# splx-ai/agentic-radar

A security scanner for your LLM agentic workflows

Repository: https://github.com/splx-ai/agentic-radar
Canonical: https://ross.abutalabs.com/products/agentic-radar
Homepage: https://splx.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agentic-ai, agentic-framework, agentic-workflow, ai, ai-red-teaming, ai-security, cli, devsecops, llm, llm-security, red-teaming, security, security-tools, generative-ai, mcp, mcp-server
Last push: 2025-11-27T15:28:44+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 54, release rhythm 59, longevity 40
- inputs: {"age_days": 567, "days_push": 279, "days_rel": 279, "gap_med": 2.5, "n_releases_24m": 23}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1043, forks 144 (observed 2026-08-28T04:03:20.944210+00:00)

## What it is
Agentic Radar is an open-source security scanner that analyzes LLM agentic workflows built with popular frameworks (e.g., CrewAI, LangGraph, OpenAI Agents SDK) and generates security reports and workflow visualizations. It maps agents, tools, and vulnerabilities to help teams secure AI pipelines as part of a DevSecOps process.

## Use cases
- scan my LangGraph agent workflow for security vulnerabilities
- generate a security report for my CrewAI multi-agent system
- visualize the architecture of my LLM agent pipeline
- find insecure tool usage in agentic AI applications
- add AI security scanning to my CI/CD pipeline
- audit MCP server integrations in my agent code
- build an AI bill of materials for agentic systems

## When to choose
- you build LLM agent workflows with supported frameworks and want static security analysis
- you need DevSecOps integration for AI application security scanning
- you want to visualize and document agentic system architecture and risks

## When to avoid
- you need runtime protection or live red-teaming of deployed AI systems rather than static scanning
- your project does not use a supported agentic framework
- you need a full commercial AI governance and compliance platform

## Facets
- artifact type: cli-tool
- maturity: active
- function: security, vulnerability-scanning, developer-tools, cli, agent-framework, mcp
- domain: security, artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: llm-security, agentic-workflows, static-analysis, red-teaming, devsecops, ai-bom, ai-agents, devops

## Member repositories
- splx-ai/agentic-radar (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.944210+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:32.214125+00:00, confidence not recorded.
  - readme: https://github.com/splx-ai/agentic-radar (fetched 2026-08-28T04:03:20.944210+00:00, sha f13ba90c1df3)
  - homepage: https://splx.ai (fetched 2026-08-29T13:03:55.756734+00:00, sha 35d47631ddef)
  - site_page: https://docs.probe.splx.ai/ (fetched 2026-08-29T13:03:55.768211+00:00, sha 5ebd006eec94)
  - site_page: https://splx.ai/about-us (fetched 2026-08-29T13:03:55.769851+00:00, sha 42c17cd0b205)
  - registry_pypi: https://pypi.org/pypi/agentic-radar/json (fetched 2026-08-29T13:03:55.771859+00:00, sha 66df918cc853)
  - site_page: https://splx.ai/pricing (fetched 2026-08-29T13:03:55.766492+00:00, sha ef9a2cc629dd)
- Data as of 2026-08-30T08:39:29.467469+00:00.