200 open source apps like Beam, closest match first.
Horay.ai
Unlock your AI Creativity with Horay.ai’s Blazing Fast
TheWhisper
Optimized Whisper models for streaming and on-device use
OS
Enables organizations to create and deploy customizable AI agents
GPT Load
Self-hosted AI gateway for multi-channel, multi-credential setups
vLLM
Inference and serving engine for large language models, built
whatcani.run
Find the best models and how to run them locally
mlx-serve
Native LLM inference server for Apple Silicon
Routerly.ai
Self-hosted LLM gateway that routes requests across AI providers
Duragraph
Self-hosted, enterprise-ready AI workflow orchestration
MOVO
Turn DeepSeek Harness into a self-hosted enterprise Agent platform
Agent Beacon
The cross-harness, self-improving memory layer for AI agents
Containarium
Open-source agent runtime — SSH-native isolation, eBPF egress policy…
Parakeet
OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX)
CliRelay
Self-hosted AI gateway for coding CLIs
Graviton
500B+ LLMs on a Mac Mini
Manifest
A complete backend in a single YAML file
Ryax Engine
Ryax is the low-code serverless and open-source solution
Kernel Images
Browsers-as-a-service for automations and web agents
Atom
Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation
Olla
High-performance lightweight proxy and load balancer for LLM infrastructure
CrewAI-Studio
A user-friendly, multi-platform GUI for managing and running CrewAI agents
LocalAI
Run LLMs, speech, image generation
pooled
Peer-to-peer LLM inference in the browser: pool your devices
OpenGateLLM
An open-source, unified interface for running and managing self-hosted LLMs
Devopness
AI DevOps on your cloud
MistLock
Catalog of Cloud dev environments
AgentPipe
High performance multithreaded task execution and optimization engine
1backend
Build AI (or any) apps with scalable microservices & microfrontends
VoidLLM
Privacy-first LLM proxy and AI gateway
Zetaforgedev
Open source AI platform for rapid development of advanced AI and AGI pipelines
Oxideterm
AI-native workspace for local shells and remote machines.Zero Webview
BodhiApp
Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs
Ai00 Server
The all-in-one RWKV runtime box with embed, RAG, AI agents, and more
DaoCloud-docs
DaoCloud Documentation
Agenvoy
Self-hosted 24/7 personal AI agent that runs on your own machine
Greywall
Container-free, deny-by-default sandbox for AI coding agents
LLM Gateway
Route, manage, and analyze LLM requests across multiple providers with one API
Web LLM
High-performance In-browser LLM Inference Engine
Skillhub
Self-hosted, open-source agent skill registry for enterprises
BOSS Console
Open-source, multi-platform harness for AI agents
Valmis
The AI Agent designed for work with security in mind
Agents
AI agent tooling for data engineering workflows
Yantr
A self-hosted homelab app store for rootless Podman
Eigent
Self-hostable desktop app that runs a coordinated team of AI agents
Deepseek Harness Desktop
Open-source Windows desktop client and GUI for DeepSeek Harness
Opengeni
Open, self-hostable agentic service for organizations
Peon
Open-source, self-hostable deployment platform
vllm-mlx
High-performance OpenAI and Anthropic compatible LLM inference server
BaseAI
A platform for building and deploying AI products
LitterBox
A self-hosted sandbox for red teams