Explore/agent app/scholar-loop
S

renee-jia/scholar-loopStale

An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.

agent appPythonMIT
GitHubCompare
Refreshed 1h ago
OverviewActivity52wAlternativesDocs
Stars470
Forks35
HF Downloads—30d
Last commit3mo ago
Refreshed1h ago
Project healthStaleNo commits in 113d.
Production readinessExperimentalGrowing but not yet battle-tested at scale.
Risk notesMITVerify license before production use.
AgentHub Score
60 / 100
Composite score from 6 signals. How we score →
Active project
60Score
Growth
88A
Activity
50C
Documentation
70C+
Maturity
73B
Community
87A
Production
58C
GitHub stars · 79 days observed470 +0.21% / 30d
snapshots
Repository activity · 79 days observedReal snapshots from pushed_at
inactivepushed
2026-07-262026-10-14
Practical assessment
Should you use it?

✓ Best for

  • Research and experimentation
  • Prototype development
  • Learning agentic patterns

◎ Strengths

  • Active community
  • Open source
  • Well-documented API

✕ Not ideal for

  • Untested at scale without validation
  • Teams without AI/ML expertise

⚠ Watch-outs

  • Review changelog before updating
  • Verify license for commercial use
Technical details
What's inside
LanguagePython
LicenseMIT
Sourcegithub
Open source✗ No
Commercial use—
Docs—
Demo—
Paper—

AgentHub Score

60
Score 60/100
Below average

Alternatives

G
gemini-cli
107.4k · agent app
95
O
open-design
101.2k · agent app
95
G
goose
55.3k · agent app
95
L
LibreChat
45.7k · agent app
95
Compare all →

Recent activity

Latest commit 3mo ago3mo ago
Indexed by AgentHub crawler1h ago
Monitor for new releasesongoing