Home / opal
xingjian-bai/opal
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
PythonCategories: Coding agents
Our summary
OPAL is a PyTorch optimizer wrapper. A coding agent (Claude Code) can rewrite the optimizer's update program and an analysis program while a model trains. The wrapped run matches the plain run until the agent changes something.
Who it is for: PyTorch users who want to train models with an optimizer that an agent adjusts during training.
What the README claims
- Wrapping an optimizer leaves the run bit-for-bit identical to the plain run until the agent changes something.
Until the agent changes something, the wrapped run is bit-for-bit the same as the plain one.
Not checked - The agent is asked to leave the model, data, loss, batch size, step count and evaluation unchanged.
It is asked not to touch your model, data, loss, batch size, number of steps or evaluation.
Not checked - A new optimizer program runs on trial for 20 steps and reverts to the previous program if it raises an error.
runs on trial for 20 steps. If it raises an error, the run goes back to the previous program.
Not checked - Improved final metrics on several example runs, such as FID 23.6 versus 35.7 for SiT-B/2.
| SiT-B/2, ImageNet 256, 400K updates | FID-50K ↓ | 35.7 (ADM evaluator; the SiT paper reports 33.0) | 23.6 |
Not checked - Its overhead is roughly fixed per agent decision, so it suits long runs and is costly in short ones.
**Long runs suit it best.** An agent decision takes about the same time in any run, about 40 s on average in ours,
Not checked
Written by AI from the project's README on 2026-11-09. It does not affect the verdict.
Watching: no other rule matched yet.
7-day star gain 18, down from 84 the week before.
PyPI downloads on the latest day: 9, down from 12 a week earlier.
Gaining 18 stars this week. Last push 9 days ago.
Verdict
MID scored 51m ago
- Hype
- 52
- Reality
- 59
- Hype Gap
- -7
- Momentum
- -
- Confidence
- 85%
- Responsive moves Reality +6 points.
- Adopted moves Reality -4 points.
- Maintained moves Reality -0 points.
Rule verdict-2.0, scoring score-2.0. How we score. Backtest.
Repository on GitHub Project homepage
Maintained by
Maintained by 1 primary developer, 1 external contributor in the last 90 days.
- xingjian-bai is a GitHub individual account.
- GitHub account created November 2021.
- Top contributors by commits: xingjian-bai 97%, mvanhorn 3%.
Why now 4% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
- Stars StarsThe number of GitHub stars on the repository at our latest reading.
- 480
- Gain 7d Gain 7dStars gained since our latest reading from at least 7 days ago.
- +18
- Pace Velocity (Nx usual pace)This week's star gain divided by the project's usual weekly gain. The usual gain is the average weekly gain over the 4 weeks before (days 8 to 35 ago), counted as at least 10 stars. 2.0x means twice the usual pace. Without a reading from 35 days ago, the ranking assumes 2% of the stars the project had 7 days ago as its usual weekly gain. More on the methodology page
- 1.8x
- HN points HN pointsHacker News points added up across posts that mention the project, published in the last 7 days.
- 0 7 days
- Downloads DownloadsDownloads per day of the project's package, as the registry (npm or PyPI) reports them.
- 9 latest day
- Contributors Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.
- 2
- Last release Latest releaseDays since the latest GitHub release was published.
- 18 days ago
Gain 24h Gain 24hStars gained since our latest reading from at least 24 hours ago. 0. Forks ForksThe number of GitHub forks of the repository at our latest reading. 29. Open issues Open issuesThe number of open issues on the repository at our latest reading, as GitHub counts them. 0. Days since push Days since pushDays since the last push to the repository. 9 days. Archived ArchivedWhether the owner has archived the repository on GitHub. An archived repository is read-only. no. Hacker News posts in 7 days Hacker News postsThe number of Hacker News posts that mention the project, published in the last 7 days.: 0. Watchers WatchersThe number of GitHub users watching the repository for notifications, at our latest reading. 1.
