# Research Flywheel

> Local-first research flywheel for papers, code, experiments, memory, and multi-model councils.

- **Type:** MCP server
- **Install:** `agentstack add mcp-lidapengpeng-research-flywheel`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [lidapengpeng](https://agentstack.voostack.com/s/lidapengpeng)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [lidapengpeng](https://github.com/lidapengpeng)
- **Source:** https://github.com/lidapengpeng/research-flywheel

## Install

```sh
agentstack add mcp-lidapengpeng-research-flywheel
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Research Flywheel

Research Flywheel 是一个 local-first 的个人科研知识库飞轮。它面向长期研究者，把本地论文、PPT、笔记、每日新文献、聊天反馈和多模型审议持续炼化成可查询、可反馈、可晋升的长期科研记忆。

它不是代码 agent、训练日志分析器，也不是自动写论文机器。默认目标是先培养一个懂你领域、能引用证据、能接受反馈、能逐步形成判断力的个人科研知识系统。

```text
论文/PPT/笔记/每日新文献
  -> paper cards / claim candidates
  -> claim ledger / self-test
  -> evidence-first 知识库对话
  -> Codex / Claude / Gemini 独立思考
  -> discuss + verdict
  -> 用户反馈
  -> reflect 晋升/降级
  -> semantic / procedural / expert profile memory
```

## Quick Start

For AI agents opening this repository, start with [AGENTS.md](AGENTS.md). The detailed shared protocol is in [docs/agent-operating-protocol.md](docs/agent-operating-protocol.md). [CLAUDE.md](CLAUDE.md) and [GEMINI.md](GEMINI.md) are role overlays, not separate sources of truth; they should be read after the shared context. For a full external review brief, read [docs/claude-review-brief.md](docs/claude-review-brief.md). Repository changes should follow the change-impact protocol so code, docs, tests, and examples stay synchronized.

```bash
python3 -m pip install -e ".[pdf,yaml]"
rf init ./research-workspace
rf doctor --workspace ./research-workspace
rf ingest papers ./research-workspace/inbox/papers --workspace ./research-workspace
rf discover papers --candidate-pool 100 --limit 10 --workspace ./research-workspace
rf memory rebuild-index --workspace ./research-workspace
rf memory search "orthophoto building segmentation" --workspace ./research-workspace
rf claim add "Multimodal fusion may improve building separation under cross-scene shift." --evidence wiki/papers/example.md --confidence hypothesis --tags multimodal,segmentation --workspace ./research-workspace
rf claim list --status hypothesis --workspace ./research-workspace
rf daily --workspace ./research-workspace
rf ask "哪些论文思想值得迁移到我的 building segmentation pipeline?" --workspace ./research-workspace
rf council ask "这个方向是否值得深读？" --workspace ./research-workspace
rf self-test generate --topic building-instance-segmentation --workspace ./research-workspace
rf self-test answer --latest --workspace ./research-workspace
rf self-test grade --latest --workspace ./research-workspace
rf feedback add "这个 idea 值得继续观察" --target idea --workspace ./research-workspace
rf reflect --workspace ./research-workspace
rf memory inspect-claim-graph --workspace ./research-workspace
rf sync notion --workspace ./research-workspace
```

如果不想安装，也可以直接运行：

```bash
python3 -m rf.cli init ./research-workspace
```

## Core Ideas

- Markdown 是权威知识底座，SQLite 保存元数据、反馈和问题历史。
- `rf memory rebuild-index/search` 使用 SQLite FTS5/BM25 做本地全文检索；索引是派生层，不是权威记忆。
- `rf discover papers` 是每日进料口：先检索并评分约 100 篇候选，再按 8 维相关度筛出 Top 10，分类保存 PDF/metadata 并入库。
- `claim ledger` 是判断层：每条重要结论必须有 evidence、confidence、status 和 user verdict。
- `self-test` 是专家考核层：定期暴露薄弱点，写入 `memory/expert_profile/weak_spots.md`。
- Obsidian 可以直接打开 `wiki/` 和 `memory/`。
- Notion 是可选 dashboard，不是唯一真相来源。
- `rf ask` 先构造 evidence pack，再回答问题。
- `rf council ask` 让 Codex、Claude、Gemini 独立思考后再综合裁决。
- `rf reflect` 只晋升 supported claims、用户认可反馈和重复出现的问题；被否定内容会进入 expert profile。
- Hermes Agent、MCP、模型 API 都是可选外壳；Research Flywheel 保持独立。

## Workspace Layout

`rf init` 会生成：

```text
research-workspace/
  research-flywheel.yaml
  RESEARCH_BRIEF.md
  inbox/
    papers/
    notes/
    presentations/
  raw/
  wiki/
    papers/
    claims/
    concepts/
    questions/
    reading/
    ideas/
    writing/
    council/
    daily/
  memory/
    working/
    episodic/
    semantic/
    procedural/
    feedback/
    expert_profile/
  exports/
```

详见 [docs/architecture.md](docs/architecture.md) 和 [docs/configuration.md](docs/configuration.md)。

## MVP Status

当前实现覆盖：

- `rf init`
- `rf doctor`
- `rf ingest papers`
- `rf discover papers`
- `rf claim add/list/review`
- `rf daily`
- `rf ask`
- `rf council ask`
- `rf self-test generate/answer/grade`
- `rf feedback add`
- `rf reflect`
- `rf memory rebuild-index/search/inspect-claim-graph`
- `rf sync notion`
- `rf mcp serve`

Graphiti 关系图适配器、真实 Notion 写入、向量索引和 Hermes skill 集成保留为可扩展接口。MVP 默认离线可用。

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [lidapengpeng](https://github.com/lidapengpeng)
- **Source:** [lidapengpeng/research-flywheel](https://github.com/lidapengpeng/research-flywheel)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-lidapengpeng-research-flywheel
- Seller: https://agentstack.voostack.com/s/lidapengpeng
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.