ToolsTencent AI-Infra-Guard Full-Stack AI Red Teaming PlatformGitHub·high signalXBlueskyLinkedInCopy link3K stars. 3 scanning modes: AI infra vulns (400+ CVEs), MCP/skills analysis (14 risk categories), LLM jailbreak eval. MIT licensed.SourceSource pageGitHub↳ Follow the threadPolicy dependency / Stack layerCherry Studio v2.0.9 unifies tool approval into one declarative policy and lets the provider catalog hot-update without an app releaseGitHubStack layer / ContrastGradient open-sources a full reinforcement-learning loop for training tool-using research agents with GRPOGitHubPolicy dependency / Stack layerHalofy ships an open governance layer for agents with identity, policy, provenance, audit and signed erasureGitHubStack layer / ContrastCline v4.1.16 fixes hooks resolving from global state, and starts redacting credentials embedded in git remote URLs before they reach the modelGitHub (cline/cline)Policy dependency / Stack layerOmniRoute broke a 27-day release silence with v3.8.50 on August 26 and maintains a rolling provider-catalog export tagGitHubThreat pattern / Update threadHolmesGPT 0.40.0 is almost entirely a security release: command injection across five toolsets, SSRF, and signed bash approval prefixesGitHubStack layer / Update threadMonkeyCode is pushed daily but has not tagged a release since July 28, with 286 open issues on 4,559 starsGitHubPolicy dependency / Update threadAgno 3.0.1 caches tool schemas across runs and loads session history incrementally, so response time stops scaling with conversation lengthGitHub (agno-agi/agno)