Swiss Army Knife
for AI Apps.

Open-source desktop app for centrally managing LLMs, MCPs, and Skills.

RoutingProtect Monitor Debug Modify

Built with Claude and a hammer.

Works With

AI Apps

Claude Code
Cursor
</>
Open WebUI
LocalRouter
Permission Request
Claude Code wants GitHub
Allow
Deny
Connects to

Any LLM Provider

OpenAI
Ollama
Connects to

Any MCP / Skill

GitHub

App Demo

UI preview only, no live functionality

Desktop powered by WinXP theme

Three ways to connect

Via Gateway or Proxy

Connect clients via the Gateway — an explicit OpenAI-compatible endpoint that routes every request across your providers — through the HTTPS Proxy, a transparent pass-through that leaves tools like Claude Code and Codex on their own provider and subscription — or with the Reverse Proxy, which wraps a local provider on its own port so apps you have already configured need no changes at all.

  • Via Gateway

    A drop-in /v1 API — one base URL and key, routed to 19+ providers, plus typed System One decisions on /v1/systemone

    ANTHROPIC_BASE_URL=http://localhost:3625 claude
  • Via HTTPS Proxy

    The tool keeps its own subscription and provider — every request shows up in the Monitor with tokens and cost, forwarded unchanged

    HTTPS_PROXY=http://localhost:3626 claude
  • Via Reverse Proxy

    Wrap a local provider: Ollama is restarted on a new port and LocalRouter takes over the original one. Every app already pointing there keeps working untouched — and every call becomes visible

    ANTHROPIC_BASE_URL=http://localhost:11434 claude

    Same address as before — nothing in the app changes

Claude Code · Codexor any app you already useLocalRouterGATEWAY:3625orHTTPS PROXY:3626orREVERSE PROXY:11434Ollama's own portAnthropicOpenAI17+ morerouted to the best modelsame provider,same accountobserved · forwarded unchangedforwardedOllama:11434→:11435restarted on a new portapps keep using :11434
STATE“I was charged twicethis month and need arefund before Friday.”QUESTIONSchoicewhich department?scorehow urgent?noulrefund requested?System OneJev · Ollaya · Kevor any chat modeldepartmentbilling85%technical10%sales5%urgencyscore 1.6 / 20 · can wait4%1 · normal30%2 · today66%refund requestedyes95%typed answers · calibrated probabilities
Typed decisions

System One decisions

Ask typed questions about a state (which option, what score, yes or no) and get calibrated probabilities back instead of text to parse. LocalRouter serves TypeSafe's System One API at /v1/systemone, so the TypeSafe SDK works by changing its base URL.

  • Native decision models

    TypeSafe's hosted Jev, or Ollaya, Kev and Ollama decision models on your own machine

  • Any chat model, translated

    Chat models answer too, with probabilities from token logprobs where the provider returns them and from JSON otherwise

  • Same protections as chat

    Guardrails, secret scanning, prompt compression and the Monitor all cover decision requests

Free-Tier Only
enabled
O
OllamaAlways Free
G
GeminiRPD: 82/250
G
GroqRPM: 2/30
OR
OpenRouter$0.00 remaining
OA
OpenAINo Free Tier
Available
Low
Exhausted
Skipped

Free Tier Exhausted

All free-tier models are at capacity. Proceed with paid models?

Client:Claude CodeTool:openai/gpt-4oServer:openai
Cost Control

Free-Tier Mode

Add all your providers and let LocalRouter use only free-tier resources until they're exhausted. No surprise bills — the router automatically tracks each provider's free tier and skips exhausted ones.

  • Provider-aware tracking

    Handles rate-limited (Gemini, Groq), credit-based (OpenRouter, xAI), and always-free (Ollama) providers with a single toggle

  • Smart backoff

    Reads rate limit headers from every provider. When one hits 429, it's skipped instantly — no wasted round-trips

  • Graceful exhaustion

    When all free providers are at capacity, returns 429 with a retry-after header so clients know when to try again

Learn more
Credential Management

Centralized Credential Store

Store provider API keys once. Issue per-client keys with scoped permissions. All secrets encrypted in OS keychain.

