Keyword: ai-safety
- fullcourtdefense-cliReleased5d agoVersion1.6.13
Full Court Defense CLI — security scanning for AI agents from your terminal
- @letterblack/lbe-sdkReleased1 week agoVersion1.2.14
Local-first execution governance SDK for AI agents.
- outlier-auditReleased15h agoVersion0.33.2
AI coding audit, token tracker, and deskilling detector. Local-first CLI that measures AI authorship, carbon footprint, agent blast radius, and context waste — with warnings, not surveillance.
- @synkro-sh/cliReleased14h agoVersion1.7.5
Catch risky code before your AI coding agent ships it. Reviews every edit and shell command with full context.
- @neurcode-ai/cliReleasedyesterdayVersion0.20.12
Neurcode CLI — deterministic operational governance runtime for AI-assisted engineering (intent contracts, import-edge governance, replay continuity)
- @miraigent/free-ai-ops-mcpReleased22h agoVersion0.1.25
Free MCP server for developers adding human review gates, prompt risk checks, FAQ review, and CRM note safety to AI tools.
- @senad-d/guardmeReleased2d agoVersion0.1.5
Deny-first Pi guardrails that keep LLM shell and file access safe, transparent, and user-approved.
- sage-governanceReleased6d agoVersion1.0.4
SAGE - Open-source governance runtime harness for agentic coding systems. Intercepts, evaluates, and audits developer prompts before code is written, and performs code security scans/fixes after AI code generation.
- @letterblack/lbe-coreReleased4d agoVersion1.3.29
Local-first execution governance SDK for AI agents. Agents propose → Controller validates → Adapters execute.
- @agledger/sdkReleased6d agoVersion1.0.4
AGLedger™ SDK — Accountability and audit infrastructure for agentic systems.
- @opena2a/aicomplyReleased3d agoVersion2.2.2
Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI.
- @rosh100yx/outlierReleased6d agoVersion0.7.0
AI Code Governance & Capability Auditing for the Terminal. Measures AI reliance, context waste, and enforces local CI/CD policies.
- @tenova/swt3-mcpReleased6d agoVersion0.5.7
Cryptographic compliance witnessing and accountability governance for AI agents. EU AI Act, NIST AI RMF, OWASP Agentic Top 10, CMMC, SR 11-7. Tool policy gates, trust mesh, inference attestation, audit sessions. Zero-config demo.
- ai-sdk-guardrailsReleased21h agoVersion6.0.0
Input and output guardrails middleware for Vercel AI SDK.
- @tenova/swt3-aiReleased6d agoVersion0.5.7
SWT3 AI Witness SDK: cryptographic attestation for AI inference. 98 procedures, 51 namespaces, 5 languages, 15 profiles. EU AI Act, NIST AI RMF, CMMC, SR 11-7.
- @atbash/atbash-langchainReleased5d agoVersion0.0.4
Atbash safety guard for LangChain DynamicStructuredTool
- substrai-guardrailgraphReleased7h agoVersion1.3.0
Composable AI safety pipeline framework with industry compliance packs (HIPAA, SOX, GDPR, FedRAMP)
- ghostfilter-aiReleasedyesterdayVersion0.1.2
Safety firewall SDK for humans and AI agents — scan untrusted text for scams/phishing and prompt-injection before you (or your agent) trust it.
- mcp-nervous-systemReleased3 months agoVersion1.11.0
Governance layer for multi-agent AI systems. 7 mechanically enforced rules, 30 tools including kill switch, audit chain, dispatch, drift audit, security audit, page health, pre-publish audit, and session close. Works with Ruflo, Hivemind, Agent Teams, and
- @emilia-protocol/gateReleased5h agoVersion0.7.0
EMILIA Gate — the Trusted Action Firewall. Deny-by-default enforcement for consequential machine actions: an action runs only with a valid, in-scope, sufficiently-assured, non-replayed EMILIA authorization receipt (proof a named human authorized this exac
- @sonate/verify-sdkReleased5d agoVersion2.1.0
Client-side SDK for verifying SONATE trust receipts
- @grovetech/defenderReleased2d agoVersion0.3.0
Active runtime protection for vibe-coded apps — drops in as Express middleware (web + AI layer), blocks prompt injection, PII leaks, and sensitive paths in real time. By Grovetech AI.
- blackwall-eliza-guardrailReleased3 weeks agoVersion0.2.1
BLACK_WALL pre-action guardrail for ElizaOS agents. Wraps every action handler with a forecast() check so STOP-rated actions abort before they run; gateCall() adds per-call gating for multi-step handlers.
- yana-rtReleased30m agoVersion1.3.0
Yana AI Runtime — WebAssembly guard for AI agents: check shell commands for destructive patterns in browser, VS Code, or Node.js