apex

Self-hosted AI platform with multi-model chat, persistent memory,
and an extensible skills engine. One Python file. Zero data leakage.

See it in action

Every feature, transparent. Nothing hidden behind a login wall.

Multi-Model Routing

Claude for deep coding. Grok for live web research. Local models for free, private inference. Each conversation targets a specific model — run them all simultaneously.

Use your existing subscriptions. Claude Pro/Max, ChatGPT Plus/Pro — Apex connects through your existing accounts. Only Grok requires a separate API key. Local models are free.

Note: Using existing subscriptions through Apex is for personal, non-commercial use only. For commercial use, use the providers' API plans.

Persistent Memory The AI remembers your projects, decisions, and past conversations. Whisper injection silently finds and injects relevant context — no "can you remind me what we discussed?" APEX.md — project rules injected into every session MEMORY.md — accumulated knowledge across sessions Semantic search — vector embeddings with hybrid recall Session recovery — survives restarts and compaction

Extensible Skills Slash commands for search, delegation, analysis. Build custom skills with just a markdown file. /recall — search all conversation transcripts /codex — delegate tasks to a background agent /grok — live web research via xAI /evaluate — sandbox-assess any GitHub repo /first-principles — 4-layer deep analysis + Build your own — drop a SKILL.md, auto-discovered

Production Security Your AI conversations and API keys deserve production-grade protection. mTLS — client certificate auth, no passwords TLS everywhere — HTTPS with built-in cert generation Atomic writes — no partial state on crash Secrets isolation — credentials in .env only QR onboarding — scan, install cert, connect in 60s

Admin Dashboard Full web-based management at /admin — health monitoring, credential management, TLS certificates, session control, live log streaming. 61 REST endpoints usable by both humans and AI agents. Server status, uptime, model reachability Per-provider green/red health dots Database stats, TLS certificate status Edit project instructions from the browser Active sessions with token usage, force compaction Alert System Multi-channel push — in-app via WebSocket, Telegram bot, and REST API. Custom categories, severity levels (info/warning/critical), ack/unack tracking. Any script, cron job, or service can POST alerts into Apex.

Multi-Agent Orchestration

The War Room — four agents (Operations, Architect, Codex, Designer) collaborating in a single conversation. Each agent has its own model, its own persona, its own specialty. Direct them with @mentions. See cost and token usage in real time.

The sidebar tells the story: dedicated channels for Claude, Grok, Codex, a trading room, a marketing agent, local models — an entire AI organization in one interface.

Same experience on mobile. Three agents spinning simultaneously on an iPhone — native SwiftUI, not a web view.

Quick Start

From zero to running in under 2 minutes.

git clone https://github.com/use-ash/apex.git ~/.apex
cd ~/.apex
bash install.sh

The installer creates a virtual environment, installs all dependencies, generates TLS certificates, and walks you through first-time setup. When it finishes, open https://localhost:8300. Your Claude subscription is detected automatically.

# Install Ollama (https://ollama.ai)
ollama pull qwen3.5

# Start Apex — Ollama is detected automatically
python3 apex.py

Create a Claude channel for heavy tasks, an Ollama channel for quick questions.

export XAI_API_KEY=xai-...
python3 apex.py

export APEX_ENABLE_WHISPER=1
export XAI_API_KEY=xai-...
export GOOGLE_API_KEY=AIza...
APEX_SSL_CERT=cert.pem APEX_SSL_KEY=key.pem APEX_SSL_CA=ca.pem python3 apex.py

All models active. Memory with semantic search. Whisper injection. mTLS auth.

What 30 minutes looks like

Fresh install. Three AI providers — Claude, Grok, and ChatGPT — collaborating in a group chat, @mentioning each other, completing a task loop. Guided onboarding channel visible in the sidebar. This is what you get in half an hour.

Free & Premium

The Apex server and web app are free and open source. Run it on your machine, use it in your browser — no limits, no costs beyond your own AI subscriptions.

Native apps for iOS, Android, and Desktop are premium — they provide the secure remote access layer that turns your self-hosted server into a mobile-ready AI platform.

Why native apps?

The web app works great on localhost. But when you want to reach your server from your phone on the train, from your laptop at a coffee shop, or from your iPad on the couch — you need:

• Certificate-pinned mTLS — your phone authenticates to your server with a client certificate, not a password
• Push notifications — real-time alerts from your AI, your cron jobs, your monitoring
• Background survival — the connection stays alive when you switch apps
• Gesture navigation — swipe between channels, long-press for actions, native scroll physics

That's the difference between a browser tab and a real app. The native experience is the premium.

Platform Availability

Architecture

server/
├── apex.py                  ← entry point, startup, router registration
├── ws_handler.py            ← WebSocket connections, streaming, session mgmt
├── agent_sdk.py             ← Claude SDK integration, auth, turn execution
├── backends.py              ← Codex, Grok, Ollama/MLX dispatch
├── model_dispatch.py        ← model routing and provider selection
├── routes_chat.py           ← chat REST endpoints
├── routes_alerts.py         ← alert ingestion, APNs push
├── routes_profiles.py       ← persona management
├── routes_models.py         ← model listing and config
├── routes_setup.py          ← guided onboarding wizard
├── routes_misc.py           ← models, usage, license, misc endpoints
├── db.py                    ← SQLite schema, all database helpers
├── state.py                 ← shared in-memory state, accessor functions
├── streaming.py             ← broadcast helpers, WS send utilities
├── config.py                ← constants, version, build metadata
├── env.py                   ← all os.environ reads (single source of truth)
├── mtls.py                  ← TLS + mTLS certificate handling
├── context.py               ← conversation context assembly
├── memory_extract.py        ← memory tag extraction and persistence
├── memory_search.py         ← semantic search and recall
├── skills.py                ← skill discovery and dispatch
├── tasks.py                 ← background task management
├── license.py               ← license validation and trial gating
├── chat_html.py             ← embedded web UI (chat SPA)
├── dashboard.py             ← admin dashboard backend
├── dashboard_html.py        ← admin dashboard UI
├── setup_html.py            ← onboarding wizard UI
├── alert_client.py          ← Telegram + push notification delivery
└── log.py                   ← logging

35 modules. No frameworks. No npm. No build step. The frontend is embedded in the Python server — python3 apex.py and everything runs.

Skills are directories with a SKILL.md file. Drop one in skills/, restart, and it's live.

skills/my-skill/
├── SKILL.md          # Metadata + instructions (required)
├── run.sh            # Executable entry point (optional)
├── feedback.log      # User corrections (auto-generated)
└── metrics.json      # Usage tracking (auto-generated)

Two types:

1. Executable skills — have a run.sh. Server executes it, passes results to the AI.
2. Thinking skills — no script. The AI reads instructions and follows them.

Risk tiers control execution:

Self-improving: /improve reads a skill's metrics and feedback, then proposes concrete changes.

• Python 3.10+
• At least one model provider:
  • Claude subscription (Pro/Max/Code), or
  • ChatGPT subscription (Plus/Pro), or
  • Ollama or MLX for free local inference, or
  • xAI API key for Grok
• Mix and match per conversation.

Optional:

• Google API key for semantic search embeddings (free tier sufficient)
• Telegram bot token for mobile alert delivery

FAQ

Getting Started · Personas · Groups · Contributing · Changelog · License

_{Elastic License 2.0 — free to use, modify, and self-host. Cannot be offered as a hosted service.}