YOUR PERSONAL AI GATEWAY

KeyKing - The Zero-Trust Free AI API Aggregator to run Free Claude Code and Manage API Keys Locally.

One API Key.
Every
AI Model.

Stop pasting your real API keys into every new project. KeyKing securely stores your keys on your computer and gives you one universal local endpoint. It automatically switches providers if you hit a rate limit.

Install Desktop Proxy:curl -fsSL https://keyking.ledgion.in/install.sh | bash
Install Serverless SDK:npm install keyking-sdk
No Cloud Storage Local Rust Proxy (1.2ms) 255+ AI Providers
KEYKING DESKTOP - v4.0.0
Dashboard Metrics
PROXY PORT: 8787
Active Keys3
Requests (24h)1,280
Latency Savings-140ms
Encrypted Providers
OpenAI (Primary) SECURE & ACTIVE
Gemini (Fallback) SECURE & ACTIVE
Groq (Smart Quota) SECURE & ACTIVE
LIVE DECISION LOGS● ONLINE
[19:04:12] POST /v1/chat/completion ➔ Decrypted local OpenAI API key
[19:04:13] POST /v1/chat/completion ➔ Route status: 200 OK (OpenAI, 184ms)
[19:12:01] POST /v1/chat/completion ➔ OpenAI 429 Quota Exhausted! Circuit Tripped.
[19:12:01] POST /v1/chat/completion ➔ Executing fallback sequence: Mapping request ➔ Groq (llama-3.3)

The Universal AI Catalog

Over 255+ providers and 1,000+ models with zero-trust local routing. From massive free monthly tiers (Mistral, Gemini, Groq, Cerebras) to full aggregator gateways (BazaarLink, OpenRouter) and Claude Code relays (AgentRouter, Lumos). Drop in your keys and code seamlessly.

Mistral La Plateforme

~1B/mo shared

Mistral Large/Medium, Codestral

Google Gemini

~3M/mo per model

Gemini 2.5 Flash, Flash-Lite

Groq

~30M/mo per model

Llama 3.3 70B, Qwen3

Cerebras

~30M/mo shared

Llama 3.1 8B, Qwen3

OpenRouter

~6M/mo per model

19+ Free Models

SambaNova

~3M/mo shared

DeepSeek V3.1, Llama 3.3

Cloudflare Workers AI

~20M/mo shared

Qwen3, Llama 4

GitHub Models

~18M/mo est.

GPT-4o, GPT-4.1

Cohere

~1-2M/mo shared

Command R+

BETA FEATURE Zero Repo Pollution

AI Context Manager &
Codebase Reverse-Engineering

Got a raw codebase with zero documentation? KeyKing scans your files, package manifests, and schemas to synthesize dense, zero-bloat architecture specs. When you drop markdown files or PRDs, AI strips conversational filler and prioritizes core invariants before sending to Claude, Cursor, or Aider.

1. Auto Codebase Derivation

No docs needed. KeyKing indexes directory structures, database schemas (Prisma, SQL), API routes, and core types into 3 dense architecture blueprints: Architecture Overview, Data Models & Schema, and API Surface Map.

⚡ HIGH PRIORITY ARTIFACTS
✔ Auto-derived in 850ms
✔ Stored in OS User Profile

2. Zero-Bloat AI Debloating

Drop architecture documents or PRDs. The AI removes conversational preambles, repetitive examples, and formatting fluff, cutting token consumption by up to 80% and sorting by High/Medium/Low priority.

🔥 -74% TOKENS SAVED
✔ Strips boilerplate fluff
✔ Dense markdown synthesis

3. Auto-Primed Agent Launch

Run keyking run or keyking claude. KeyKing injects your active sprint goal, git branch context, and distilled high-priority artifacts directly into the agent's priming kick-off prompt.

👑 UNIVERSAL INTERCEPTOR
✔ Claude Code • Aider • OpenCode
✔ Zero config required

One Gateway, Five Powerful Capabilities

KeyKing v4.0.0 unites universal multi-provider local routing, AI codebase reverse-engineering, zero-bloat context distillation, and seamless agent interception under one unified local engine.

LOCAL DEVELOPMENT

Desktop Proxy

Ideal for vibe-coding. Run the high-performance Rust proxy binding to localhost:8787. Route Cursor, Claude Code, Aider, OpenCode, and local scripts with automated token telemetry and zero dotfile leaks.

Localhost:8787
AI CONTEXT MANAGER (BETA)

Codebase Reverse-Engineering

Zero documentation? KeyKing scans manifests, routes, and schemas to auto-derive high-density architecture specs. Auto-debloats dropped docs by priority to cut context bloat by up to 80% with zero repo dotfiles.

Zero Repo Pollution
UNIVERSAL AGENT LAUNCHER

Zero-Config Agent Wrappers

Run Claude Code, Aider, OpenCode, and Codex with one command: keyking run or keyking-claude. Pre-primed with distilled codebase context and routed through 255+ providers.

Claude • Aider • OpenCode
PRODUCTION DEPLOYMENT

Serverless SDK

Deploy to production using @keyking/sdk. Purpose-built for serverless environments (Vercel, AWS Lambda, Cloudflare Workers) to unpack encrypted vaults in memory with zero cloud lock-in.

NPM SDK
KEY ENCRYPTION & VAULT

Hardware Derived Vault

Secure local credential management. Encrypts all your LLM provider API keys using hardware-derived AES-256-GCM + PBKDF2. Keys never touch third-party servers or telemetry collectors.

AES-256-GCM
DYNAMIC FAILOVER

Priority Fallback Ladders

Automatic failovers across 255+ providers. If Anthropic or OpenAI returns a 429 rate limit, requests instantly cascade to DeepSeek, Mistral, Gemini, or Groq with zero broken connections.

Zero Downtime

Interactive Proxy
Playground

Experience the routing engine without downloading the desktop client. Switch between developer code integrations below, and click the simulation button to watch Key King's local proxy decrypt, select quotas, execute, and stream responses.

CODE TEMPLATE // CURL
curl http://localhost:8787/v1/chat/completions \
  -H "Authorization: Bearer kk-5a3d8f92b7c64e018d9f1c" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 0.7
  }'
LOCAL PROXY STDOUT (SIMULATOR)
Ready. Trigger "Send Test Request" to begin transaction.

Transparent, developer-first billing

Deploy locally at no cost, or scale seamlessly with our enterprise Ultra subscription plan. Payment processing and subscription management are handled securely.

FREE WORKSPACE

Community Free

LOCAL DEVELOPMENT ENVIRONMENT

$0/ forever
  • Lock up to 2 API keys
  • Register up to 2 machines
  • Basic routing (no priorities)
  • Rate limit: 30 requests/minute
  • Full AES-256-GCM local storage
KEYKING ULTRA // RECOMMENDED

Ultra Plan

PRODUCTION-GRADE MANAGEMENT PLATFORM

PREMIUM
$2/ month
  • Unlimited API keys & vault space
  • Unlimited machine registrations
  • Smart prioritized quota routing
  • Unlimited request speed rates
  • Instant fallback & circuit breaker protection

Developer FAQs

Detailed information regarding the local proxy security model, architecture, and subscription billing.