Self-host Agenvoy
v1.2.2Local AI agent that builds tools and runs 24/7
- Stars
- 613
- Port
- 17989 (Web dashboard)
What is Agenvoy?
A Go-written AI agent that operates as a local daemon on your computer. It transforms natural language into completed tasks by breaking them down, running tools, and delivering outcomes while storing all data locally. Missing tools are created, tested in a sandbox, and kept for reuse. An integrated MCP server allows Claude Code, Codex, and other MCP clients to access the same sandboxed toolset. A browser dashboard at localhost:17989 provides a UI with live voice chat. Eleven model providers plus any OpenAI-compatible endpoint are supported with automatic routing, cron scheduling, a three-level memory system, and Telegram/Discord bots using outbound connections only. Setup requires one curl command. The project uses AGPL-3.0 with a commercial option.
Should you self-host Agenvoy?
Agenvoy scores 51/100 on selfhost.directory (how scoring works) and ranks #33 of 120 in AI Assistant. It has 613 GitHub stars.
It shipped 10 stable releases in the past year. The latest, v1.2.2, came out on 22 October 2026. New versions land roughly every 3 days.
Setup is easy: most people get it running in one sitting. It is AGPL-3.0-licensed and written mostly in Go.
Its closest alternative on selfhost.directory is hermes-agent (89/100, 257 885 stars). It scores higher overall, so compare the two before you pick. See Agenvoy vs hermes-agent side by side.
Features
- 3-tier memory
- Auto tool generation
- File operations
- MCP Client
- MCP Server
- Multi-model dispatch
- RAG integrationOptional; requires KuraDB
- Realtime voice
- Sandboxed Execution
- Scheduler
- Self-improvement
- Skill System
- Sub-agents
- Telegram & Discord bots
- Web Search & Fetch
Agenvoy README
More in Local AI
Agora CosmicaSelf-hosted, open-source education platform where 30 historical figures teach through narrated stories, teachings, debates, and live AI conversation.
AI GridAI Grid is a self-hosted, open-source orchestrator that pools your computers into a single OpenAI-compatible endpoint for local LLM inference and training.
airunnerSelf-hosted, open-source desktop AI engine: local LLM chat companions, Stable Diffusion art generation, TTS/STT voice, and a headless Ollama/OpenAI-compatible API.
aixclSelf-hosted platform for running LLMs locally with Vault secrets, GPG-signed commits, and rootless Podman. Includes Open WebUI, pgAdmin, Grafana, and BYO app framework.
AnyLoom-AnythingLLM-Local-AI-agentic-DyTopo-swarmSelf-hosted AI assistant with Qwen3-30B, hybrid RAG, multi-agent swarm, and AnythingLLM UI — all 100% local on your GPU.
AnythingLLMAnythingLLM is a self-hosted, open-source AI app for document chat, AI agents, and local/cloud LLMs — running on your hardware with no token limits.
ATLASOpen-source, self-hosted AI coding agent for your own GPU. It wraps compact GGUF models in a verify-before-write pipeline with a sandboxed executor and a terminal UI.
Atomic ChatSelf-hosted desktop/mobile app for running LLMs locally with OpenAI-compatible API. 1000+ models, multiple engines, MCP, agent launching.
BelullamaSelf-hosted AI app bundling Ollama, Open WebUI, and Automatic1111 for local LLMs and image generation with one-command Docker install.
chatbot-ollamaSelf-hosted, open-source chat web UI for Ollama: stream local model replies, upload documents and images, and switch between dark and light themes.
chatbot-uiOpen-source AI chat app you self-host with a Supabase backend, supporting OpenAI, Anthropic, Gemini, Mistral and Azure keys plus local Ollama models.
DreamServerSelf-hosted local AI server that installs models, Open WebUI, voice, workflows, RAG, and agents on your hardware. Replaces CloudAI services with one-command setup.
0 comments