AI 어시스턴트가 읽고 쓸 수 있도록 프로젝트 계획, 결정 사항, 결과 및 교훈을 로컬 SQLite 데이터베이스에 기록합니다.
다른 이름 Dankaro-projects/project-memory, project-memory, project-memory-mcp
- 스타
- 0
- Tools
- —
- 다운로드, 30일
- 328
- 최신 버전
- 0.5.0b9
- 마지막 커밋
- 2026년 10월 8일
- 라이선스
- MIT
Project Memory MCP란?
AI 어시스턴트가 읽고 쓸 수 있도록 프로젝트 계획, 결정 사항, 결과 및 교훈을 로컬 SQLite 데이터베이스에 기록합니다.
프로젝트 README에서 생성된 요약
Project Memory MCP server 정보
Project Memory는 소프트웨어 제품, 컨설팅 업무 또는 n8n 워크플로우 자동화의 라이프사이클을 추적하기 위한 로컬 SQLite 데이터베이스를 제공합니다. AI 어시스턴트가 프로젝트 계획, 결정, 결과 및 학습된 교훈에 관한 기록을 읽고 쓸 수 있도록 지원합니다. 개발자는 세 가지 특정 MCP 도구를 통해 작업의 연속적인 히스토리를 유지하며, 이를 통해 서로 다른 채팅 세션 간에도 컨텍스트가 보존되도록 합니다.
이 시스템은 Python 3.11 이상 환경에서 로컬 사용을 위해 설계되었습니다. Claude Code 또는 Codex와 같은 기존 CLI 도구와 통합되어 위임된 작업 및 에이전트 체크를 관리하며, 사용자의 기존 계정과 사용 제한을 그대로 활용합니다. 사용자는 아키텍처, 의존성, 결정 이력(decision lineage) 뷰를 제공하는 Notion 워크스페이스 방식의 읽기 전용 로컬 제어 패널을 통해 진행 상황을 모니터링할 수 있습니다.
설정은 uv를 통해 이루어지며, 사용자는 product, engagement, automation과 같은 특정 템플릿을 사용하여 프로젝트를 초기화할 수 있습니다. 이를 통해 시작 문서와 프로젝트 단계가 처음부터 자동으로 구조화됩니다. 서버는 텔레메트리나 호스팅된 데이터베이스 없이 작동하므로 모든 프로젝트 데이터는 로컬 머신에 안전하게 보관됩니다.
활용 사례
- 1결정 이력 유지AI 어시스턴트가 프로젝트 진행 중 내려진 모든 결정 사항을 근거 및 예상 결과와 함께 기록할 수 있습니다.
- 2프로젝트 제약 조건 강제사용자는 학습된 교훈을 기반으로 가드레일을 설정하여 어시스턴트가 특정 실수를 반복하지 않도록 방지할 수 있습니다.
- 3Obsidian으로 히스토리 내보내기개발자는 프로젝트 데이터베이스를 Markdown 노트 모음으로 변환하여 Obsidian vault에서 사용할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
Project Memory MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 Project Memory MCP 설치
$ claude mcp add project-memory -- uvx project-memory-mcpCursor에 Project Memory MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"project-memory": {
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}VS Code에 Project Memory MCP 설치
.vscode/mcp.json
{
"servers": {
"project-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}VS Code CLI에 Project Memory MCP 설치
$ code --add-mcp '{"name":"project-memory","type":"stdio","command":"uvx","args":["project-memory-mcp"]}'Claude Desktop에 Project Memory MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"project-memory": {
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}Codex에 Project Memory MCP 설치
$ codex mcp add project-memory -- uvx project-memory-mcpCodex config.toml에 Project Memory MCP 설치
~/.codex/config.toml
[mcp_servers.project-memory] command = "uvx" args = ["project-memory-mcp"]
Gemini CLI에 Project Memory MCP 설치
$ gemini mcp add -s user project-memory uvx -- project-memory-mcpGemini settings.json에 Project Memory MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"project-memory": {
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}자동 검사
2026년 11월 15일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 이는 보안 감사가 아닙니다. 코드를 직접 읽고 서버에 필요한 최소한의 권한만 부여하십시오. 검사 방식
- 소스 저장소 연결 및 접근 가능dankaro-projects/project-memory is public and reachablegithub.com/dankaro-projects/project-memory ↗통과
- 패키지가 이 저장소를 소스로 명시project-memory-mcp names dankaro-projects/project-memory as sourcepypi.org/project/project-memory-mcp/ ↗통과
- 빌드 출처(Sigstore 증명)Sigstore attestation for project-memory-mcppypi.org/project/project-memory-mcp/ ↗통과
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-10-08github.com/dankaro-projects/project-memory ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음No popular package one edit away from project-memory-mcp통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음1 resolved dependencies checked; no critical advisoryosv.dev ↗통과
- 모델에 대한 숨겨진 지침 없음0 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기Project Memory
Project Memory keeps the plan, the evidence, the decisions, the outcomes and the accepted lessons of one project in a local SQLite database. Your assistant reads and writes those records through three MCP tools. You follow the same records in a local control panel, which is read only, and you decide in the chat what is approved, accepted and merged.
