Open-source project, GitHub, github.com/Fzkuji/OpenProgram
Agentic Programming framework: Python drives the deterministic control flow, the LLM reasons only when asked. Automatic context threading over a DAG, terminal + web UIs with live execution visualization, self-evolving workflows, and any LLM provider (Claude / GPT / Gemini). Runs natively on macOS, Linux, and Windows.
Open-source project (built on OpenProgram), GitHub, github.com/Fzkuji/OpenProgram
Ingests notes / docs / chats into an Obsidian-compatible vault with [[wikilinks]]. Track record: Obsidian vault output.
Open-source project (built on OpenProgram), GitHub, github.com/Fzkuji/OpenProgram
Literature survey → idea → experiments → paper draft → cross-model review. Track record: turns a topic into a submission-ready draft.
Open-source project (built on OpenProgram), GitHub, github.com/Fzkuji/OpenProgram
Observe → plan → click → verify by vision; drives desktop apps and OSWorld VMs. Runs on macOS / Windows / Linux (perception macOS-tuned). Track record: 79.8% on OSWorld Multi-Apps (72.6 / 91).
Open-source project (code for Tandem, ACL 2026 Findings), GitHub, github.com/Fzkuji/Ensemble-Hub
Reference implementation of Tandem (ACL 2026 Findings): a mentor–intern framework where an LLM emits compact GPRA reasoning insights to guide an efficient SLM, with cost-aware termination and progressive effort levels. ~40% cost reduction; +2.56% accuracy over a standalone 32B LLM at 59% of its compute on MATH.