BREAK THE LOOP before it breaks YOUR BUDGET.

Loopers is the firewall for the agentic era. It acts as a baremetal, zero-delay circuit breaker that intercepts requests to prevent token overspending, stop runaway agent loops, and safeguard against catastrophic bill shocks like LLMjacking.

/* Start in 30 sec */
$ docker pull ghcr.io/cursed-me/loopers-oss

[ AUDIT LOGS ]

Why autonomous AI infrastructure needs a firewall, not a dashboard.

INCIDENT-001Critical

LLMjacking

Attackers steal API keys from public repos, deploy agents, and leave you with the bill. Sysdig documented a 376% spike in AI credential theft.

$100,000/DAY
from one compromised Claude Opus key.
INCIDENT-002Critical

Agent Runaway

Autonomous agents stuck in retry loops scale costs silently. Token cost grows O(n²) in agent steps. The loop doesn't sleep.

$47,000
bill after an 11-day stuck retry loop.
INCIDENT-003Critical

Provider Gaps

Google's caps have a 10-minute enforcement lag. AWS Budgets exclude Marketplace charges entirely by design. They don't stop the bleed.

$30,141
AWS Bedrock bill. Zero alerts fired.

Why Loopers?

If an autonomous agent gets stuck in a loop or an API key is compromised, it can burn thousands of dollars in minutes. Loopers isn't just an alert or an observability dashboard—it's a strict, fail-closed firewall with an active kill-switch.

[ CORE ARCHITECTURE ]
FEATURE_01[ACTIVE]

Atomic Correctness Guarantee

Executes checks in a single Redis Lua transaction, preventing TOCTOU race conditions under extreme concurrency.

FEATURE_02[ACTIVE]

Zero-Storage Security Model

Pass-through architecture. Your API keys are only kept in-memory during request lifecycles. Zero persistence to disk/database, rendering it immune to data breaches.

FEATURE_03[ACTIVE]

Sub-Millisecond Overhead

Written in Go using httputil.ReverseProxy and Redis, adding only ~1-2ms of latency to the request path. No cold starts, no blocking streaming performance.

FEATURE_04[ACTIVE]

Fail-Closed Guarantee

Fails closed if Redis or the proxy goes down, instantly blocking requests to protect your wallet.

FEATURE_05[ACTIVE]

Mid-Stream Cutoffs

Intercepts streaming Server-Sent Events (SSE) responses, counts tokens in real-time, and severs the connection instantly if limits are exceeded.

How it works

01

Point your SDK

That's the entire integration.

openai.base_url = "https://gateway.tryloopers.com/v1"
02

Set your caps

Any granularity you need.

loopers budget set --key my-app --daily 50.00
03

Sleep

Your key is never stored. It's injected into the provider call, then discarded on response. We can't lose what we never had.

Performance Benchmarks (Episode 1)

Loopers is engineered to handle massive concurrent traffic spikes without dropping the ball on budget enforcement. In our latest LLM Gateway benchmarks against Python/FastAPI alternatives, Loopers demonstrated absolute dominance.

[ LOAD TEST RESULTS ]
Budget Leakage (1,000 req flood)
Loopers (Go)
0% ($0.00)
LiteLLM
0.17% ($0.000017)
Advantage
Complete Protection
Peak Throughput (RPS)
Loopers (Go)
4,623 req/s
LiteLLM
~176 req/s
Advantage
25x Faster
Proxy Overhead (P99 Latency)
Loopers (Go)
240.98 ms
LiteLLM
46,812.60 ms
Advantage
190x Lower Latency
Resource Footprint (Idle RAM)
Loopers (Go)
41.58 MB
LiteLLM
957.83 MB
Advantage
23x Lighter
Metric
Loopers (Go)
LiteLLM
Advantage
Budget Leakage (1,000 req flood)
0% ($0.00)
0.17% ($0.000017)
Complete Protection
Peak Throughput (RPS)
4,623 req/s
~176 req/s
25x Faster
Proxy Overhead (P99 Latency)
240.98 ms
46,812.60 ms
190x Lower Latency
Resource Footprint (Idle RAM)
41.58 MB
957.83 MB
23x Lighter

[ SPEC SHEET ]