It works for a software product, a consulting engagement and a workflow automation built in n8n. Work items can be code, documents, deliverables or exported workflows.
Public beta. Python 3.11 or newer is required. The runtime uses only the Python standard library. There is no telemetry, no hosted database and no account. Agent checks and delegated work run through the Codex or Claude Code CLI that you already have installed, and they consume that account's usage.
Install
Install uv, then run this inside the project you want to remember:
uvx project-memory-mcp@0.6.0b16 setup --client codex --trust
For Claude Code, replace --client codex with --client claude. Setup preserves existing records and settings, connects the MCP server and the lifecycle hooks, and opens the control panel. --trust approves the project integration in that client; omit it to approve the connection yourself. Start a new assistant session afterwards. Add --no-view for a headless installation.
For a permanent command:
uv tool install project-memory-mcp==0.6.0b16
project-memory doctor
project-memory view
To install the published wheel directly from GitHub instead of PyPI:
uvx --from https://github.com/Dankaro-projects/project-memory/releases/download/v0.6.0b16/project_memory_mcp-0.6.0b16-py3-none-any.whl project-memory setup --client claude --trust
Other local MCP clients use setup --client mcp and the stdio server. Setup and lifecycle covers client configuration, the plugins, upgrades, backups and removal.
Start a project
A new project starts from one of three templates:
project-memory init ~/projects/pricing-tool --template product --client codex
| Template | For | Starter documents | Phases |
|---|---|---|---|
product |
A software product | docs/brief.md, docs/research.md, docs/architecture.md, docs/stories.md |
Goals and brief, Research, Requirements approval, Architecture, User stories and acceptance, Build, Review and release |
engagement |
A consulting engagement | engagement/brief.md, engagement/stakeholders.md, engagement/research.md, engagement/findings.md, deliverables/README.md |
Scope and brief, Stakeholders and hypotheses, Research and evidence, Analysis and synthesis, Recommendations and deliverables, Client review, Handover |
automation |
A workflow automation, with n8n exports in workflows/ |
automation/process.md, automation/systems.md, automation/solution-design.md, workflows/README.md |
Process discovery, Systems and credentials inventory, Solution design, Workflow stories and test data, Build workflows, Test with sample data, Deployment and handover |
init creates the folder, initialises git unless you pass --no-git, writes any starter document that does not exist yet, connects the clients you name and records each phase as a work item. Running it again creates nothing a second time and never overwrites a document you have edited.
The kickoff conversation
Each template carries seven kickoff questions. Your assistant reads them with memory_get kickoff and asks you, for example what problem the product solves, who the stakeholders are, or which systems the process uses. It records your answers with memory_write answer_kickoff, fills the starter documents from those answers and proposes requirements. Only you approve the requirements baseline. Until that approval exists, the control panel opens on a kickoff checklist that shows the open questions, the research still needed, the starter documents that are still empty and the phases.
The everyday loop
Tell the assistant the result you want, the constraints and what would count as complete. It then records a work item with its objective, its completion criterion, the next action and the files it may change, continues from that record in later sessions, and records each decision with its evidence, alternatives, uncertainty and expected consequence. After acting, it records what actually happened. A failure stays visible after a later success.
You approve requirements, accept or reject proposed lessons, widen the allowed paths, and decide what is merged. Capturing a document does not approve its contents, and a plan does not authorise work.
