Skip to content
  1. Home
  2. AI tools
  3. Security & quality

Open-source AI tools for security & quality

19 AI tools filed under security & quality, sorted by GitHub stars. Audits, sandboxing, evals and observability.

19 of 19 shown

  • Security Guidance plugin

    NousResearch/hermes-agent

    Warns when written code contains known-dangerous patterns

    ToolGitHub stars: 263k
  • security-guidance

    anthropics/claude-plugins-official

    Security warnings on edits plus LLM diff review

    ToolGitHub stars: 47k
  • Langfuse

    langfuse/langfuse

    Open-source tracing, evals and cost tracking for LLM applications

    ToolGitHub stars: 37k
  • Promptfoo

    promptfoo/promptfoo

    CLI for evaluating and red-teaming prompts, agents and RAG apps

    ToolGitHub stars: 27k
  • SkillSpector

    NVIDIA/SkillSpector

    Security scanner that checks agent skills before you install them

    ToolGitHub stars: 26k
  • DeepEval

    confident-ai/deepeval

    Pytest-style evaluation framework for LLM apps and agents

    ToolGitHub stars: 19k
  • PR-Agent

    The-PR-Agent/pr-agent

    Open-source AI reviewer for pull requests

    ToolGitHub stars: 16k
  • Arize Phoenix

    Arize-ai/phoenix

    Open-source LLM tracing and evaluation built on OpenTelemetry

    ToolGitHub stars: 12k
  • garak

    NVIDIA/garak

    LLM vulnerability scanner that probes models for known failure modes

    ToolGitHub stars: 10k
  • Claude Code Security Reviewer

    anthropics/claude-code-security-review

    GitHub Action that reviews pull-request diffs for vulnerabilities

    ToolGitHub stars: 6.9k
  • Hermes Security plugin

    NousResearch/hermes-official-plugins

    Evidence-based security review of a repository

    ToolGitHub stars: 672
  • Snyk plugin

    NousResearch/hermes-official-plugins

    Scan code, dependencies, containers and IaC with Snyk's own MCP server

    ToolGitHub stars: 672
  • claude-code-hooks

    karanb192/claude-code-hooks

    Ready-made Claude Code hooks for safety, automation and observability

    ToolGitHub stars: 581
  • OpenCode Swarm

    ZaxbyHub/opencode-swarm

    Architect-led agent team that verifies coding work

    ToolGitHub stars: 527
  • pi-sandbox

    carderne/pi-sandbox

    OS-level sandbox with permission prompts for Pi

    ToolGitHub stars: 305
  • pi-automode

    czottmann/pi-automode

    Auto-mode guardrail for Pi

    ToolGitHub stars: 212
  • pi-warden

    DevMortimer/pi-warden

    Rule enforcement and test-before-done checks for Pi

    ToolGitHub stars: 192
  • pi-permission-system

    MasuRii/pi-permission-system

    Deterministic permission gates for Pi

    ToolGitHub stars: 175
  • Review Loop

    earendil-works/pi-review-loop

    Incremental diff review while Pi works

    ToolGitHub stars: 171