Technical comparison vs alternatives

Type
Loopers
Active Firewall
Bifrost
OSS Gateway
AgentBudget
Python SDK
LiteLLM
OSS Gateway
Pre-Call Enforcement
Loopers
[X] Yes (Atomic Lua)
Bifrost
[X] Yes
AgentBudget
[X] Yes
LiteLLM
[-] Partial
Storage Security
Loopers
Zero-Storage
Bifrost
In-Memory
AgentBudget
In-Process
LiteLLM
DB Required
Agent Loop Circuit Breaking
Loopers
[X] Yes
Bifrost
[ ] No
AgentBudget
[X] Yes
LiteLLM
[ ] No
Fail-Closed Guarantee
Loopers
[X] Yes
Bifrost
[-] Varies
AgentBudget
[-] N/A
LiteLLM
[ ] No
Control
Bifrost
AgentBudget
LiteLLM
Loopers
Type
OSS Gateway
Python SDK
OSS Gateway
Active Firewall
Pre-Call Enforcement
[X] Yes
[X] Yes
[-] Partial
[X] Yes (Atomic Lua)
Storage Security
In-Memory
In-Process
DB Required
Zero-Storage
Agent Loop Circuit Breaking
[ ] No
[X] Yes
[ ] No
[X] Yes
Fail-Closed Guarantee
[-] Varies
[-] N/A
[ ] No
[X] Yes

Fully Transparent. MIT Licensed.

Any piece of software that sits between your application and your AI provider must be fully transparent. Inspect every line. Fork it. Run it yourself.

The managed SaaS adds anomaly detection, team controls, and compliance reporting — that's what you pay for. The core kill switch is open.

Pre-call budget enforcement (Atomic Lua)
OSS
Cloud
10 provider support
OSS
Cloud
5 budget time-windows
OSS
Cloud
Mid-stream SSE cutoff
OSS
Cloud
Fail-closed Redis guarantee
OSS
Cloud
Zero-storage pass-through key model
OSS
Cloud
Agent loop circuit breaker / loop detection
OSS
Cloud
MCP tool-call interception
OSS
Cloud
Tool-call circuit breaking
OSS
Cloud
Prometheus metrics + OTel export
OSS
Cloud
Single-key budgets
OSS
Cloud
Helm chart & Docker Compose
OSS
Cloud
Hierarchical budgets (Org -> Team -> Key)
OSS
Cloud
Web dashboard & spend analytics
OSS
Cloud
Policy-as-Code Engine (OPA/Rego)
OSS
Cloud
Behavioral anomaly detection (LLMjacking)
OSS
Cloud
Agent registry & identity
OSS
Cloud
Team management & RBAC
OSS
Cloud
Tamper-proof audit log
OSS
Cloud
Slack / PagerDuty / Webhook alerts
OSS
Cloud
Automated Compliance (EU AI Act, SOC 2)
OSS
Cloud
Business+
SSO / SAML
OSS
Cloud
Business+
Managed infrastructure
OSS
Cloud
Support
OSS
Community
Cloud
Priority / Dedicated
FeatureOSS (Self-Hosted)Loopers Cloud
Pre-call budget enforcement (Atomic Lua)
10 provider support
5 budget time-windows
Mid-stream SSE cutoff
Fail-closed Redis guarantee
Zero-storage pass-through key model
Agent loop circuit breaker / loop detection
MCP tool-call interception
Tool-call circuit breaking
Prometheus metrics + OTel export
Single-key budgets
Helm chart & Docker Compose
Hierarchical budgets (Org -> Team -> Key)
Web dashboard & spend analytics
Policy-as-Code Engine (OPA/Rego)
Behavioral anomaly detection (LLMjacking)
Agent registry & identity
Team management & RBAC
Tamper-proof audit log
Slack / PagerDuty / Webhook alerts
Automated Compliance (EU AI Act, SOC 2)Business+
SSO / SAMLBusiness+
Managed infrastructure
SupportCommunityPriority / Dedicated

Frequently Asked Questions

Direct answers for developers and engineering teams.

What happens if my AI agent gets stuck in an infinite loop?

AI providers like OpenAI charge for every word generated. If your code has a bug and makes endless requests, you could wake up to a massive surprise bill. Loopers sits between your app and the AI provider. You set a strict spending limit, and Loopers automatically blocks any requests that go over budget.

Can't I just use the budget limits on the OpenAI dashboard?

Provider dashboards update slowly and usually only let you set account-wide limits. If you hit that limit, your entire application goes down. Loopers acts as an active firewall, letting you set real-time, custom budgets for specific users, projects, or API keys. This means one bad actor or bug can't take down your whole system.

How does Loopers protect against stolen API keys?

Hackers constantly search for exposed AI API keys to steal and use on your dime—a fast-growing attack known as LLMjacking. Loopers protects you by enforcing strict daily or hourly spending limits. Even if a key is stolen, the hackers are instantly blocked the moment they hit the limit you defined.

Will routing requests through Loopers slow down my app?

No. Loopers is designed to be extremely fast. It checks budgets instantly before forwarding your request to the AI provider. It adds only ~1-2ms of latency to the request path, which is completely unnoticeable compared to the time it takes the AI to actually generate a response.

Join the Waitlist

No spam. No growth hacks. One email when we launch.