  • Multiple auth methods

    API key, OAuth, or STDIO-based authentication per client

  • Scoped access

    Restrict each client to specific models, providers, and MCP servers

  • OS keychain storage

    Secrets encrypted via macOS Keychain, Windows Credential Manager, or libsecret

Learn more
Clients
CursorCursor
key-1
C
Cline
key-2
Open WebUIWebUI
key-3
Auth
LocalRouter
API
Providers
sk-...4f
OpenAIOpenAI
sk-...8k
AnthropicAnthropic
gsk-...2n
G
Groq
System Keychain
All keys securely stored
Encrypted
Client Keys
Provider Keys
model: "auto"Planning?(Your policy)YesNoPLANNINGYour planning modelOTHER WORKYour default modelfailfailFALLBACK PROVIDERAnthropic / GeminiFALLBACK PROVIDERAnthropic / GroqfailfailOFFLINE FALLBACKLlama 4 405B (local)OFFLINE FALLBACKLlama 3.2 3B (local)✓✓✓✓✓✓
Planning Route
Default Route
Provider Fallback
Offline Fallback
Smart Routing

Automatic Model Routing

Request model: "auto" to apply your routing policy. Automatic failover on rate limits, outages, or policy errors.

  • User-defined routing policies

    Choose a decision provider, write your question, and map each answer to a model. Explicit client mode rules run without inference.

  • Offline fallback

    Falls back to local Ollama/LMStudio models when cloud providers are unreachable

  • Provider failover chain

    Configure primary → secondary → offline provider sequence per route

  • Decision-model routing

    Choose a decision model, define your question and map its answers to destination models

Learn more
MCP Gateway

Unified MCP Gateway

Reverse proxy merging multiple MCP servers into one endpoint. Tools from all servers appear in a single namespace with client-level access control.

  • Unified tool namespace

    All MCP server tools aggregated under one STDIO or SSE endpoint

  • Client-level server restrictions

    Whitelist specific MCP servers per client—others are hidden

  • Context Management

    98% catalog compression with FTS5 search—tools loaded on-demand via ctx_search

Learn more
Skills

Skills via MCP

Multi-step workflows exposed as callable MCP tools. Web search, code review, document summarization—each skill chains multiple operations behind a single tool call.

  • Composite workflows — orchestrates API calls, file I/O, shell commands as atomic tools
  • Per-client whitelist — assign specific skills per client
  • Standard MCP interface — compatible with any MCP client
Learn more
Coding Agents

AI Coding Agents via MCP

Orchestrate AI coding agents as MCP tools. Claude Code, Gemini CLI, Codex, and more — managed through unified MCP tools.

  • 10 agents — Claude Code, Gemini CLI, Codex, Amp, Aider, and more
  • Session-based — long-lived with bidirectional communication
  • Approval routing — tool approvals forwarded via MCP elicitation
Learn more
Marketplace

Marketplace for MCP & Skills

Browse and install MCP servers and skills from registries. AI-assisted discovery via MCP tools. All installs require your approval.

  • Multiple registries — official, community, and private sources
  • MCP-exposed search — AI agents query and suggest installations
  • Gated installation — explicit approval required for every package
Learn more
MCP via LLM

MITM MCP Injection

Optionally inject MCP tools into LLM requests and execute tool calls server-side. Gives MCP capabilities to clients that don't natively support MCP — no client changes needed.

