Sandbox
4 repos for ai-safety · DocsClear
assafkip/
research-mode

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

151
lc198707/
anti-lie

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.

89
JKHeadley/instarFrameworks & SDKs

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

79
yzhao062/
anywhere-agents

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

244