Roadmap & Vision
Where Animus is heading. The current product is the foundation — here's what it enables.
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.
Agent Runtime
A complete, self-contained agent runtime with memory, tools, identity, admin UI, and Docker deployment.
Communication Layer
Unified channel architecture connecting agents to the platforms where people actually are.
Network & Ecosystem
Expanding the node architecture toward multi-agent coordination and specialized tooling.
Strategic Capabilities
What the architecture is designed to enable. Not all shipped yet — but the foundation is in place.
Node Architecture
Delegate work to remote nodes via SSH or WebSocket. Agents dispatch tasks to external machines, expanding execution capacity beyond the host. Per-node tool registration and auto-reconnection.
Privacy-First Architecture
AES-256-GCM diary encryption. No mandatory cloud dependency. Local-first by design — every feature works offline.
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.
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.
Interested in the trajectory?
Animus is in active development with production deployments. If this direction aligns with what you're building, let's talk.