  • Optional per-client — enable for clients without MCP support, disable for those that have it
  • Agentic loop — automatic tool call → execute → resume cycles
  • Mixed tools — MCP tools run server-side, client tools returned normally
Learn more
UPSTREAM SERVERSAPPSVocalCordEvents streamAny MCP serverEvents pollNetGetChannelLocalRouterone eventBlock · Ask · AllowMonitortranslatesame event idClaude CodeChannelOpenClawWebhookCodexPolling toolsheld
Push Event Approval

Held until you decide, before it reaches the app

Client:Claude CodeEvent:vocalcord__message.received
Deny
Edit
Allow
Push Relay

Push Notifications, Translated

MCP servers can push events — new messages, finished jobs, alerts. LocalRouter receives every kind of push and delivers it in whatever form each app understands, so a server speaking MCP Events can wake Claude Code through Channels, and an app with no push support at all still gets it through polling tools.

  • Any push in, any push out

    MCP Events (push, poll, and webhooks out to apps), Claude Code Channels and resource updates, translated between each other automatically

  • See and control every event

    Allow, Ask or Off per app, server and event type; inspect, hold or edit events in Monitor before they reach the app

  • Works with every app

    Native push where the app supports it, LocalRouter's polling tools where it doesn't

Learn more
Reversible secret redaction

Keep the secret.
Send the placeholder.

LocalRouter holds the original in your OS credential store. The model gets a unique reference. When it returns that reference, LocalRouter puts the secret back.

1. Hold locally

Original credential

API_KEY=demo-only-secret
OS credential store
Keychain · Credential Manager · Linux credential backend
2. Send the reference

What the model sees

<localrouter-redacted id='abc123' usage='Unmasked when returned verbatim'/>

The model can copy the reference into its reply or a tool call.

3. Restore on return

Reference returned → original restored

<localrouter-redacted id='abc123'/>

write_file → .env

API_KEY=demo-only-secret

The file gets the original. Tool results are protected again before the next model call.

Synthetic example with a shortened ID. Applies to supported text gateway and active proxy requests. Tool permissions still apply; the model can request use of a reference. References belong to one client and persist for 14 days of inactivity. No extra system prompt is added.
Safety

Runtime Safety

Every request passes through LocalRouter's safety layer — content scanning, secret detection, approval gates, and MCP permission controls. Configurable per client, model, and server.

  • Multi-layer protection

    Content safety scanning, secret detection, and runtime approval gates all run in the request pipeline

  • Interactive approval popups

    Inspect, modify, allow, or deny any operation in real time — from tool calls to LLM sampling requests

  • Per-client policies

    Granular rules per client, model, MCP server, and skill — allow once, for session, or deny

Learn more
Clients
Open WebUIWebUI
C
Cline
CursorCursor
LocalRouter
Safety Layer
Resources
Marketplace
Skills
MCPs
LLMLLMs
GuardRails

Content Safety Inspection

Scan LLM requests and responses for prompt injection, jailbreaks, PII leakage, and code injection. When a rule triggers, a popup lets you allow or deny.

  • Multi-source detection — built-in rules, Microsoft Presidio, LLM Guard
  • Moderation API — OpenAI-compatible /v1/moderations endpoint
  • Parallel scanning — zero-latency overhead on clean requests
Learn more
Secret Scanning

Secret Scanning

Scans outbound requests for API keys, tokens, and passwords before they reach providers. Multi-stage pipeline with regex matching and Shannon entropy filtering.

  • Regex + Shannon entropy — multi-stage pipeline catches real secrets, ignores false positives
  • Three actions — Ask (popup), Notify (alert), Off — per-client override
  • Time-based bypass — approve once for a configurable period
Learn more
Firewall

Runtime Approval Firewall

Interactive approval prompts for sensitive operations. Inspect and modify tool arguments, model parameters, and API payloads in real time.

  • Request inspection & modification — edit tool args, model params before they reach their destination
  • Granular policies — per-client, per-model, per-MCP server, per-skill
  • Allow once / for session / deny — configurable per client
Learn more
MCP Permissions

Elicitation & Sampling

MCP servers can request user input via structured forms and route LLM completions through your configured providers — all gated by approval policies.