The control panel
Run project-memory view in the project, or ask the assistant to open Project Memory. The panel reads the same database and refreshes while it is open. It is laid out as a Notion workspace: a sidebar of views, database tables with views, filters, sorting and grouping, and each item opening as a page beside the list, in a light or a dark theme.
| View | Content |
|---|---|
| Now | One sentence on the project position, the kickoff checklist, and the work in progress, paused, ready and done with the next step of each, and recent decisions |
| Plan | The hierarchy of phases, epics, stories, research items, deliverables and workflows as an outline with nested sub-items and progress, and a gallery of the phases |
| Work | A table and a board of work items, and a page for each with the plan, the allowed paths, dependencies, agent runs, lineage and history |
| Architecture | Components from source code, exported n8n workflows and authored items such as systems, stakeholders and deliverables |
| Dependencies | The work dependency graph with blocked chains, and the declared package table |
| Decisions | Decisions with their outcomes, and the lineage from requirement to outcome |
| Learning | Accepted guards and their recurrences, lessons awaiting your acceptance, failures without a lesson and scope widenings |
| Agents | Host availability, agent checks, delegated runs, and the merge or discard decision |
| Records | Search across every record kind, captured documents and host receipts |
| Requirements | The current requirements, their version and their approval evidence |
project-memory view --output review.html --include-bodies --no-open writes an offline snapshot instead. See the control panel guide.
Read the records in Obsidian
project-memory export --obsidian <vault> writes the records as a folder of Markdown notes with frontmatter and wikilinks, which Obsidian opens as a vault. A work item is a folder holding its own decisions, outcomes and plans, and sources, lessons and requirement revisions sit in shared folders beside it. The graph, the backlinks and the search of Obsidian then work on the project history, while the panel stays the place where you decide.
The export runs in one direction. The database is the source of truth, the export owns one folder inside the vault and touches nothing outside it, and a note edited inside that folder is lost on the next run. After a session that wrote records, the session stop hook refreshes the vault in a separate process.
Agent checks and delegated work
When Codex or Claude Code is configured, Project Memory can start short, separate host processes. An agent check reads the records and the project and reports on an outcome, on the current intent or on an unconfirmed execution. Delegated work runs a work item in its own git worktree, limited to the paths in its plan, and a second host reviews the resulting diff before you merge it. If one host reports a usage limit or a rate limit, the run reroutes once to the other configured host.
These runs use your installed Codex or Claude Code account and consume that account's usage. A reviewer cannot edit plans, accept lessons or merge anything. See agent checks and delegated work.
Guards and scope
An accepted lesson with a trigger becomes a guard. When a guard matches the paths or the wording of a work item, a decision must list that lesson in lessons_considered with an explicit yes or no and a reason, otherwise the decision is rejected. When a work item has allowed paths, the lifecycle hooks block an edit outside them, record the block and ask you to extend the scope in the chat. The record fields document defines the pattern rules.
Honest boundaries
- A recorded plan is not permission. Autonomy and scope are advisory records; your host's own permissions and your current instructions decide what may run.
- The scope guard reads the file paths of edit tools, patch markers and the targets of MCP write tools. It does not parse shell redirection or other indirect writes inside shell commands.
- Hooks record events mechanically. Only the assistant can record what those events meant, and a connected panel does not prove that the recording is complete.
- An agent verdict is an interpretation. A passing check does not prove that the work is correct, and an empty findings list is not proof either.
- Architecture is read statically from imports, manifests and exported workflow files. Dynamic loading is not detected.
- Bounded retrieval limits the characters a call returns. It cannot control the complete model input of the host.
- Daily productivity, token usage, correction rates and human task time are not measured, and this project makes no claim about them. Testing and limitations states what is verified and what is not.
Documentation
- User guide, from the first conversation to delivery
- Control panel and agent checks and delegated work
- Setup and lifecycle and record fields
- Testing and limitations, contributing, security and releasing
Packages are published on PyPI and in GitHub Releases.
Project Memory MCP 질문
Project Memory MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add project-memory -- uvx project-memory-mcp를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
Project Memory MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
Project Memory를 어떤 프로젝트에 사용할 수 있나요?
소프트웨어 제품, 컨설팅 업무, n8n으로 구축한 워크플로우 자동화에 모두 사용할 수 있습니다.
Project Memory는 데이터를 클라우드에 저장하나요?
아니요, 모든 프로젝트 기록은 텔레메트리나 호스팅된 데이터베이스 없이 로컬 SQLite 데이터베이스에 보관됩니다.
Obsidian에서 프로젝트 기록을 볼 수 있나요?
네, 기록을 frontmatter와 wikilink가 포함된 Markdown 노트 폴더로 내보내어 Obsidian에서 사용할 수 있습니다.
프로젝트의 시각적 개요를 어떻게 확인하나요?
Plan, Work, Decisions와 같은 다양한 뷰를 제공하는 Notion 스타일의 워크스페이스인 로컬 제어 패널을 실행할 수 있습니다.