# File System-First Agentic Research Framework: Enabling AI Agents to Have Persistent Research Memory

> This article introduces an innovative AI-assisted research workflow framework that solves common issues in AI research such as context loss and difficulty in source tracing by persisting research states to the file system instead of relying on conversation context.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-05-26T03:16:04.000Z
- 最近活动: 2026-05-26T03:26:06.476Z
- 热度: 159.8
- 关键词: Agentic研究, AI辅助研究, 文件系统工作流, 研究方法论, 来源管理, 知识管理, AI代理, 研究框架
- 页面链接: https://www.zingnex.cn/en/forum/thread/agentic-ai-557037ac
- Canonical: https://www.zingnex.cn/forum/thread/agentic-ai-557037ac
- Markdown 来源: floors_fallback

---

## Introduction to the File System-First Agentic Research Framework

This introduces the Agentic Research Harness framework, whose core is to persist research states to the file system instead of relying on conversation context, solving issues like context loss and difficulty in source tracing in AI research. The framework emphasizes "one folder per problem, goals first, separation of sources and synthesis, and binding claims to evidence", ensuring the persistence, auditability, and collaboration of research through structured file storage.

## Pain Points of AI-Assisted Research and Framework Background

With the development of large language models, AI-assisted research has become popular, but traditional workflows use chat conversations as the workspace, leading to the loss of context, discoveries, and conclusions after conversations end. The Agentic Research Harness framework proposes a solution that uses the file system as the workspace, chat as a temporary container, and persists research results in structured files.

## Core Design Philosophy of the Framework

### File System as Workspace
Each research problem corresponds to an independent folder, storing structured files such as goals, sources, and claims. Its advantages include persistence, auditability, collaboration, and recoverability.
### Source Quality Grading System
Establish a three-level source standard (A/B/C): Level A is original sources (highest credibility), Level B is strong secondary sources (aiding understanding), Level C is discoveries/noise (only guiding discoveries). Clear rules include: Level C cannot support final claims, and important claims must trace back to original sources.

## Project File Structure and Collaboration Process

#### Auto-Generated File Structure
research/my-research-topic/ contains files like GOAL.md (research goals), STATE.md (current state), SOURCES.md (source index), claims.md (claims and evidence), as well as directories like sources/ and notes/.
#### Collaboration Process with AI Agents
1. Read GOAL.md and STATE.md
2. Use references from SOURCES.md and claims.md
3. Decompose search sub-problems
4. Prioritize original sources
5. Save source texts
6. Update SOURCES.md and claims.md
7. Write synthesis content
8. Update STATE.md

## Tool Agnosticism and Privacy/Security Considerations

#### Tool Agnosticism
Not tied to specific AI tools or search engines; can be used with Hermes Agent, Claude Code, OpenAI Codex CLI, etc., reflecting the lasting value of the research method.
#### Privacy and Security
The research/ directory is excluded from gitignore by default to avoid accidental publication of real research folders, protecting source confidentiality and data security.

## Comparison with Traditional AI Research Models

| Dimension | Traditional AI Chat Mode | Agentic Research Harness |
|-----|--------------|-------------------------|
| Persistence | Lost after conversation ends | Files saved permanently |
| Traceability | Difficult to trace claim sources | Each claim is bound to evidence |
| Collaboration | Hard to share research state | Folders can be shared directly |
| Tool Dependency | Tied to specific AI platforms | Tool agnostic |
| Quality Control | Relies on AI self-restraint | Structured quality grading |
| Context Management | Limited by context window | File system has no limits |

## Framework Value and Conclusion

Agentic Research Harness represents a reflection on AI-assisted research, emphasizing that AI is a tool and chat is a means; the core value is verified knowledge and a clear thinking process. By persisting research states through the file system, the framework cultivates rigorous, transparent, and sustainable research habits, which are particularly important in the era of information explosion and AI hallucinations.

## Recommended Research Workflow

1. Create a research project
2. Fill in GOAL.md
3. Launch the AI agent from the project folder
4. Ask the agent to develop a small research plan
5. Search and save sources
6. Update SOURCES.md
7. Convert discoveries into claims.md entries
8. Write synthesis content to notes/ or outputs/
9. Update STATE.md
10. Start a new conversation when context is too large (no need to worry about loss as state is saved in files)