Upstar ranks GitHub repos by how fast they gain stars, topic by topic. How trending works
nuglifeleoji/Sentry
Learning to Recover from LLM Agent Failures at Test Time
Updated 54 min ago
Maintain this repo? Add this badge to your README.
Growth
- Last 24 hours
- +712
- stars
- Last 7 days
- +1k
- stars
- Last 30 days
- +1.3k
- stars
- Total stars
- 1,256
- created 20 days ago
- Forks
- 103
Top 3 in LLM this week
- 1 xerj-org/xerj +8.1k stars this week
- 2 eagle-hq/EAGLE-4 +740 stars this week
- 3 nuglifeleoji/Sentry +1k stars this week
This repo: #3 of 365 this week, #1 of 107 today, #8 of 655 this month.
Also this week: #6 in AI agents, #26 in Python
See all 365 LLM reposStar history
Total stars at the end of each week, from GitHub’s daily star counts.
Why it’s rising: +1k stars this week, against ~115 in a usual week
Health signals
Too new to assessToo new to assess: the repository is less than 60 days old or has fewer than 10 commits. The signals below are shown for information only.
- Commit activity
- Commits in 2 of the last 3 weeks 5 commits on the default branch in 90 days
- Maintainers
- 1 commit author in 90 days Top author: 100% of the last 5 commits
- Issue responsiveness
- Too few issues to tell 0 issues opened by others in 90 days
- Pull requests
- None opened in 90 days
- Releases
- No GitHub releases Not counted: many projects ship without them
- Project hygiene
- License; no CI or security policy
- OpenSSF Scorecard
- Not scanned Unknown, not counted against the project
Signals are computed automatically from public GitHub data. They are not an endorsement or a security audit. How health is computed
README
An external runtime failure management layer for LLM agents.
Detect execution failures, guide recovery, and learn reusable lessons from verified recoveries.
Sentry runs alongside your agent loop without replacing the agent, environment, or evaluator.