Verfolgt Projektpläne, Entscheidungen, Ergebnisse und Learnings in einer lokalen SQLite-Datenbank, die von KI-Assistenten gelesen und beschrieben werden kann.
Auch bekannt als Dankaro-projects/project-memory, project-memory, project-memory-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 Tage
- 328
- Neueste Version
- 0.5.0b9
- Letzter Commit
- 8. Okt. 2026
- Lizenz
- MIT
Was ist Project Memory MCP?
Project Memory ist ein MCP server. Verfolgt Projektpläne, Entscheidungen, Ergebnisse und Learnings in einer lokalen SQLite-Datenbank, die von KI-Assistenten gelesen und beschrieben werden kann.
Zusammenfassung generiert aus dem README des Projekts
Über Project Memory MCP server
Project Memory bietet eine lokale SQLite-Datenbank, um den Lebenszyklus von Softwareprodukten, Consulting-Projekten oder n8n Workflow-Automatisierungen zu tracken. Es ermöglicht KI-Assistenten, Datensätze zu Projektplänen, Entscheidungen, Ergebnissen und Learnings zu lesen und zu schreiben. Entwickler nutzen dies, um durch drei spezifische MCP Tools eine kontinuierliche Historie der Arbeit aufrechtzuerhalten und sicherzustellen, dass der Kontext über verschiedene Chat-Sessions hinweg erhalten bleibt.
Das System ist für die lokale Nutzung mit Python 3.11 oder neuer konzipiert. Es lässt sich in bestehende CLI Tools wie Claude Code oder Codex integrieren, um delegierte Aufgaben und Agent-Checks zu verwalten, wobei die bestehenden Accounts und Nutzungslimits des Nutzers verwendet werden. Nutzer können den Fortschritt über ein schreibgeschütztes lokales Control Panel überwachen, das wie ein Notion-Workspace funktioniert und Ansichten für Architektur, Abhängigkeiten und die Historie von Entscheidungen bietet.
Das Setup erfolgt über uv, und Nutzer können Projekte mithilfe spezifischer Templates wie product, engagement oder automation initialisieren. Dies stellt sicher, dass Starter-Dokumente und Projektphasen von Beginn an automatisch strukturiert sind. Der Server arbeitet ohne Telemetrie oder gehostete Datenbanken, sodass alle Projektdaten auf der lokalen Maschine bleiben.
Was du damit machen kannst
- 1Entscheidungshistorie pflegenEin KI-Assistent kann jede während eines Projekts getroffene Entscheidung zusammen mit der Argumentation und den erwarteten Konsequenzen aufzeichnen.
- 2Projektbeschränkungen durchsetzenNutzer können Schutzmechanismen basierend auf bereits gelernten Lessons setzen, um zu verhindern, dass der Assistent bestimmte Fehler erneut macht.
- 3Historie nach Obsidian exportierenEntwickler können ihre Projektdatenbank in eine Sammlung von Markdown-Notizen umwandeln, um sie in einem Obsidian Vault zu nutzen.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Project Memory MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenProject Memory MCP in Claude Code installieren
$ claude mcp add project-memory -- uvx project-memory-mcpProject Memory MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"project-memory": {
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}Project Memory MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"project-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}Project Memory MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"project-memory","type":"stdio","command":"uvx","args":["project-memory-mcp"]}'Project Memory MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"project-memory": {
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}Project Memory MCP in Codex installieren
$ codex mcp add project-memory -- uvx project-memory-mcpProject Memory MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.project-memory] command = "uvx" args = ["project-memory-mcp"]
Project Memory MCP in Gemini CLI installieren
$ gemini mcp add -s user project-memory uvx -- project-memory-mcpProject Memory MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"project-memory": {
"command": "uvx",
"args": [
"project-memory-mcp"
]
}
}
}Automatisierte Checks
Geluften am 15. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbardankaro-projects/project-memory is public and reachablegithub.com/dankaro-projects/project-memory ↗Bestanden
- Paket nennt dieses Repository als Quelleproject-memory-mcp names dankaro-projects/project-memory as sourcepypi.org/project/project-memory-mcp/ ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)Sigstore attestation for project-memory-mcppypi.org/project/project-memory-mcp/ ↗Bestanden
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-10-08github.com/dankaro-projects/project-memory ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from project-memory-mcpBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten1 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenProject 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 Fragen
Wie füge ich Project Memory MCP zu Claude Code hinzu?
Führe claude mcp add project-memory -- uvx project-memory-mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Project Memory MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Für welche Arten von Projekten kann ich Project Memory nutzen?
Es eignet sich für Softwareprodukte, Consulting-Projekte und Workflow-Automatisierungen, die in n8n erstellt wurden.
Speichert Project Memory meine Daten in der Cloud?
Nein, alle Projektdatensätze werden in einer lokalen SQLite-Datenbank gespeichert, ohne Telemetrie oder gehostete Datenbank.
Kann ich meine Projektdatensätze in Obsidian ansehen?
Ja, du kannst die Datensätze als Ordner mit Markdown-Notizen inklusive Frontmatter und Wikilinks exportieren, um sie in Obsidian zu nutzen.
Wie erhalte ich eine visuelle Übersicht über mein Projekt?
Du kannst ein lokales Control Panel ausführen, das einen Notion-ähnlichen Workspace mit verschiedenen Ansichten wie Plan, Work und Decisions bietet.