AutoResearch (Orchestra)
13,149 starsOrchestrates end-to-end autonomous AI research projects with a two-loop architecture: an inner loop of rapid experiment iterations with clear optimization targets, an outer loop that synthesizes results and steers direction, routing to domain-specific skills; part of a 98-skill AI research library (model architectures, tokenization, fine-tuning, interpretability, data processing).
- First published：2025-11-03
- data as of：
- 2026-09-30
- Licence：
- MIT
When to use it
For automated ML research loops: experiment, analyze, redirect.
Caution
Autonomous research means high token and compute cost; needs an experiment environment; results require human review (automated synthesis can amplify errors). The repo has not been updated since 2026-06.
Install prompt
請幫我安裝「AutoResearch (Orchestra)」技能：從 https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/0-autoresearch-skill（技能路徑：0-autoresearch-skill/） 取得完整的技能目錄，放進我的 Agent 的技能目錄（例如專案內的 skills/ 資料夾，或該 Agent 文件指明的全域技能位置），確認裡面的 SKILL.md 存在、frontmatter 的 name 與 description 完整，然後列出這個技能宣告的腳本、外部工具與 API 需求，先不要執行任何腳本。Paste this to your agent. It deliberately contains no tool subcommands — check the tool's official docs for commands.