Same code on your GPU, on Ollama, or on cloud APIs. Effort-based model routing, persistent memory and multi-agent coordination — without the lock-in.
pip install aither-adk adk quickstart # detects hardware, pulls models, configures backends adk init my-agent && cd my-agent && python agent.py
Most agent frameworks bind you to one provider. This one treats the backend as configuration.
Declare how hard a task is; the selector picks a model to match. Trivial work does not pay for a frontier model.
vLLM, Ollama and cloud APIs behind one interface. Change the backend without touching agent code.
Agents keep durable, queryable memory across runs rather than restarting cold every session.
Compose agents into fleets with shared context, so work can be decomposed and run in parallel.
Bundle tools, prompts and identity into a pack — a reusable unit an agent can be given wholesale.
No GPU? Set an API key. Have one? It auto-detects. Both? It routes by task complexity.
Install, set up inference, and run your first agent. The bootstrap installer handles Python for you if you would rather not manage it.
# with Python already available pip install aither-adk adk quickstart adk quickstart --cloud adk start # no Python? one line (macOS / Linux) curl -fsSL https://aitherium.com/install.sh | sh # Windows powershell -ExecutionPolicy ByPass -c "irm https://aitherium.com/install.ps1 | iex"