macrokit/core
Run weak/local LLMs on narrow workflows reliably: encode a workflow once at design time as a deterministic macro, then a small local model just routes to it at runtime. TypeScript SDK, Apache-2.0, BYO-model (OpenAI-compatible + Ollama).
GitHub repository with 5 stars and 2 forks.
Language: TypeScript
Topics: ai-agents, llm, llm-tools, local-llm, ollama, on-device-ai, typescript