mcp server

A.L.I.C.E

Alice Framework Agi — Autonomous AI agent framework. 279 x402 tools, 611 norms, 517 protocols. USDC on Base

VZero911/A.L.I.C.Ecommunitylistedunreviewed

Use tool

Set up

Runs on your computer. Pick your agent and operating system.

This project does not publish an install method we can turn into a config. Follow the README instead.

README

synced Oct 21, 2026

Dashboard

What is A.L.I.C.E?

An AI agent framework designed for full sovereignty — no cloud APIs, no external dependencies, no data leaving your machine.

ALICE monitors, automates, defends and coordinates everything on a single machine. She talks to her own local LLM (Ollama), syncs with THESEED L0 blockchain, self-heals on disconnect, and exposes a full HTTP API for queries and tasks.

Core capabilities

Local LLM — Ollama-powered, model loaded in VRAM, zero API keys needed
Chain sync — continuous background sync with L0 blockchain (chain 0)
Self-healing — auto-recovery from disconnects, crashes, service failures
106-panel dashboard — React TSX, live metrics via WebSocket, 3 screens
Defense engine — CYBER ENGINE, firewall, ghost mode, fortress lockdown
MCP server — 36 tools for Claude Code / Cursor with USDC micropayments
Agent fleet — master/general coordination, task delegation, swarm
ChibiAlice — animated desktop companion (Electron overlay)

Metrics

Metric	Value
Framework	Alice Framework Agi V0
Dashboard	106 React TSX panels across 3 screens
AI modules	36 active (chain sync, defense, monitoring, trading, ...)
MCP server	36 tools for Claude Code / Cursor
Docker	7 containers (ALICE-MASTER, ALICE-GENERAL, ALICE-CORE, Ollama, geth, PostgreSQL, TOA)
Tools	235 automation scripts
Lines of code	132K
Unit tests	34 test files (ALICE core)

Architecture

                         ┌─────────────────────┐
                         │     ALICE-CORE       │
                         │  Local LLM (30.5B)   │
                         │  Ollama · VRAM       │
                         └──────────┬──────────┘
                                    │
              ┌─────────────────────┼─────────────────────┐
              │                     │                     │
    ┌─────────▼─────────┐ ┌────────▼────────┐ ┌─────────▼─────────┐
    │   ALICE-MASTER    │ │  ALICE-GENERAL  │ │  CYBER ENGINE     │
    │   Coordination    │ │  Task Worker    │ │  Defense Engine   │
    │   Delegation      │ │  Chain Sync     │ │  Firewall · Ghost │
    └─────────┬─────────┘ └────────┬────────┘ └─────────┬─────────┘
              │                     │                     │
              └─────────────────────┼─────────────────────┘
                                    │
                    ┌───────────────┼───────────────┐
                    │               │               │
          ┌────────▼───────┐ ┌─────▼─────┐ ┌──────▼──────┐
          │  THESEED L0    │ │ Dashboard │ │  MCP Server │
          │  chain 0   │ │ 106 panels│ │  36 tools   │
          │  geth PoA      │ │ React TSX │ │  USDC/Base  │
          └────────────────┘ └───────────┘ └─────────────┘

Quick Start

docker compose -f docker/docker-compose.public-node.yml up -d

Starts 3 services automatically:

Service	Description
Ollama	Local LLM (auto-pulls model on first run)
THESEED geth	L0 blockchain (chain 0, gasless)
ALICE Node	Autonomous agent with LLM + chain sync

API

Endpoint	Method	Description
`/health`	GET	Health check
`/status`	GET	Full node status (agent + chain + LLM)
`/api/chain`	GET	Chain info (block number, sync status)
`/api/query`	POST	Query the agent (LLM-powered)
`/api/task`	POST	Send task for execution
`/api/node`	GET	Node identity and role
`/api/logs`	GET	Activity logs
`/api/llm`	GET	LLM status (model, availability)

GPU Support

To enable GPU acceleration for Ollama:

# AMD (ROCm)
ollama:
  image: ollama/ollama:0.3.12-rocm
  devices:
    - /dev/kfd
    - /dev/dri

# NVIDIA
ollama:
  deploy:
    resources:
      reservations:
        devices:
          - capabilities: [gpu]