@loomfsm/provider-ollama
v0.3.8
Published
Local-model provider for loom — runs agents through a local Ollama server, no API key.
Maintainers
Readme
@loomfsm/provider-ollama
Local-model provider for loom: runs agents through a local Ollama server — no API key, no
data leaving your machine. Bind an agent with loom models set <agent> ollama:<model>.
Installed on demand — the base @loomfsm/pipeline stays lean.
Part of loom
loom drives multi-step LLM agent work — code review, implementation, any review-gated task — as a replay-deterministic state machine: safety invariants enforced at commit time, human gates where they matter, and a complete, replayable audit trail in a local SQLite file.
Most users should install @loomfsm/pipeline
(npm i -g @loomfsm/pipeline), which pulls the whole runtime in one step. Install this
package directly only if you are assembling your own runtime.
Website · Quickstart · Why loom · GitHub
License
Apache-2.0
