Explore/framework/sandboxed.sh
S

Th0rgal/sandboxed.shActive

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.

frameworkRust
GitHubCompare
Refreshed 3h ago
OverviewActivity52wAlternativesDocs
Stars444
Forks45
HF Downloads30d
Last commit5h ago
Refreshed3h ago
Project healthActiveLast commit 5h ago.
Production readinessExperimentalGrowing but not yet battle-tested at scale.
Risk notesUnknown licenseVerify license before production use.
AgentHub Score
79 / 100
Composite score from 6 signals. How we score →
Active project
79Score
Growth
88A
Activity
96A+
Documentation
70C+
Maturity
74B
Community
87A
Production
58C
GitHub stars · 90 days444 +10.6%
30d90d1y
latest release
Commit activity · 52 weeksActive contributor activity
LowHigh
JunSepDecMarNow
Practical assessment
Should you use it?

✓ Best for

  • Multi-agent orchestration
  • Production agentic workflows
  • Stateful long-running tasks

◎ Strengths

  • Stable API
  • Active release cadence
  • Strong GitHub community

✕ Not ideal for

  • Simple single-step automation
  • Teams without Python/ML expertise

⚠ Watch-outs

  • Breaking changes between minor versions
  • Ecosystem lock-in if tightly coupled
Technical details
What's inside
LanguageRust
License
Sourcegithub
Open source✗ No
Commercial use
Docs
Demo
Paper

AgentHub Score

79
Score 79/100
Above average

Alternatives

C
crewai
26.1k · Multi-Agent
87
A
autogen
42.7k · Multi-Agent
71
S
smolagents
11.2k · Coding
84
O
openai-agents-python
9.4k · Multi-Agent
81
Compare all →

Recent activity

Latest commit 5h ago5h ago
Indexed by AgentHub crawler3h ago
Monitor for new releasesongoing