PUFFER

The autonomous immune system for AI agents

Like a puffer fish โ€” inflates when threatened, repels with spines, then deflates back to calm.

A local-first security daemon that sits between your AI agents and LLM providers โ€” inspecting every request through 7 defense layers. Ships in monitor mode: observes everything, blocks nothing.

The agent-first install

Tell your agent: "Install puffer from openpuffer.org"

Your agent visits the site, runs the install, downloads the skill, and starts monitoring itself.

ฮฒ BETA
$ curl -fsSL https://openpuffer.org/install.sh | bash
Local-first No telemetry Apache 2.0 7 defense layers

How it works

Designed for agents, not humans

The full install flow is agent-driven. You give the order โ€” your agent does the rest.

๐Ÿ’ฌ 01

Tell your agent

"Install puffer from openpuffer.org"

Your agent visits this site. You never touch the terminal.

โšก 02

Agent installs

Runs install.sh, initializes the daemon

Puffer starts in monitor mode โ€” the only safe default.

๐Ÿ“ฅ 03

Skill downloaded

Agent pulls SKILL.md into ~/.claude/skills/puffer/

From now on, your agent knows how to interpret Puffer verdicts.

๐Ÿ“Š 04

You watch the dashboard

localhost:8788 shows live events

Every agent request is inspected. Verdicts appear in real time.

๐Ÿ”’ 05

You decide when to enforce

Run puffer mode enforce when ready

Puffer will NEVER block traffic until you explicitly say so.

๐Ÿก Monitor mode is the default. Always.

Puffer will NEVER block, intercept, or alter traffic until you explicitly run puffer mode enforce. You are always in control.

Defense

7 Layers. Zero compromise.

Every LLM request and response passes through all 7 layers in real time.

L1

PII Scanner

SSNs, credit cards, API keys, passwords, private keys, JWTs

L2

Injection Detector

Prompt injection, role switching, jailbreaks, data exfiltration via prompt

L3

Command Analyzer

rm -rf /, curl | bash, fork bombs, privilege escalation, destructive shell commands

L4

Network Egress Guard

SSRF attacks, DGA domains, private IP ranges, unauthorized outbound connections

L5

Filesystem Sentinel

~/.ssh, ~/.aws, /etc/shadow, path traversal (../), secret file leakage

L6

Behavior Analyzer

Cost runaway, agent loops, excessive tool calls, bypass attempts

L7

MCP Detector

Unauthorized MCP servers, tool result poisoning, unapproved tool registration

๐Ÿก

All 7 layers

Active on every request, every response, every agent.

Operating Modes

You control the dial.

Four modes. Start at zero. Move up when you're ready.

DEFAULT
๐Ÿ‘ monitor

Observe only. Logs all verdicts but never blocks traffic. Every agent action is recorded.

$ puffer mode monitor
๐Ÿ›ก enforce

Block threats in real time. Requires explicit user approval before activating.

$ puffer mode enforce
๐Ÿ”’ paranoid

๐Ÿก๐Ÿ’จ Puffer inflated. Whitelist-only mode. Only approved traffic passes. Maximum restriction.

$ puffer mode paranoid
๐Ÿ’ฌ interactive

Ask the user before blocking each individual threat. Ideal for learning what Puffer catches.

$ puffer mode interactive

Puffer ships in monitor mode. Always.

No traffic is ever blocked until you explicitly run puffer mode enforce. Agents are instructed to NEVER auto-enable enforce mode โ€” this is a user decision only.

Compatibility

Works with everything you use.

Puffer intercepts at the proxy layer โ€” no SDK changes, no framework lock-in.

Supported Agents

Claude Code OpenClaw Cursor Aider Continue.dev Cline GitHub Copilot LangChain CrewAI AutoGen + more coming

Supported LLM Providers

OpenAI Anthropic Ollama LM Studio LocalAI vLLM DeepSeek Groq Together OpenRouter + any OpenAI-compatible

FAQ

Good questions.

Here are the ones we get most often.

Does Puffer phone home?

No. Puffer is entirely local-first. It runs as a daemon on your machine, intercepts traffic on localhost, and writes logs to ~/.puffer/audit.jsonl. No data is ever sent to any external server. No telemetry. No analytics.

Will it break my agent?

No. In monitor mode (the default), Puffer is completely transparent โ€” it observes and logs every request/response, but never modifies or blocks anything. Your agent works exactly as before. You only risk behavior changes if you explicitly enable enforce mode.

How do I enable blocking?

Run `puffer mode enforce` after reviewing the audit log and confirming you understand what Puffer considers a threat. We strongly recommend running in monitor mode for at least a few sessions first. Agents are instructed never to run this command on their own initiative.

What exactly does it detect?

7 layers: L1 PII (SSNs, API keys, credit cards), L2 Prompt Injection (jailbreaks, role switching), L3 Dangerous Commands (rm -rf, fork bombs), L4 Network Egress (SSRF, DGA domains), L5 Filesystem (~/.ssh, ~/.aws, path traversal), L6 Behavior (loops, cost runaway), L7 MCP (unauthorized servers, tool poisoning).

Is Puffer open source?

Yes. Puffer is released under the Apache 2.0 license. You can inspect the source, contribute, or fork it. The security layers are fully auditable โ€” no black boxes.

Is it production-ready?

Puffer is currently in ฮฒ BETA. Core monitoring is functional and stable, but some features are still being polished. We recommend starting with monitor mode to evaluate it in your environment before enabling enforce mode in critical pipelines.