syndicalt/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.

3 best points · 0 comments · 2 Hacker News posts · 46 GitHub stars · View on GitHub

Hacker News discussions

• Llmff v0.1.2: FFmpeg-Shaped Pipelines for LLM Workflows (3 points, 0 comments, by syndicalt, 2026-05-22)
• Show HN: Llmff v1.0 FFmpeg for Inference (3 points, 0 comments, by syndicalt, 2026-05-31)