  • Elicitation — servers request structured user input via JSON Schema popup forms
  • Sampling — servers request LLM completions routed through your providers
  • Gated access — Allow / Ask / Deny policies per server
Learn more
Optimizations

Built-in Optimizations

Automatic repairs, intelligent compression, and token optimization — all running transparently in the request pipeline with zero configuration required.

  • Pipeline stages run in parallel

    JSON repair, catalog compression, output indexing, and history compression execute concurrently — no added latency

  • Zero-config defaults

    Works out of the box with sensible defaults — per-client overrides available for every stage

  • Transparent to clients

    All optimizations happen between your app and the provider — no client-side changes needed

</>
Client
Compressed Chat History
Deferred Loading
Response Healing
Indexed Tool Output
LocalRouter
MCP Gateway
Optimized request
Raw response
LLM
Compresses past messages in history
Fixes malformed JSON responses
Defers MCP tools, loads on-demand
Indexes file reads, scripts, web fetch
Context Management

Deferred Loading

Progressive compression shrinks MCP tool catalogs to fit any context window. FTS5 search index lets AI discover and activate tools on-demand.

  • 3-phase compression — descriptions, servers, then counts
  • Search activation — ctx_search discovers deferred tools
  • Auto-tuned — thresholds adapt to your context window
Learn more
JSON Repair

Automatic Response Healing

LLMs return malformed JSON — trailing commas, missing brackets, wrong types. LocalRouter fixes it automatically before it reaches your app, including during streaming.

  • Syntax repair — fixes commas, brackets, quotes, fences, and prose wrapping
  • Schema coercion — coerces types, normalizes enums, strips extra fields
  • Streaming — character-at-a-time state machine, no buffering
Learn more
Context Mode

Indexed Tool Output

Large outputs from Bash, WebFetch, and MCP tools are automatically indexed into a searchable FTS5 store. AI retrieves relevant fragments on demand instead of flooding context.

  • Auto-indexing — tool outputs above threshold are indexed and truncated
  • Search retrieval — AI queries indexed content via ctx_search
  • Configurable — per-client thresholds, retention, and indexing rules
Learn more
Prompt Compression

Compressed Chat History

LLMLingua-2 compresses older messages in chat histories by removing redundant tokens. Recent messages are preserved intact. Extractive only — zero hallucination risk.

  • Past messages only — recent messages preserved, older history compressed
  • Extractive — keeps original tokens, no paraphrasing or generated text
  • Per-client config — compression rate, min messages, preserved recents
Learn more
MemoryExperimental

Persistent Conversation Memory

LLMs recall past conversations across sessions. Per-client isolation with automatic transcript capture and semantic search via Zillis memsearch.

  • Per-client isolation

    Each client gets its own memory index and directory — no cross-client data leakage

  • Auto-capture

    Transcripts saved automatically in MCP via LLM and Both client modes

  • Semantic recall

    MemoryRecall virtual MCP tool with hybrid vector search across all past sessions

  • Session compaction

    LLM-powered summarization at session boundaries — raw transcripts archived for re-compaction

Learn more
U

What did we discuss about rate limiting last week?

MemoryRecall
{ query: "rate limiting configuration" }
Session from Mar 8

Discussed per-client rate limits: 100 RPM for Cursor, 50 RPM for Cline. Set cost limit of $5/month for OpenAI provider. Configured token limits at 100k input / 8k output...

A

Last week you configured rate limits for two clients: Cursor at 100 RPM and Cline at 50 RPM, with a $5/month cost cap on OpenAI...

Local-Only by Design

Runs entirely on your machine. Zero telemetry, zero cloud sync, zero analytics.
API keys and request payloads never leave your device.

No telemetry
No cloud sync
Open source
Runs offline
Learn more

Get Started

Download, configure providers, point your apps to localhost:3625.