|
Clawdit — See What Your AI Agent Really Did
Open-source runtime security for AI agents. Intercept, audit, and enforce policies on every tool call. The black box recorder your agents need.
|
88 % |
|
ASH — Agent Safety Harness
|
86 % |
|
Sunglasses | The Input Firewall for AI Agents | Open Source AI Agent Security
Sunglasses is an open source filter that blocks prompt injection and MCP tool poisoning before it reaches your AI agent. Local first, MIT licensed.
|
85 % |
|
Prismor :: AI Agent Security Control Plane
Prismor intercepts every tool call your AI agents make, enforces security policies, and logs a full audit trail. Works with all enterprise AI agents.
|
85 % |
|
node9 · Access control for AI agents
Access control for AI agents. You decide what your agents can do; node9 enforces it before they act: allow, review or block each tool call, with every decisi...
|
85 % |
|
Clawsec - Open Source Security Guardrails for AI Agents
Your AI agent has root access. And zero guardrails. Clawsec is an open-source security plugin that blocks dangerous actions in under 5ms. One command: opencl...
|
85 % |
|
AgentX: The Action Firewall for AI Agents
Block the catastrophic deterministically, coach the recoverable. AgentX is a runtime firewall for AI agents. It blocks catastrophic tool calls (DROP TABLE, s...
|
85 % |
|
jes: Open-source guardrails for AI agents, powered by Jev
jes is an open-source Python library that secures AI agents. It blocks prompt injection, data leaks and risky tool calls with Jev decision models, in millise...
|
85 % |
|
ifivo: Agent Control Plane for AI (Policy, Approvals, Kill Switch)
ifivo is the runtime control plane for AI agents. Enforce spend limits, vendor allowlists, and risk policies. Approve high-risk actions from Slack or in-app....
|
84 % |
|
Straight Chaos - Security for AI agents
Wrap any AI agent — Claude Code, Cursor, Codex — in one command. See every API call, file, secret, and tool it touches, then control it: stop prompt-injectio...
|
84 % |
|
hoop.dev | Runtime controls for AI agents
Data and context make agents useful. hoop.dev makes it safe. Attach a sidecar to a database, cluster, or agent sandbox and get masking, guardrails, and appro...
|
84 % |
|
ClawShield — Security Gateway for AI Agents
Real-time security gateway for AI agents. Rate limiting, IP filtering, and OWASP LLM Top 10 prompt injection protection — with a Python SDK your agents conne...
|
84 % |
|
Rune — Runtime Security for AI Agents
Block prompt injections, data exfiltration, and policy violations before they reach production. Works with LangChain, OpenAI, Anthropic, CrewAI, and MCP. Fre...
|
84 % |
|
AgentWall – Stop your AI agent before it goes too far
Your AI agent can read every credential on your machine. AgentWall blocks dangerous tool calls before they execute, independent of the runtime.
|
84 % |
|
Calus — Drop-in AI Security Gateway
Drop-in, detection-only AI-security gateway. Flags prompt injection, jailbreaks & agent abuse on every call. No code changes, never alters your traffic.
|
84 % |
|
Security guardrails for coding agents · agentjail
Offline policy guardrails for coding agents. Block dangerous tool calls, sandbox execution, and audit agent activity. Open source, Apache-2.0.
|
84 % |
|
LLM firewall & AI security proxy — AiDren
Drop-in AI security proxy: blocks prompt injection, scans LLM outputs for PII and secrets, scans model files. Self-serve, 14-day free trial.
|
84 % |
|
Jeprum — The live control room for AI agents
See everything, set rules, stop anything. Jeprum intercepts your agent's MCP tool calls, enforces guardrails before execution, and gives you a remote kill sw...
|
83 % |
|
The control plane for AI agents | ClawMetry
Observe AI agent activity, understand spend, and govern supported actions with ClawMetry. Local by default. Start with one install.
|
83 % |
|
clawdcursor: safe desktop control for any AI agent
Local MCP server that gives any AI agent safe desktop control. Compiles the screen into a UI map (a11y tree + OCR) with stable element ids, acts by id not by...
|
83 % |
Detected social media networks