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
-
area: server enhancement good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
scs0209/laya-guard#52 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 2 days