Search results
98 packages found
Sort by: Default
- Default
- Most downloaded this week
- Most downloaded this month
- Most dependents
- Recently published
An open-source SDK for AI agent safety
Deterministic AI code guardrail engine — 37 built-in rules, hybrid YAML/function DSL, MCP server, .cursorrules sync, sqlite cache.
Shared core for aicqtools — tree-sitter parser, sqlite incremental cache, SARIF/JSON/text reporters, config loader, i18n.
aicq command-line interface — `aicq check`, `aicq mcp`, `aicq sync-ai-rules`, `aicq provenance`, `aicq docs build`.
Runtime rule enforcer for AI coding agents. Reads CLAUDE.md / AGENTS.md / .cursorrules and enforces them via Claude Code and Cursor hooks, with a deterministic safety baseline.
- claude
- claude-code
- claude-md
- agents-md
- cursor
- cursor-hooks
- cursor-rules
- ai-agent
- ai-tools
- hooks
- guardrail
- linter
- code-quality
User rule authoring SDK for aicqtools — `defineRule()` helper plus Rule / RuleContext / Visitor types.
CLI and MCP servers for Cutline, including SlopBurn: a product quality engineering roguelike RPG for vibecoding workflows.
- cutline
- mcp
- mcp-server
- model-context-protocol
- cli
- security
- guardrail
- vibecoding
- cursor
- claude
- windsurf
- code-audit
- engineering-audit
- nfr
- View more
Pharos Skill Engine-compatible transaction safety firewall for AI agents.
- pharos
- mcp
- mcp-skill
- defi
- risk-engine
- ai-agent
- farodex
- viem
- atlantic-testnet
- web3
- pharos-skill-engine
- guardrail
- transaction-safety
- transaction-firewall
- View more
Kill Switch for coding agents — stop runaway Claude Code / Cursor / Aider sessions from racking up an LLM bill. Native hook + token-metering proxy with per-session and daily-rolling budgets.
AI Output Verification Toolkit — Local-first LLM safety, hallucination detection, PII redaction, prompt injection defense, and runtime monitoring. Zero telemetry. OWASP LLM Top 10 aligned.
- llmverify
- llm
- ai
- verification
- guardrail
- guardrails
- ai-guardrail
- ai-guardrails
- llm-guardrail
- safety
- ai-safety
- llm-safety
- prompt-injection
- prompt-injection-detection
- View more
CLI and MCP servers for Cutline, including SlopBurn: a product quality engineering roguelike RPG for vibecoding workflows.
- cutline
- mcp
- mcp-server
- model-context-protocol
- cli
- security
- guardrail
- vibecoding
- cursor
- claude
- windsurf
- code-audit
- engineering-audit
- nfr
- View more
MCP server that proxies all agent actions, classifies risk, enforces natural-language policies, and logs to a local SQLite audit DB. View activity in the hosted dashboard at roxy-agent-web.vercel.app.
Entropy0 MCP server — source trust and URL safety tools for AI agents
Core types, chain orchestration, and utilities for the Guardrail Chain framework
CLI and MCP servers for Cutline, including SlopBurn: a product quality engineering roguelike RPG for vibecoding workflows.
- cutline
- mcp
- mcp-server
- model-context-protocol
- cli
- security
- guardrail
- vibecoding
- cursor
- claude
- windsurf
- code-audit
- engineering-audit
- nfr
- View more
Observability interfaces (logging, metrics, tracing) for the Guardrail Chain framework
Bindings-only Newton guardrail policy pack (zod schemas + deployments). No PolicyPack export yet — use with NewtonShield.guardedCall until pack.ts lands.
Built-in guardrail implementations for the Guardrail Chain framework
Two-way guardrails for AI agents — gate inputs, outputs, and actions
Guardrail plugin for OpenClaw that blocks prompt injection, jailbreak attempts, and sensitive credential exfiltration before agent dispatch.
- guardrail
- guardrails
- guardrail-bridge
- guardrailbridge
- openclaw
- openclaw-plugin
- openclaw-security
- openclaw-guardrail
- clawhub
- agent-security
- ai-agent-security
- ai-agent
- prompt-injection
- jailbreak-detection
- View more