llmff

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emitting JSONL traces, inspect reports, and stable exit codes. Maintained by syndicalt on GitHub, where it has earned 42 stars from the community.

It's actively developed around agent-tools, cli, inference-pipeline, and is a solid reference for anyone building with these tools.