Runtime Security Python Packages

insa-its

Runtime Security for Multi-Agent AI — Website & Documentation

4K 36 3

aegis-langchain

Runtime security & governance control plane for AI agents. Enforces per-tool authorization, OPA policy, behavioral risk scoring, blast-radius analysis, autonomy contracts, and tenant kill-switch. Every decision is ed25519-signed and Merkle-anchored for tamper-evident audit. 12 microservices, sub-30ms p95, OWASP LLM Top-10 coverage.

4K 3 1

clampd

Clampd - Runtime Security for AI Agents. Dev infrastructure and orchestration.

4K 1 0

aegis-openai

3K 3 1

aegis-bedrock

3K 3 1

intentprobe

Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.

3K 8 0

aegis-anthropic

3K 3 1

bluerock-oss

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.

3K 32 5

cerberus-ai

Cerberus Core — runtime security for AI agent tool execution (open core, MIT).

2K 0 0

mobsf

Mobile Security Framework (MobSF) is an automated, all-in-one mobile application (Android/iOS/Windows) pen-testing, malware analysis and security assessment framework capable of performing static and dynamic analysis.

2K 21K 4K

adrian-sdk

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

1K 376 77

aegis-aevf

1K 3 1

varden

A self-hosted runtime firewall for AI agents

1K 0 0

omega-walls

Omega Walls — a deterministic runtime trust boundary for RAG and AI agents that models cumulative prompt-injection, secret-exfiltration, and tool-abuse pressure before untrusted content reaches context or tools.

751 7 0

bluerock

Runtime security sensor for Python — monitors imports, process execution, dynamic code, network calls, and AI frameworks

681 32 5

orchesis

Runtime Gateway for AI Agents. 17-phase security pipeline between agents and LLM APIs. Works with OpenClaw, Paperclip, Claude Code, Cursor. Open source, MIT license.

677 6 2

pyrasp

PyRASP is a Runtime Application Self Protection package for Python-based Web Servers (Flask, FastAPI and Django), Serverless Functions (AWS Lambda, Azure and Google Cloud Functions) and MCP Servers (FastMCP)

556 35 5

axiom-constitutional

AXIOM gives agentic AI systems a verifiable control layer: bonded tokens, signed state registers, append-only audit trails, and runtime gates that block unauthorized agent actions before execution. Event Tokens, CANNOT_MUTATE , track reasoning trajectories to guage constitutional distance.

490 4 0

policyshield

Declarative firewall for OpenClaw tool calls.

480 15 2

mcp-rampart

Security toolkit for FastAPI-based MCP servers — pre-flight audit + runtime prompt-injection guardrail.

466 1 0

agentguardx

Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency local mode included.

383 1 1

ancilis

Python-first runtime evaluation and policy enforcement for AI agent tool calls

216 5 0

agentshield-runtime

Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency local mode included.

207 1 1

suy-sideguy

agent-warden is a runtime policy guard for autonomous AI agents that enforces kill/flag policy on a live agent process and emits a forensic report of what it did. Scores file, network, and subprocess behavior against a YAML policy and halts or SIGKILLs the agent before it breaks things. (Installs as suy-sideguy until the next release.)

198 0 0