Facts
- License
- MIT source, checked 21 Nov 2026
- Language
- Python source, checked 21 Nov 2026
- Homepage
- https://xingjianbai.com/reactive-optimizers/ source, checked 21 Nov 2026
- Last release
- v0.3.10, 3 Nov 2026 source, checked 21 Nov 2026
- Releases
- 6 source, checked 19 Nov 2026
- Contributors
- 2 source, checked 19 Nov 2026
- Archived
- no source, checked 21 Nov 2026
Nerd stuff
PythonCLI
- Languages
- Python (detected)
- Stack
- PyTorch >=2.6; python_version >= '3.13' (detected)
- Runs on
- Python >=3.10 (detected)
- Interfaces
- CLI (detected)
- Docs
- docs/ folder (detected), examples/ folder (detected)
- License
- MIT (detected)
- Package ecosystem
- Python packaging (detected)
The Receipts
| Source | Evidence | Date |
|---|---|---|
| Package | PyPI opal-optimizer | 21 Nov 2026 |
| deps.dev | Dependent packages on PyPI: 0 | 22 Nov 2026 |
| deps.dev | Security advisories on PyPI: 0 | 22 Nov 2026 |
What changed recently
GitHub release dates we stored. We do not track license changes yet.
Cite this
opal is a GitHub project at https://github.com/xingjian-bai/opal written mainly in Python, described there as "OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains".
Source: https://midorreal.com/project/xingjian-bai-opal, checked 22 November 2026. The same facts as JSON: /project/xingjian-bai-opal.json.
Rank history
Peak day: +48 stars on 3 Nov 2026, 19 days ago.
Best rank on Blowing up: #92 on 9 Nov 2026.
Stars
PyPI downloads
Packages
| Registry | Package |
|---|---|
| PyPI | opal-optimizer |
Only packages whose registry page links back to this repository are listed.
Signals
| Source | What we measured | Checked |
|---|---|---|
| GitHub | 480 stars, 18 gained in 7 days | 21 Nov 2026 |
| Hacker News | No posts stored | - |
| Feed mentions | Not tracked yet | - |
| npm | No linked package found | - |
| PyPI | 9 downloads on the latest day | 21 Nov 2026 |
| Docker Hub | No linked package found | - |
| crates.io | No linked package found | - |
| Homebrew | No linked package found | - |
| deps.dev | 0 PyPI dependents | 22 Nov 2026 |
| Hugging Face | Not tracked yet | - |
| Bluesky | Not tracked yet | - |
| Stack Exchange | Not tracked yet | - |
| YouTube | Not tracked yet | - |
Attention vs adoption
Attention: above 77% of tracked projects
Star velocity against all tracked projects
Adoption: above 30% of tracked projects
Strongest of downloads, dependents and pulls (PyPI)
Attention runs ahead of adoption: star velocity above 77% of tracked projects, best adoption figure above 30%. This describes the numbers; it is not a verdict.
Compared with Coding agents
| Measure | This project | Category median |
|---|---|---|
| Star velocity | 1.8 | 0.4 |
| Days since release | 17.7 | 4.5 |
| Contributors, all time | 2 | 2 |
| Median time to first reply on issues | no data | 14 hours |
| Commits in the last 30 days | 66 | 48 |
Star velocity: above 78% of Coding agents projects
Days since release: above 76% of Coding agents projects
Contributors, all time: above 43% of Coding agents projects
Commits in the last 30 days: above 63% of Coding agents projects
Compared with the project's first category only. A percentile line appears only where at least 30 projects in the category have the measure. This describes the numbers; it is not a verdict.
