Magec MCP server

Magec

---

Define multiple AI agents, each with its own LLM, memory, and tools. Chain them into multi-step workflows. Access via voice, Telegram, webhooks, or cron. Manage it all from a visual admin panel.

Your server, your data, your rules.

Quick Start

One-line install (fully local, no API keys)

curl -fsSL https://raw.githubusercontent.com/achetronic/magec/master/scripts/install.sh | bash

Downloads a Docker Compose file with everything: LLM (Ollama), STT (Parakeet), TTS (Edge TTS), embeddings, Redis, PostgreSQL. Add --gpu for NVIDIA acceleration.

Docker with OpenAI (minimal)

docker run -d --name magec \
  -p 8080:8080 -p 8081:8081 \
  -v $(pwd)/config.yaml:/app/config.yaml \
  -v magec_data:/app/data \
  ghcr.io/achetronic/magec:latest

Create backends, agents, and clients from the Admin UI. See the Docker Quick Start guide.

Binary

Download from Releases, extract, and run:

./magec --config config.yaml

Ideal for local MCP tools (filesystem, git, shell). See the Binary Installation guide.

---

Admin UI → http://localhost:8081 · Voice UI → http://localhost:8080

Highlights

• Multi-agent: per-agent LLM, memory, voice, and tools. Hot-reload from the Admin UI.
• Agentic Flows: visual graph editor. Agents, routers, joins, loops, parallel fan-out, and code blocks (CEL and Starlark).
• Run auditing: every execution recorded and browsable as a timeline; conversations projected from the same data.
• Secrets: encrypted at rest, usable by agents and flows through placeholders the models never see resolved.
• Any backend: OpenAI, Anthropic, Gemini, Ollama, or any OpenAI-compatible API.
• MCP tools: Home Assistant, GitHub, databases, and hundreds more via Model Context Protocol.
• Memory: session (Redis) + long-term semantic (PostgreSQL/pgvector).
• Voice: wake word, VAD, STT, TTS. All server-side via ONNX Runtime. Privacy-first.
• Clients: Voice UI (PWA), Telegram, Discord, Slack, webhooks, cron, REST API.
• A2A: expose agents and flows to other agent platforms via the Agent-to-Agent protocol.

Screenshots

See all screenshots in the documentation.

Roadmap

• Multi-agent system with per-agent LLM, memory, and tools
• Visual flow editor
• MCP tool integration (HTTP + stdio transports)
• Voice UI with wake word detection and VAD
• Telegram client with voice support
• Long-term semantic memory (pgvector)
• Session memory (Redis)
• Webhook and cron clients
• Admin UI with hot-reload
• Secrets management (encrypted storage for API keys and sensitive credentials)
• Slack client
• Context window management: automatic summarization when approaching token limits (experimental)
• Expose agents and flows with A2a (Agent-to-agent) protocol
• Discord client
• Flows as real graphs (routers, joins, loops, fan-out, CEL/Starlark blocks)
• Run auditing with per-block timelines
• Secrets usable by agents and flows without exposing values to the models

Documentation

Full docs at magec.dev/docs: installation, configuration, agents, flows, backends, memory, MCP tools, clients, voice system, and API reference.

Development

Requirements

• Go 1.25+
• Node.js 22+ (for UI builds)
• Docker (for infrastructure services)

Make commands

Command	Description
make build	Build frontend UIs + embed models + compile server binary
make dev	Build all and start server
make dev-admin	Start Admin UI dev server (Vite, hot-reload)
make dev-voice	Start Voice UI dev server (Vite, hot-reload)
make swagger	Regenerate Swagger docs
make infra	Start PostgreSQL + Redis
make ollama	Start Ollama with qwen3:8b + nomic-embed-text
make docker-build	Build Docker image (current arch)
make docker-buildx	Build multi-arch image (amd64 + arm64)
make clean	Remove build artifacts

Key dependencies

Dependency	Purpose
google.golang.org/adk	Google Agent Development Kit
modelcontextprotocol/go-sdk	MCP client
yalue/onnxruntime_go	ONNX Runtime for wake word / VAD
mymmrac/telego	Telegram bot
achetronic/adk-utils-go	ADK providers, session, memory
yuin/goldmark	CommonMark + GFM parser for Telegram HTML rendering

Special Mentions

Who	What
@travisvn	Built the ARM64 Docker image for OpenAI Edge TTS in record time. This is the local TTS service we recommend: it exposes an OpenAI-compatible API (/v1/audio/speech) that uses Microsoft Edge's free neural voices under the hood, so Magec can use it as a drop-in replacement for OpenAI TTS.

Contributors

License

Apache 2.0 · Alby Hernández

---