The Premise

The agent ecosystem is converging on orchestration — chains, tools, prompts. These are solved problems. The unsolved problems are persistence (agents that survive across sessions and substrate changes), communication (agents that operate across multiple platforms simultaneously), and coordination (agents that form networks and share knowledge).

Animus is built on the conviction that agents need their own infrastructure — not borrowed from human-facing SaaS, not dependent on a single cloud provider, not limited to one communication channel. An agent framework should be as infrastructure-grade as the database or message queue it sits next to.

The C++ kernel, the embedded admin UI, the channel architecture — these aren't technical choices for their own sake. They're decisions about what the product is: a deployable, self-contained runtime that works the same way on a Raspberry Pi behind a NAT as it does on a cloud VPS.

Development Trajectory

Three phases. Each phase is a complete, usable product. Each enables the next.

Shipped
Phase 1

Agent Runtime

A complete, self-contained agent runtime with memory, tools, identity, and admin UI. Deploy anywhere.

Multi-layer memory + consolidation pipeline
Lua scripting runtime + tool bridge
Multi-provider LLM (6 providers)
Embedded admin UI (Vue 3 + Vuetify)
Multi-tenant agent management
In Progress
Phase 2

Communication Layer

Unified channel architecture connecting agents to the platforms where people actually are.

IRC, Telegram, VK, Bluesky, Mastodon — live
Unified ChannelManager + REST API
Per-channel agent binding + session routing
Email (AgentMail) — in development
Slack, Discord, Signal — connector interface
Planned
Phase 3

Network & Ecosystem

Multi-agent coordination, cross-network relay, and shared knowledge infrastructure.

Mesh networking + state sync
Cloud relay (encrypted backup + NAT traversal)
Community hub (SOPs, scripts, showcase)
Self-replication to viable hosts
Domain tool modules (accounting, automation)

Strategic Capabilities

What the architecture is designed to enable. Not all shipped yet — but the foundation is in place.

🔗

Mesh Networking

Multi-agent coordination with CRDT-lite state synchronization. Agents form meshes, share knowledge, and coordinate on complex tasks. Works across NAT boundaries via cloud relay.

Foundation ready
Relay service
🔐

Privacy-First Architecture

AES-256-GCM diary encryption. Client-side encryption for cloud sync. No mandatory cloud dependency. Local-first by design — every feature works offline.

Diary encryption
Sync encryption
🏗️

Extensible via Lua

Custom tools written in Lua, registered at runtime. No kernel recompilation. The scripting runtime is sandboxed with budget limits — safe for production deployment.

Lua 5.4 runtime
Network access
📊

Provider Independence

Agent identity is separate from the model substrate. Switch providers without changing agent logic. Six providers supported today; any OpenAI-compatible endpoint works.

6 providers
Local models (Ollama)

Commercial Path

Open-source core. Sustainable revenue from infrastructure, not gatekeeping.

Always Free

Full agent framework. All channels. All memory features. Lua scripting. Admin UI. Self-hosted, no cloud dependency, no feature gates.

Cloud Sync Relay

Encrypted backup and cross-network relay. Agents behind NAT reach each other. Client-side encryption — the relay never sees plaintext. Disaster recovery for agent state.

Community Hub

Shared SOPs, script exchange, agent showcase. Browsable repository of proven agent patterns. Import directly into your Animus config.

Interested in the trajectory?

Animus is in active development with production deployments. If this direction aligns with what you're building, let's talk.