1.xinxuxin / keystone-bench
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
+142 stars
from 931 · score 4.96
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
6 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.Cygnux-Labs / Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
+125 stars
from 234 · score 4.84
3.superwesleyhys-ux / factcircuit
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
+99 stars
from 833 · score 4.61
4.OWASP / www-project-agent-memory-guard
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
+3 stars
from 190 · score 1.39
5.x-zheng16 / Awesome-Embodied-AI-Safety
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
+2 stars
from 158 · score 1.10
6.mthamil107 / prompt-shield
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
+2 stars
from 17 · score 1.10