Self-Hosted AI Agents
Self-hosted agents ranked by verified user ratings.
Self-hosted AI agents run on your own infrastructure, so data never leaves your network and you control the model, updates, and access. The tradeoff is operational overhead. These agents are ranked by verified user ratings from teams running them in production.
AI agents
honcho
Memory library for building stateful agents
byterover-cli
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
Viper
Adversary simulation and Red teaming platform with AI
gpustack
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
sparrow
Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
genkit
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google
SQLBot
🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.
emdash
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
mcp-ui
UI over MCP. Create next-gen UI experiences with the protocol and SDK!
pyspur
A visual playground for agentic workflows: Iterate over your agents 10x faster
agentops
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
RWKV-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
Frequently asked questions
What is a self-hosted AI agent?
A self-hosted AI agent runs on infrastructure you control, such as your own cloud account or on-premise servers, rather than the vendor hosting it for you.
Why self-host an AI agent?
Teams self-host mainly for data privacy, compliance, cost control at scale, and the ability to customize or swap models.