deepseek-ai/deepseek-coder vs karpathy/autoresearch
deepseek-ai/deepseek-coder shows stronger signals overall
As of June 2026, deepseek-coder shows healthier maintenance signals than autoresearch. deepseek-coder rates Healthy overall while autoresearch rates Mixed. deepseek-coder last saw a commit 7 months ago with 17+ active contributors, while autoresearch last saw a commit 3 months ago with 9+ active contributors. Neither has known critical or high-severity CVEs in its dependency tree.
Informational only. RepoPilot summarises public signals at the time of analysis. Not professional, security, or legal advice.
deepseek-ai/deepseek-coder →
Healthy across all four use cases
Permissive license, no critical CVEs, actively maintained — safe to depend on.
Has a license, tests, and CI — clean foundation to fork and modify.
Documented and popular — useful reference codebase to read through.
No critical CVEs, sane security posture — runnable as-is.
- ⚠Slowing — last commit 6mo ago
- ⚠No CI workflows detected
- ✓Last commit 6mo ago
- ✓17 active contributors
- ✓Distributed ownership (top contributor 27% of recent commits)
- ✓MIT licensed
- ✓Tests present
Computed from maintenance signals — commit recency, contributor breadth, bus factor, license, CI, tests
karpathy/autoresearch →
Missing license — unclear to depend on
no license — legally unclear; no tests detected…
no license — can't legally use code; no tests detected…
Documented and popular — useful reference codebase to read through.
no license — can't legally use code; no CI workflows detected
- ⚠Concentrated ownership — top contributor handles 78% of recent commits
- ⚠No license — legally unclear to depend on
- ⚠No CI workflows detected
- ⚠No test directory detected
- ✓Last commit 6w ago
- ✓9 active contributors
What would improve this?
- →Use as dependency Concerns → Mixed if: publish a permissive license (MIT, Apache-2.0, etc.)
- →Fork & modify Concerns → Mixed if: add a LICENSE file
- →Deploy as-is Concerns → Mixed if: add a LICENSE file
Computed from maintenance signals — commit recency, contributor breadth, bus factor, license, CI, tests
Signal-by-signal breakdown
| deepseek-coder | autoresearch | |
|---|---|---|
| Stars | 23,283 | 79,838 |
| Last commit | 7mo ago | 3mo ago |
| License | MIT | — |
| Open issues | 157 | 186 |
| Has tests | ✓ | — |
| Has CI | — | — |
| Test coverage | 28% | 0% |
| Dependency CVEs | No CVEs | No CVEs |
| Architecture grade | — | — |
| Cycles | — | — |
| Bottom-line | Healthy signals | Mixed signals |
Want the full analysis? deepseek-ai/deepseek-coder · karpathy/autoresearch
Ask AI about deepseek-ai/deepseek-coder vs karpathy/autoresearch
Open the chat with a comparison question pre-filled.