vaultit

io.github.TheRealDataBossPublished by GitHub account TheRealDataBossv0.6.1Updated Oct 24, 2026

Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.

Overview

AI-generated overview

vaultit keeps shared project context across AI agents, exposing sessions, tasks, decisions and handoffs to an assistant over MCP.

What you can do
  • Track agent sessions and end them with a summary
  • Create and list project tasks and architectural decisions
  • Generate handoffs between sessions and agents
  • Sync repo state, diff changes and export project context
  • Validate context files and run database schema migrations
When to use it
Useful when several agents or LLM tools work on the same project and you want continuity — sessions, tasks, decisions and handoffs — instead of re-explaining context each time. Also fits teams that want a paste-ready briefing for any agent.
Requirements
Local Python package installed with pip, run as a stdio process (for example python -m vaultit.mcp). A project must be initialized with vaultit init; storage is file-based by default, or SQLite or PostgreSQL via a database URL. The optional REST server uses API keys.
Before you install
Project context, tasks and decisions are stored locally or in a configured database, so anything written there persists and may be shared with other agents. The REST server issues API keys and accepts a bearer token; keep them private. The PostgreSQL backend needs a database URL containing credentials. Writes to context files and schema migrations change stored data.

Installation

In SourceWeft

  1. Open vaultit in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

vaultit

mcp-name: io.github.TheRealDataBoss/vaultit

[PyPI] [Python 3.10+] [License: MIT] [MCP Native]

Zero model drift between AI agents.


Install

bash
pip install vaultit

Quickstart

bash
vaultit initvaultit sync --agent claudevaultit bootstrap --clipboard# paste into any AI — full context restored

CLI Reference

CommandDescription
initScaffold project context — state vector, conventions, tasks
syncScan repo and update state vector with current project state
bootstrapGenerate paste-ready briefing for any AI agent
statusShow tracked projects and their current state
doctorValidate context files for consistency and missing fields
migrateRun database schema migrations
exportExport project context to JSON/Markdown
diffShow what changed since last sync
serveStart the REST API server (FastAPI + Uvicorn)
sessionsList and manage agent sessions
tasksList and manage project tasks
decisionsList and manage architectural decisions
authCreate and revoke API keys (ck_ prefix, SHA-256 stored)

Python SDK

python
from vaultit import VaultItClient
client = VaultItClient()
# Sessionssession = client.create_session(agent="claude", project="myproject")client.end_session(session.id, summary="Implemented auth module")
# Tasks & decisionsclient.create_task(project="myproject", title="Add rate limiting")client.create_decision(project="myproject", title="Use PostgreSQL", rationale="Need JSONB")
# Handoffhandoff = client.create_handoff(from_session=s1.id, to_agent="gpt-4")

MCP Server

10 tools — native Claude Code integration via Model Context Protocol.

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "vaultit": {      "command": "python",      "args": ["-m", "vaultit.mcp"]    }  }}

Backends

bash
# File (default) — zero configvaultit init
# SQLitevaultit init --backend sqlite
# PostgreSQLvaultit init --backend postgres --db-url postgresql://user:pass@localhost/ck

REST API

14 endpoints + 3 auth endpoints. FastAPI with OpenAPI spec.

bash
vaultit serve --port 8420# → http://localhost:8420/docs   (Swagger UI)# → http://localhost:8420/openapi.json

Auth header: Authorization: Bearer ck_your_api_key

Multi-Agent Coordination

Three modes for concurrent agent access:

  • sequential — one agent at a time (default)
  • lock-based — pessimistic locking per resource
  • merge — optimistic merge with conflict resolution

Links

License

MIT © TheRealDataBoss

Source: packages/python/README.md at commit b4b0a08

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.6.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts