APort Agent Guardrails

npm • PyPI • Website • Docs • Meet Porter • Quick Start • Security

Deterministic pre-action authorization for AI agents. Guardrails run before tool execution, so prompt injection cannot bypass policy checks.

CTF Evidence

From the live APort Vault adversarial testbed:

Metric	Result
Total authorization decisions observed	4,437
Total attack sessions observed	1,151
Level 5 ("Vault") restrictive attempts	879
Level 5 ("Vault") successful breaches	0
Level 5 restrictive success rate	0%
Permissive baseline success rate (for comparison)	74.6%

Start Here

Install in 30 seconds

npx @aporthq/aport-agent-guardrails

Choose your framework: openclaw, cursor, claude-code, langchain, crewai, deerflow, n8n
OpenClaw direct: npx @aporthq/aport-agent-guardrails openclaw
Hosted passport: npx @aporthq/aport-agent-guardrails openclaw <agent_id>
Reset a framework to a clean APort state: npx @aporthq/aport-agent-guardrails reset claude-code --yes

Why Developers and teams trust APort

Deterministic enforcement: runtime hook, not prompt instructions
Fail-closed defaults: verification failures block risky actions
Auditable decisions: each allow/deny is logged with context
Open standard artifacts: Open Agent Passport (OAP) v1.0 passport and decision formats
Research-backed outcomes: in a live adversarial testbed, permissive-policy success was 74.6% vs 0% under restrictive OAP policy (879 top-tier attempts)
Low latency at production scale: cloud API verification p50 ~53ms at N=1,000
Security docs: SECURITY.md, SECURITY_MODEL.md
Backed by Peer-reviewed research: arXiv preprint (Mar 2026)

Fast path by persona

I need OpenClaw now: docs/QUICKSTART_OPENCLAW_PLUGIN.md
I already have agent_id: docs/HOSTED_PASSPORT_SETUP.md
I need framework setup docs: docs/frameworks
I want Claude marketplace install: docs/frameworks/claude-code.md

Brand personality (optional)

Security should feel rigorous, not intimidating. Meet Porter, the APort mascot used across the product experience: Meet Porter.

Deeper background (threat model, rationale, evidence)

The security concern is that agent tools and skills can execute sensitive actions (files, commands, external calls). APort addresses this by verifying each tool call against a passport and policy limits before execution. This reduces prompt-injection and “agent decided wrong” risk from runtime behavior to policy configuration.

🔌 Supported frameworks

APort Agent Guardrail adapters and providers are available per framework; the same passport and policies apply. Node users: npx @aporthq/aport-agent-guardrails (then choose framework) or npx @aporthq/aport-agent-guardrails <framework>. Python users (LangChain/CrewAI/DeerFlow): run the same CLI for the wizard and config, then install the Python package shown in the framework doc.

Two ways to use APort: (1) Guardrails (CLI/setup) — run the installer to create your passport and config; (2) Core (library) — use the OAPGuardrailProvider (docs/PROVIDER.md) in your app so each tool call is verified. One provider per language (Python + TypeScript), works with any framework. Framework docs: OpenClaw, Cursor, Claude Code, LangChain, CrewAI, DeerFlow, n8n.

CLI-supported frameworks: openclaw, langchain, crewai, cursor, claude-code, deerflow, n8n. OpenClaw/Cursor/Claude Code include runtime-specific integration scripts; DeerFlow/LangChain/CrewAI use framework docs plus generic setup output from the CLI. See Deployment readiness.

Framework	Doc	Integration	Install
OpenClaw	docs/frameworks/openclaw.md	Plugin: `before_tool_call` via `openclaw-aport`	`npx @aporthq/aport-agent-guardrails openclaw`
Cursor	docs/frameworks/cursor.md	`beforeShellExecution` / `preToolUse` hooks → writes `~/.cursor/hooks.json`. Runtime enforcement is the bash hook; the Node package `@aporthq/aport-agent-guardrails-cursor` is a helper only (Evaluator, `getHookPath()`).	`npx @aporthq/aport-agent-guardrails cursor`
Claude Code	docs/frameworks/claude-code.md	PreToolUse hook → writes `~/.claude/settings.json` (Claude Code format; not Cursor).	`npx @aporthq/aport-agent-guardrails claude-code`
LangChain / LangGraph	docs/frameworks/langchain.md	Python: `APortCallback` (`on_tool_start`)	`npx @aporthq/aport-agent-guardrails langchain` then `pip install aport-agent-guardrails-langchain` + `aport-langchain setup`
CrewAI	docs/frameworks/crewai.md	Python: released hook adapter by default; native `GuardrailProvider` mode for CrewAI builds with native provider support	`npx @aporthq/aport-agent-guardrails crewai` then `pip install aport-agent-guardrails-crewai` + `aport-crewai setup`
DeerFlow	docs/frameworks/deerflow.md	Python: generic OAP provider wiring in DeerFlow config	`npx @aporthq/aport-agent-guardrails deerflow` then follow printed `uv`/config steps
n8n	docs/frameworks/n8n.md	Coming soon — custom node and runtime in progress	—
VoltAgent	VoltAgent PR #1171	In progress — pluggable `GuardrailProvider` interface landing upstream in `@voltagent/core`	—

Install via npx @aporthq/aport-agent-guardrails <framework> (or choose when prompted). OpenClaw can also use the full installer flow. For LangChain, CrewAI, and DeerFlow, the CLI writes config and installs the local runtime into the framework config directory; then install the Python package and wire the provider/callback shown in the framework doc. Python packages are on PyPI; Node packages are on npm (same version as the CLI).

Passport path: Each framework has its own default passport path (where that framework stores data): e.g. Cursor → ~/.cursor/aport/passport.json, OpenClaw → ~/.openclaw/aport/passport.json, LangChain → ~/.aport/langchain/aport/passport.json. The passport wizard’s first question is “Passport file path [default]:” — press Enter for the framework default or type a different path. In non-interactive mode (e.g. CI) use --output /path/to/passport.json to choose the path. Roadmap: docs/FRAMEWORK_ROADMAP.md.

Using SDKs or middleware directly: If you prefer to integrate with the APort API from your own app (no CLI/framework installer), use the official SDKs and middleware: Node — @aporthq/sdk-node, @aporthq/middleware-express; Python — aporthq-sdk-python, aporthq-middleware-fastapi.

🚀 Quick Start

Prerequisites: For the setup wizard you need Node 18+ (or use the Python CLI below). jq is needed for local/bash guardrail. No clone required.

1. Run the setup — Choose your framework when prompted (or pass it). Same wizard for everyone.

Node (Cursor, OpenClaw, or to create config for any framework):

npx @aporthq/aport-agent-guardrails
# or: npx @aporthq/aport-agent-guardrails openclaw | cursor | claude-code | langchain | crewai | deerflow | n8n
# optional mode flags (all frameworks):
#   --mode=api --api-url=https://api.aport.io
#   --mode=local

Reset / uninstall APort-owned wiring

Use the same dispatcher for cleanup:

npx @aporthq/aport-agent-guardrails reset claude-code --yes
# or
npx @aporthq/aport-agent-guardrails claude-code reset --yes

Supported reset targets match the CLI-supported frameworks: openclaw, cursor, claude-code, langchain, crewai, deerflow, n8n.

Reset removes APort-owned config and integration wiring for the selected framework. When possible, unrelated user hooks are preserved.

Python (LangChain, CrewAI, or DeerFlow): Use the Python CLI directly via uvx or an installed package:

uvx --from aport-agent-guardrails aport setup --framework=langchain
# or --framework=crewai / deerflow

Or install the package first:

pip install aport-agent-guardrails
aport setup --framework=langchain
# or --framework=crewai / deerflow

Then install the framework-specific Python package and follow the printed integration step for your framework.

This runs the passport wizard and writes config for your framework. Follow the next steps printed at the end (e.g. restart Cursor; or for CrewAI: by default install aport-agent-guardrails-crewai for released CrewAI, or opt into native-provider mode if your CrewAI build supports it).

Guardrail mode (local vs API) — On the Node installer (npx @aporthq/aport-agent-guardrails … / bin/agent-guardrails), every framework accepts the same flags: --mode=api (with optional --api-url, default https://api.aport.io) or --mode=local, and an optional hosted ap_<hex> argument (API mode, no local passport). That flow writes …/aport/guardrail-mode.env where the hooks/generic installers need it. The Python aport setup CLI does not parse those flags yet; use the Node command above for API/local mode during setup, or set mode in your framework config.yaml per the framework doc.

2. Hosted passport (optional) — If you already have an agent_id from aport.io, use it to skip the wizard: npx @aporthq/aport-agent-guardrails openclaw <agent_id>. See Hosted passport setup.

3. Test that policy runs — After setup, the guardrail runs automatically when your agent uses tools (Cursor hook, LangChain callback, OpenClaw plugin, etc.). To try allow/deny from the command line (any framework), use the installed aport-guardrail command (Node) or call the evaluator from Python; both use your existing passport from the framework config dir (e.g. ~/.cursor/aport/, ~/.aport/langchain/aport/).

Node:

aport-guardrail system.command.execute '{"command":"ls"}'      # ALLOW (safe)
aport-guardrail system.command.execute '{"command":"rm -rf /"}'  # DENY (blocked pattern)
# Exit: 0 = ALLOW, 1 = DENY

(If you use npx without -g, run npx aport-guardrail ....)

Python: Use the guardrail in your app (e.g. add APortCallback() to your LangChain agent, use register_aport_guardrail() for released CrewAI, or enable_guardrail(OAPGuardrailProvider(...)) for CrewAI builds with native provider support). The guardrail runs on every tool call. To test allow/deny from the shell without Node, use npx aport-guardrail ... as above, or see your framework doc for in-app testing.

Check passport status and audit:

What	Where
Passport & audit	Stored in your framework config dir (e.g. `~/.cursor/aport/`, `~/.openclaw/aport/`, `~/.aport/langchain/aport/`). Same for all frameworks.
Audit log	`config_dir/aport/audit.log` — one line per decision (timestamp, tool, allow/deny, policy, context).
Last decision	`config_dir/aport/decision.json` (OAP v1.0 format).

Your framework doc (Cursor, OpenClaw, LangChain, CrewAI) describes where the config dir is and any framework-specific status commands.

📖 Per-framework: OpenClaw · Cursor · Claude Code · LangChain · CrewAI · DeerFlow · n8n
🌐 Hosted passport: Use agent_id from aport.io

🔒 Enforcement Options

	OpenClaw Plugin ✅	AGENTS.md only ⚠️
Deterministic	Yes	No
Bypass risk	None	High
Recommended	Yes	Only if plugin unavailable

Plugin (recommended): Platform runs the guardrail before every tool; the model cannot skip it. This repo implements the public plugin (before_tool_call) integration for OpenClaw. AGENTS.md: Agent is instructed to call the guardrail; best-effort only.

🔌 Verification methods (local vs API)

Default and recommended: API mode — full OAP policy evaluation (JSON Schema, assurance, regions, evaluation rules from policy JSON, signed decisions). The setup wizard defaults to API when you choose a mode.

Fail-closed by default: If the evaluator cannot find a passport or guardrail script (e.g. first run, wrong config dir), it denies the tool call (oap.misconfigured). For legacy allow-when-missing behavior, set fail_open_when_missing_config: true in your config or APORT_FAIL_OPEN_WHEN_MISSING_CONFIG=1 in the environment.

Mode	Best for	Full OAP?	Network
API (default)	Production, full policy parity, new policy packs without code changes	✅	Yes (api.aport.io or self-hosted)
Local (bash)	Privacy, offline, air-gapped	Subset only (hand-coded limits for exec, messaging, repo)	No

API mode can use either a local passport file (sent in the request body; not stored) or agent_id only: set APORT_AGENT_ID to your hosted passport’s agent ID and the API fetches the passport from the registry — no passport JSON file needed. See Hosted passport setup.

Deep dive (what each supports, comparison table): Verification methods.

⚡ Performance

Guardrail verification latency from the latest preprint benchmark set (N=1,000).

Mode	p50	p95	p99	N
Cloud API (agent_id, pack in path)	53ms	63ms	76ms	1,000
Cloud API (agent_id, policy in body)	53ms	62ms	77ms	1,000
Cloud API (passport in body, pack in path)	54ms	63ms	74ms	1,000
Cloud API (passport in body, policy in body)	53ms	63ms	71ms	1,000
Local policy evaluation	174ms	243ms	358ms	1,000

Source: Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents

📐 How It Works (expand)

📐 How It Works

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#f0f9ff','primaryTextColor':'#0c4a6e','primaryBorderColor':'#0284c7','lineColor':'#0369a1','secondaryColor':'#e0f2fe','tertiaryColor':'#bae6fd'}}}%%
sequenceDiagram
  autonumber
  participant User as 👤 User
  participant OC as 🦀 OpenClaw
  participant Hook as 🔒 before_tool_call
  participant Plugin as 🛡️ APort Plugin
  participant Guard as 📋 Guardrail

  User->>OC: "Run: rm -rf /tmp"
  activate OC
  OC->>Hook: tool call (exec.run, params)
  activate Hook
  Hook->>Plugin: before_tool_call(exec.run, params)
  activate Plugin
  Note over Plugin: Map tool → policy<br/>exec.run → system.command.execute.v1
  Plugin->>Guard: evaluate(passport, policy, context)
  activate Guard
  Note over Guard: API or local script<br/>passport + limits
  Guard-->>Plugin: DENY (blocked pattern)
  deactivate Guard
  Plugin-->>Hook: block: true, blockReason
  deactivate Plugin
  Hook-->>OC: Tool blocked
  deactivate Hook
  OC-->>User: ❌ Action blocked by policy
  deactivate OC

Flow (high level):

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#f0f9ff','primaryTextColor':'#0c4a6e','primaryBorderColor':'#0284c7','lineColor':'#0369a1'}}}%%
flowchart TB
  subgraph User["👤 User"]
    A[User request]
  end
  B[🦀 OpenClaw: tool call]
  C[🔒 before_tool_call hook]
  D[🛡️ APort plugin]
  E[📋 Guardrail: passport + policy]
  F{Decision}
  G[✅ ALLOW — tool runs]
  H[❌ DENY — tool blocked]
  A --> B --> C --> D --> E --> F
  F --> G
  F --> H
  style A fill:#0277bd,stroke:#01579b,stroke-width:2px,color:#fff
  style B fill:#1565c0,stroke:#0d47a1,stroke-width:2px,color:#fff
  style C fill:#0288d1,stroke:#01579b,stroke-width:2px,color:#fff
  style D fill:#ff6f00,stroke:#bf360c,stroke-width:3px,color:#fff
  style E fill:#ff6f00,stroke:#bf360c,stroke-width:2px,color:#fff
  style F fill:#7b1fa2,stroke:#4a148c,stroke-width:2px,color:#fff
  style G fill:#388e3c,stroke:#1b5e20,stroke-width:2px,color:#fff
  style H fill:#c62828,stroke:#b71c1c,stroke-width:2px,color:#fff

User → "Delete all log files"
         ↓
   OpenClaw: tool "exec.run"
         ↓
   🔒 before_tool_call hook
         ↓
   🛡️ APort plugin → guardrail (passport + policy)
         ↓
   ┌─────────┴─────────┐
   ✅ ALLOW            ❌ DENY
   Tool runs           Tool blocked

Key: The platform enforces policy. The AI cannot skip this check.

🏛️ Security model (three layers) (expand)

🏛️ Security model (three layers)

APort enforces identity → authorization → audit before any tool runs. This repo implements the plugin (Option 2) integration: OpenClaw calls the APort extension in before_tool_call; the extension uses either local script or API to evaluate policy.

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#f0f9ff','primaryTextColor':'#0c4a6e','primaryBorderColor':'#0284c7','lineColor':'#0369a1'}}}%%
graph TB
  subgraph L1["Layer 1: Identity (Who)"]
    A[Agent Passport<br/>OAP v1.0 / W3C DID]
    B[Owner, contact, org]
    C[Assurance level L0–L3]
  end

  subgraph L2["Layer 2: Authorization (What)"]
    D[Policy packs<br/>code.*, data.*, messaging.*]
    E[Graduated controls<br/>Max amounts, daily caps]
    F[Context-aware rules<br/>Branch allowlist, PII filters]
  end

  subgraph L3["Layer 3: Audit (Proof)"]
    G[Decision receipts<br/>Ed25519 in API mode]
    H[Audit trail<br/>Allow/deny logged]
    I[Kill switch<br/>Local file or global via API]
  end

  A --> D
  B --> D
  C --> D
  D --> G
  E --> G
  F --> G
  G --> H
  H --> I

  style A fill:#0277bd,stroke:#01579b,stroke-width:2px,color:#fff
  style D fill:#ff6f00,stroke:#bf360c,stroke-width:2px,color:#fff
  style G fill:#6a1b9a,stroke:#4a148c,stroke-width:2px,color:#fff

Local-first: Passport and policy live on your machine (or in repo); no cloud required for basic enforcement.
Fail-closed: Missing or invalid passport → deny.
Opt-in cloud: Use API mode for global kill switch, signed receipts, and team sync.

What APort Protects

✅ Pre-action authorization (agent misbehavior):

Prompt injection - Hook-based enforcement; agent cannot bypass via prompts
Malicious skills - Third-party OpenClaw skills validated before execution
Unauthorized commands - Allowlist + 50+ blocked patterns (rm -rf, sudo, nc, find -exec rm, etc.)
Data exfiltration - File access, messaging, web requests controlled by policy
Resource limits - Rate limits, size caps, transaction amounts enforced

Application-layer security model: APort enforces policies at the agent action layer (between agent decision and tool execution). It operates within the OS trust boundary—standard for authorization systems like OAuth, IAM, and policy engines.

For production: Use API mode (mode: api with agent_id) for cryptographically signed decisions, protected passports, and global suspend. See docs/SECURITY_MODEL.md for full threat model, attack scenarios, and best practices.

🌐 When to use API vs local

Use local when	Use API (default) when
Single developer, no cloud	Team; same policies across machines
Offline or air-gapped	You want global kill switch (<15s)
Plain audit logs are enough	You need signed receipts (e.g. SOC 2, compliance)
No API key / self-host not ready	Registry checks, analytics, or policy marketplace

See Verification methods for a detailed comparison.

📖 Example outcomes

Scenario	Without APort	With APort
Oversized PR	Agent creates 1200-file PR	Denied: “PR size exceeds limit of 500 files”
PII export	Agent exports SSN/driver’s license	Denied: “PII export not allowed” (data.export policy)
Kill switch	Manually edit config on every machine	API: suspend passport once → all agents deny in <15s

📜 Commands (after install)

Node: When you install via npm install @aporthq/aport-agent-guardrails (or use npx), these commands are available:

Command	Purpose
`agent-guardrails`	Main entry — prompt for framework or pass one: `agent-guardrails openclaw \| cursor \| claude-code \| langchain \| crewai \| deerflow \| n8n`. Args after the framework are passed through (e.g. `agent-guardrails openclaw <agent_id>`).
`agent-guardrails reset <framework> [--yes]`	Remove APort-owned config and hook/plugin wiring for one framework. Positional form also works: `agent-guardrails <framework> reset --yes`.
`aport`	OpenClaw one-command setup (passport + plugin + wrappers). Optional: `aport <agent_id>` for hosted passport.
`aport-guardrail`	Run guardrail check from the CLI (e.g. `aport-guardrail system.command.execute '{"command":"ls"}'`). Uses passport from your framework config dir.