Compare with
Hacker News
| Post | Points PointsThe points the post has on Hacker News. | Comments CommentsThe number of comments on the post on Hacker News. | Date |
|---|---|---|---|
| No Hacker News posts mention it in the last 7 days. | |||
Caveats
Repo health
- Languages LanguagesShare of the repository's code by bytes, as GitHub's language detection reports it. The five biggest languages are named and the rest are grouped as Other.Python 100%
- License LicenseThe SPDX license id GitHub detects, and a class: Open source (OSI) if the license is on the Open Source Initiative approved list, Source-available if the code is readable but the license limits use, Unclear if GitHub cannot match a known license, No license detected if it finds none. A public repository without a license is not open source.MIT, Open source (OSI)
- Repository age Repository ageTime since the repository was created on GitHub. This is the repository, not necessarily the project, which may have existed elsewhere before.31 days, created 21 Oct 2026
- Release dates Release datesThe date of the first and the latest GitHub release, and the latest release tag. Projects that ship without GitHub releases show none.First release 22 Oct 2026, current version v0.3.10 (3 Nov 2026)
Development
- Commits in the last 7 days Commits in the last 7 daysCommits to the repository in the last 7 days, as GitHub counts them.0
- Commits in the last 30 days Commits in the last 30 daysCommits to the repository in the last 30 days, as GitHub counts them.66
- Commits in the last 90 days Commits in the last 90 daysCommits to the repository in the last 90 days, as GitHub counts them.66
- Contributors, all time Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.2, a small team
- Releases ReleasesThe number of GitHub releases, and how many days ago the latest one was published.6, latest release 18 days ago
- Releases in the last 90 days Releases in the last 90 daysHow many GitHub releases were published in the last 90 days.6
- Issues in the last 30 days Issues in the last 30 daysIssues opened and issues closed in the last 30 days, as GitHub search counts them.6 opened, 6 closed
- Pull requests merged in the last 30 days Pull requests merged in the last 30 daysPull requests merged in the last 30 days, as GitHub search counts them.2
- Packages that depend on the latest version Packages that depend on the latest versionHow many other packages list the project's latest published version as a dependency, from deps.dev, added up across npm and PyPI.0
Maintenance
- Median time to close issues Median time to close issuesMedian time from opening to closing, over a sample of the last 30 closed issues.16 hours
- Sampled issues with no reply Sampled issues with no replyHow many of the sampled closed issues never got a comment from someone other than their author.6 of 6
- Stale open issues Stale open issuesOpen issues with no update in the last 90 days, as GitHub search counts them.0
- Open pull requests Open pull requestsPull requests open now, as GitHub search counts them.0
Hygiene
- Automated tests or builds (CI) Automated tests or builds (CI)Whether the repository has at least one GitHub Actions workflow file in .github/workflows.Yes
- A tests folder A tests folderWhether the repository has a top-level folder named tests, test, __tests__ or spec.Yes
- A license A licenseWhether GitHub detects a license file in the repository.Yes
- Contributing guide Contributing guideWhether the repository has a contributing guide.Yes
- Code of conduct Code of conductWhether GitHub finds a code of conduct in the repository.No
- CODEOWNERS file CODEOWNERS fileWhether the repository has a CODEOWNERS file, which names who reviews changes to which files.No
- A Dockerfile A DockerfileWhether the repository has a Dockerfile at its top level.No
Security
- Security policy Security policyWhether the repository has a SECURITY.md or SECURITY.rst file.No
- Unpatched high or critical advisories Unpatched high or critical advisoriesPublished GitHub security advisories rated high or critical on this repository that list a vulnerable version with no patched version.0
- Signed latest release Signed latest releaseWhether the latest GitHub release has an attached signature file (.sig, .asc or .sigstore).No
- Known advisories on the latest version Known advisories on the latest versionSecurity advisories deps.dev lists against the project's latest published version, added up across npm and PyPI.0
Badge
For maintainers: one measured fact, no verdict.
Markdown
[](https://midorreal.com/project/xingjian-bai-opal)
HTML
<a href="https://midorreal.com/project/xingjian-bai-opal"><img src="https://midorreal.com/badge/xingjian-bai-opal.svg" alt="Mid or Real"></a>
Verdict badge: It shows the verdict as this page shows it today.
Markdown
[](https://midorreal.com/project/xingjian-bai-opal)
HTML
<a href="https://midorreal.com/project/xingjian-bai-opal"><img src="https://midorreal.com/badge/xingjian-bai-opal.svg?style=verdict" alt="Mid or Real: MID"></a>
Passport
Copy these facts into a post, a README or a page. Cite as "Source: Mid or Real". Full record: JSON.
First tracked 25 Oct 2026 at 197 stars.
- GitHub data 24 h old
- Hacker News data 5 min old, no posts found
Is this your project? Claim it
Figures by method 1.0