research-workbench

Open-Source AI research workbench with scientific agents for reproducible research and discovery.

Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.

本地优先的个人 A 股研究决策工作台 · 案卷式研究闭环：进口判断→证伪→复盘→记忆。人做决策，AI 做广度/证伪/风险。A local-first personal A-share research OS.

Local-first AI research workbench for quant. Turn a natural-language strategy idea into a reproducible, auditable backtest — factor code, Reviewer checks, charts, and research notes, all saved locally.面向本地的量化AI研究工作台。将自然语言策略想法转化为可复现、可审计的回测结果——因子代码、审核员检查、图表和研究笔记，全部保存于本地。

AI-assisted 13-stage academic research workbench for Codex: 40 bundled skills, research ledger, novelty audit, three-round review, de-AI polish, publication-grade figures.

Messy long context -> structured insight -> auditable markdown, research threads, and inspectable outcomes.

Local-first asset-pricing and macro mispricing research system with alternative-data pipelines and research workflow orchestration.

FerrAI–Terra'Nova CIC Framework — System Architecture, State Logic and Governance Boundaries · v16 · DOI: 10.5281/zenodo.20732376

Public sanitized release of my read-only crypto research workbench: frontend shell, Python JSON API, synthetic fixtures, tests, CI, and bilingual docs.

Pure-static, local-first research workbench: literature library, calendar, submission tracking, AI assistant, API quota monitoring. Zero dependencies.

[INACTIVE - superseded by Political Pathology Workbench] Reproducible corpus workbench for Koenigsberg's Law of Sacrifice via CMT and LCC-style metaphor analysis. Preserved as source history and audit provenance. New work at https://github.com/ashitaka-emishi/political-pathology-workbench

证据优先的半导体产业研究工作台：历史盲测、反证审计与人工发布门禁

Local-first, auditable PubMed research workbench with explicit human review gates