Good community traction and solid fundamentals. Nearly in the top tier.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Documentation
85
No CONTRIBUTING.md found (−47 pts base + up to −53 pts more for content).
→ Add a CONTRIBUTING.md telling newcomers how to get involved. Include setup, code style, test, and PR instructions.
README is present.
README documents how to install the project.
Licensed under Apache-2.0.
Engineering
77
No issue or PR templates found (−100 pts).
→ Add .github/ISSUE_TEMPLATE/ with bug_report.md and feature_request.md to guide contributors. It dramatically improves issue quality.
CI is configured (.github/workflows/_run-ci.yml).
Lockfile present (requirements.txt). Installs are reproducible.
Test files detected (miles/utils/test_wandb_utils.py).
Linter or formatter configured ([tool.ruff] / [tool.black] in pyproject.toml).
Project health
88
Dependency manifest found (pyproject.toml).
Repository has a description.
Actively maintained (pushed within the last month).
.gitignore present.
Repository health signals
Activity, community, and responsiveness at scan time
Activity
- —Commits (30d / 90d)
- 273Forks
- 0Releases
Community
- —Community health
- —authors own >50% of commits
- 1,604Watchers
Responsiveness
- 3hMedian issue response
- <1hMedian PR merge time
- 398Open issues
Repository files22 root entries
- .claude
- .githubGood: CI is configured (.github/workflows/_run-ci.yml).
- dockerGood: Environment pinned via docker/Dockerfile.
- docs
- examples
- imgs
- milesGood: Test files detected (miles/utils/test_wandb_utils.py).
- miles_plugins
- scripts
- tests
- tools
- .gitignoreGood: .gitignore present.
- .gitmodules
- .pre-commit-config.yaml
- CODE_OF_CONDUCT.mdGood: Code of conduct present.
- LICENSEGood: Licensed under Apache-2.0.
- pyproject.tomlGood: Dependency manifest found (pyproject.toml).
- README.mdGood: README is present.Good: README is well structured with multiple sections.Good: README includes screenshots or visuals. Great for first impressions.Good: README has code examples.Good: README links to a live demo or deployed app.Good: README includes status badges.Good: README documents how to install the project.Good: README documents how to run the project.
- requirements.txtGood: Lockfile present (requirements.txt). Installs are reproducible.
- setup.py
- train_async.py
- train.py