Psyllama documentation

Psyllama helps you run large language models locally with a simple CLI and an OpenAI-compatible API.

Quickstart

Install Psyllama and run your first model.

curl -fsSL https://psyllama.com/install.sh | sh
psyllama run kimi-k2.5:cloud

Go to quickstart →

API reference

Use the local HTTP API to build apps and integrations.

curl http://localhost:11434/api/chat \
  -d '{"model":"kimi-k2.5:cloud","messages":[{"role":"user","content":"Hello!"}]}'

Go to API introduction →

Libraries

Use any HTTP client. Official language SDKs can be added later.

Community