slime
Repository: slime
Author: THUDM · Source status: Clear source
Score 92Clear source
Manual reviewslime is an LLM post-training framework for RL Scaling.
Score basis：Clear source · Risk needs review · Universal
Author unclaimed
Universal
5.3K
Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Comparison matrix
Highlights show current best; tooltip explains diff/best rules.
SAS-v2.1 diff rules / risk tag notes
Start with the matrix. Open this section when you need to understand audit grades, top threats, control gaps, and best-value highlights.
Suggested baseline
Search to add skills, or paste 2–4 comma-separated slugs.
How differences are detected
A row is marked different when selected skills have distinct values. Only-differences mode hides rows that are identical.
How best values are highlighted
Audit score, evidence confidence, trust score, and community signal prefer higher values; execution risk and install friction prefer lower values.
How to read risk tags
Risk tags come from SAS-v2.1 public-evidence signals and point to command, network, secret, context, or supply-chain items to review before install.
Selected audit signals
AgentRL
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
splitrail
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
WebRL
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | AgentRL | splitrail | WebRL |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Threat tags | unexpected code execution, data exfiltration, human approval gap | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, data exfiltration, human approval gap |
Permission summary | Permission review, Network, Command | Permission review, Network, Secrets, Command | Permission review, Network, Command |
Evidence confidence | 65% | 67% | 65% |
| Source & provenance | |||
Provenance | THUDM/AgentRL | Piebald-AI/splitrail | THUDM/WebRL |
Category | Dev & Engineering | Dev & Engineering | Agent & Tools |
Freshness | |||
| Risk & trust | |||
Trust score | 67 | 82 | 92 |
Audit signals | No explicit signals | needs credentials | metadata-only |
| Install & compatibility | |||
Install friction | 40 | 55 | 75 |
| Community | |||
Stars | 265 | 150 | 515 |
Repository: claude-code-env-manager
Author: Genuifx · Source status: Clear source
Control center for Claude Code & Codex — multi-model parallel sessions, Telegram remote control, scheduled cron tasks with push notifications, usage analytics, permission modes.
Score basis：Clear source · Low risk signals · Universal
Repository: Claude-Code-Agent-Monitor
Author: hoangsonww · Source status: Clear source
A real-time monitoring dashboard for Claude Code agents, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, and WebSockets.
Score basis：Clear source · High risk signals · Universal
Repository: rox
Author: BeWelcome · Source status: Clear source
:earth_africa: BeWelcome lets you share a place to stay, connect with travellers, meet up and find accommodation on your journey.
Score basis：Clear source · Low risk signals · Universal
2026-01-17 |
2026-04-06 |
2025-06-06 |
Permission hints |
|---|
repository clone, local runtime dependencies |
local runtime dependencies, repository clone |
repository clone |