Python: After pip install aport-agent-guardrails you get aport (setup helper). For LangChain or CrewAI, install the framework package and setup:

Command	Purpose
`aport setup --framework=langchain`	Print next-step commands (npx wizard, then `pip install aport-agent-guardrails-langchain`, `aport-langchain setup`).
`aport setup --framework=crewai`	Default released CrewAI path: bootstrap config/runtime, then use `pip install aport-agent-guardrails-crewai` and `aport-crewai setup`.
`aport setup --framework=crewai --integration-mode=native`	Native CrewAI path: bootstrap config/runtime, then use `uv add aport-agent-guardrails` and `OAPGuardrailProvider`.
`aport-langchain setup`	LangChain config and wizard (after installing `aport-agent-guardrails-langchain`).

Use the framework-specific doc for where config and passport live and for any extra steps (e.g. Cursor: restart IDE; LangChain/CrewAI: add callback/hook in code).

Contributors: repo layout and dev scripts (build, test, release) are in docs/REPO_LAYOUT.md and CONTRIBUTING.md.

📚 Documentation

Doc	Description
QuickStart: OpenClaw Plugin	5-minute OpenClaw setup
Hosted passport setup	Use passport from aport.io — `npx ... openclaw <agent_id>` or choose hosted in wizard
Verification methods (local vs API)	Deep dive: bash vs API evaluator
Quick Start Guide	Passport wizard, copy-paste option
OpenClaw Local Integration	API, Python example
Tool / Policy Mapping	Tool names → policy packs
Repo Layout	For contributors: package layout (`bin/`, `src/`, `extensions/`)
Upgrade Guide	Migrating between versions (e.g. 0.1.0 → 1.0.0)
Frameworks	Per-framework setup and how guardrails run
→ OpenClaw	`before_tool_call` plugin
→ Cursor	beforeShellExecution / preToolUse hooks, `~/.cursor/hooks.json`
→ Claude Code	PreToolUse hook, `~/.claude/settings.json`
→ LangChain / LangGraph	`APortCallback` handler
→ CrewAI	Released hook adapter by default; native provider mode when available
→ DeerFlow	Generic provider wiring via DeerFlow `config.yaml`
→ n8n	Custom node, branch on allow/deny
Framework roadmap	Support status and roadmap

🏗️ Architecture (expand)

🏗️ Architecture

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#f0f9ff','primaryTextColor':'#0c4a6e','primaryBorderColor':'#0284c7','lineColor':'#0369a1','secondaryColor':'#e0f2fe','tertiaryColor':'#bae6fd'}}}%%
flowchart LR
  subgraph Runtime["Runtime"]
    OC[🦀 OpenClaw / IronClaw]
    S[Sandbox, channels, tools]
    OC --> S
  end
  subgraph Policy["Pre-action policy"]
    AP[🛡️ APort Guardrails]
    P[Passport, limits, audit]
    AP --> P
  end
  Runtime <-->|before every tool| Policy
  style OC fill:#1565c0,stroke:#0d47a1,stroke-width:2px,color:#fff
  style S fill:#6a1b9a,stroke:#4a148c,stroke-width:1px,color:#fff
  style AP fill:#ff6f00,stroke:#bf360c,stroke-width:3px,color:#fff
  style P fill:#ff6f00,stroke:#bf360c,stroke-width:1px,color:#fff

Where verification runs (this repo):

