Self-hosted alternatives to Twigg
200 self-hosted apps like Twigg, closest match first.
Top picks
- G
GoModel
LaunchAI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming,
FreeOpen sourceSelf-hosted
- R
Routerly.ai
LaunchSelf-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No da
FreeOpen sourceSelf-hosted
- O

OmniKey-AI-Unified-Key-Manager
LaunchA self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM platforms with automatic fallback, key scheduling, rate-limit tracking and encrypted credential storage
FreeOpen sourceSelf-hosted
- W
Webchat2api
LaunchOpenAI-compatible Web Chat API proxy with GPT, Grok, Gemini account management and Docker self-hosting
FreeOpen sourceSelf-hosted
- F
Faster Chat
LaunchFaster Chat is an open-source AI chat interface that you can self-host. You can run local models through Ollama or LM Studio, or connect to OpenAI, Anthropic, Groq, Mistral and other providers, including any OpenAI-compatible API. Conversat
FreeOpen sourceSelf-hosted
- N
NadirClaw
LaunchSource-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, n
FreeOpen sourceSelf-hosted
More like Twigg
About Twigg
Twigg
Stateful LLM API
Twigg is a hosted, stateful API for working with large language models. You create a chat once, then send only the next event, and Twigg stores the conversation, fits it to the context window of the model you choose, and routes the request to one of several providers. The providers listed are Anthropic, OpenAI, Google, xAI, Fireworks and OpenRouter, and you can switch models in the middle of a conversation. Twigg reports what each request cost. The product is aimed at developers building agents, chatbots, support bots and other LLM apps, who would otherwise manage message history and context length themselves. The conversation is kept outside the model providers, in Twigg's context store. The website explains that it is a JavaScript app, so the documentation is published as markdown files that can be read directly: an index at llms.txt, a complete file at llms-full.txt, a quickstart, an API reference and a model catalogue with prices. Every endpoint is under the /api/v1 path on the API host, and requests are authenticated with an API key sent as a bearer token. An OpenAPI specification is also published for the API.
- Category
- AI
- Website
- twigg.ai


