|
Oriva - private AI routing
One OpenAI-compatible endpoint. Route across providers with fallback, credentials, and usage tracking.
|
85 % |
|
ai-gateway — one endpoint for every AI model
ai-gateway — a self-hosted, OpenAI-compatible AI traffic control plane: virtual keys, routing and failover, guardrails, and balance-based billing, behind one...
|
84 % |
|
NorthDipper API
OpenAI-compatible AI gateway with model routing, quota controls, and operational visibility.
|
84 % |
|
Rootsys
An OpenAI-compatible API gateway. Many models behind one endpoint.
|
82 % |
|
compos — Programmable Infrastructure Platform
One runtime for the workloads behind your product. Push from Git, then add databases, workers, queues, storage, and agents to the same project — same identit...
|
82 % |
|
API Access Point — Semantic LLM Router with the Gateway Built In
A semantic LLM router with the gateway built in. Your product calls one endpoint; each request is classified, routed to the least effort that meets the goal,...
|
82 % |
|
unigate.sh
Unified AI gateway for developers. Connect all your AI tools to any LLM provider through a single local endpoint.
|
82 % |
|
Stoke — your agents, your machines, your rules
A single Rust gateway with hard budget caps, loop detection, local-first routing, and an embedded control room at /ui so you can watch enforcement happen in...
|
82 % |
|
RouteChain — Unified AI API Gateway for Developers (Light)
Access 50+ leading LLMs with a single OpenAI-compatible API key. Smart routing, zero log retention, and 99.9% uptime.
|
82 % |
|
Roost — one self-hosted dashboard for your machines
Run any CLI across your macOS and Linux machines from one self-hosted browser dashboard. Roost v0.5.0 supports automatic Tailscale Serve or direct HTTPS.
|
82 % |
|
Crane | Token Relay
Route 30+ frontier models through a single OpenAI-compatible endpoint. Millisecond routing, automatic failover, token-based billing.
|
82 % |
|
RouteMind — one endpoint for every AI model
RouteMind aggregates AI model providers behind a single API endpoint, with automatic failover, request caching and usage analytics. Billed by subscription an...
|
82 % |
|
sjetZ
Unified AI API gateway — one key, every model, built on New API.
|
82 % |
|
ompanion — a client for omp, on machines you own
ompanion drives omp (oh-my-pi), the open-source coding agent, over SSH on your own machines, from macOS, Windows, Linux, iOS and Android. No account and no d...
|
82 % |
|
GopherMind — an AI coding agent that asks first
A single Go binary that turns your own OpenAI-compatible model into a terminal coding agent. Local llama.cpp, Ollama, LM Studio, vLLM or hosted. Every mutati...
|
81 % |
|
GotoAi.one — OpenAI-compatible model gateway for routing, usage, and billing
Connect to multiple model providers through one OpenAI-compatible API with routing, usage controls, billing ledger, and an Enterprise governance roadmap.
|
81 % |
|
QuantSync | One endpoint for all your AI keys
Bring your own AI keys. QuantSync routes one request across cloud and local models and fails over when a provider hits a limit or goes down.
|
81 % |
|
Kyon — a terminal that answers to nobody but you
A GPU-rendered, block-structured terminal with a built-in editor, code search, SSH-native remote work, and AI that runs on your own keys. No account, no tele...
|
81 % |
|
milim — Local control plane for coding agents
Use your own models and subscriptions, keep one canonical coding-agent thread, review the diff, and ship with milim.
|
81 % |
|
Canopy — from outcome to working software
One local-first IDE with two ways to build: let Canopy plan, route and verify an outcome in Build mode, or take full control of the same project in Engineer...
|
81 % |
Detected social media networks