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#f0f9ff','primaryTextColor':'#0c4a6e','primaryBorderColor':'#0284c7','lineColor':'#0369a1'}}}%%
flowchart TB
  subgraph Machine["Your machine"]
    OC[🦀 OpenClaw]
    Plug[🛡️ APort plugin<br/>before_tool_call]
    Guard[📋 Guardrail]
    OC --> Plug
    Plug --> Guard
  end
  Guard -->|API mode| API[📡 api.aport.io<br/>or self-hosted]
  Guard -->|Local mode| Bash[📜 aport-guardrail-bash.sh]
  style OC fill:#1565c0,stroke:#0d47a1,stroke-width:2px,color:#fff
  style Plug fill:#ff6f00,stroke:#bf360c,stroke-width:3px,color:#fff
  style Guard fill:#ff6f00,stroke:#bf360c,stroke-width:2px,color:#fff
  style API fill:#2e7d32,stroke:#1b5e20,stroke-width:1px,color:#fff
  style Bash fill:#6b7280,stroke:#374151,stroke-width:1px,color:#fff

OpenClaw = Runtime (sandbox, channels, tools).
APort plugin = Pre-action hook; calls guardrail (API or local script).
Guardrail = Passport + policy evaluation; allow/deny before the tool runs.

Defense in depth: policy before execution, runtime safety during execution.

🤝 Contributing

Contributions welcome: policy packs, framework adapters, docs. See CONTRIBUTING.md.

📄 License

Apache 2.0 — see LICENSE.

Open-core: Local evaluation and CLI in this repo are open source (Apache 2.0). api.aport.io is a separate product for cloud features such as signed receipts, global kill switch, and team sync.

🔗 Links

npm package · APort · Docs
GitHub Issues · Discussions

Name		Name	Last commit message	Last commit date
Latest commit History 122 Commits
.changeset		.changeset
.claude-plugin		.claude-plugin
.cursor/rules		.cursor/rules
.github		.github
bin		bin
docs		docs
examples		examples
extensions/openclaw-aport		extensions/openclaw-aport
external		external
hooks		hooks
integrations		integrations
local-overrides		local-overrides
packages		packages
python		python
scripts		scripts
skills		skills
src		src
tests		tests
.editorconfig		.editorconfig
.env.example		.env.example
.gitignore		.gitignore
.gitleaks.toml		.gitleaks.toml
.gitleaksignore		.gitleaksignore
.gitmodules		.gitmodules
.npmignore		.npmignore
.shellcheckrc		.shellcheckrc
CHANGELOG.md		CHANGELOG.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
Makefile		Makefile
PUBLISHING.md		PUBLISHING.md
README.md		README.md
RELEASE.md		RELEASE.md
SECURITY.md		SECURITY.md
lerna.json		lerna.json
package-lock.json		package-lock.json
package.json		package.json
pyproject.toml		pyproject.toml
security.txt		security.txt
test.md		test.md
uv.lock		uv.lock

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

APort Agent Guardrails

CTF Evidence

Start Here

Install in 30 seconds

Why Developers and teams trust APort

Fast path by persona

Brand personality (optional)

🔌 Supported frameworks

🚀 Quick Start

🔒 Enforcement Options

🔌 Verification methods (local vs API)

⚡ Performance

📐 How It Works

🏛️ Security model (three layers)

What APort Protects

🌐 When to use API vs local

📖 Example outcomes

📜 Commands (after install)

📚 Documentation

🏗️ Architecture

🤝 Contributing

📄 License

🔗 Links

About

Uh oh!

Releases 22

Packages

Uh oh!

Uh oh!

Contributors

Uh oh!

Languages

Folders and files

Latest commit

History

Repository files navigation

APort Agent Guardrails

CTF Evidence

Start Here

Install in 30 seconds

Why Developers and teams trust APort

Fast path by persona

Brand personality (optional)

🔌 Supported frameworks

🚀 Quick Start

🔒 Enforcement Options

🔌 Verification methods (local vs API)

⚡ Performance

📐 How It Works

🏛️ Security model (three layers)

What APort Protects

🌐 When to use API vs local

📖 Example outcomes

📜 Commands (after install)

📚 Documentation

🏗️ Architecture

🤝 Contributing

📄 License

🔗 Links

About

Topics

Resources

License

Code of conduct

Contributing

Security policy

Uh oh!

Stars

Watchers

Forks

Releases 22

Packages 0

Uh oh!

Uh oh!

Contributors

Uh oh!

Languages

Packages