InternScience/InternAgent
在全部 GitHub 仓库 中按Star排名第 531(共 803)
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
项目介绍
Rename .env.example to .env and fill in your API keys:
To use OpenRouter as the model gateway, set OPENROUTERAPIKEY and run with config/openrouterconfig.yaml. See docs/openrouter.md for setup details.
AutoDebug is a self-contained toy task (no dataset or model downloads required) and is the recommended first run to verify your setup.
QA mode uses InternAgent's deep research pipeline to answer a research question directly — no experiment loop, just a synthesized answer grounded in literature.
launch.py is a unified entry point for both modes:
Algorithm discovery tasks live under tasks/. Each contains a prompt.json (task description), baseline code/, and a launcher.sh. Datasets and…
最新指标
| Star | 1.4k | 2026-09-12 |
|---|---|---|
| Fork | 129 | 2026-09-12 |
| 提交 | 49 | 2026-09-12 |
| 发布 | 0 | 2026-09-12 |
| Watcher | 42 | 2026-09-12 |
| 开放 issue | 3 | 2026-09-12 |
| 开放 PR | 2 | 2026-09-12 |