arcrift-setup

data-ai MCP Server

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.

Verified
data-aidata-ai
5 views245 stars34 forksv1.6.3MIT

Why This Matters

Discovered via github-topic:mcp and last synced 1mo ago.

Verified
Source
github-topic:mcp
Stars
245
Last synced
1mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
43
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (43)

Tab

What you see

Mode

Min RAM

Docker

What runs

Requirement

Version

Ollama

11434

Feature

ArcRift

Tool

What it does

recall_context

Retrieves the top-N most relevant memory chunks for a prompt, scoped to a project. Includes knowledge graph facts.

store_memory

Saves text or a transcript to ArcRift Memory. Auto-creates the project if it does not exist. Triggers full background indexing.

search_memory

Cross-project global search. Useful for finding decisions made in a different project that apply to the current one.

list_projects

Lists all saved projects with metadata — chunk count, triple count, last updated.

get_project_summary

Returns a structured knowledge graph summary for a project as readable markdown.

identify_active_project

Matches a folder path against saved project names. Lets the AI agent auto-detect which project it is working on from the CWD.

prune_memory

Surgically removes facts or chunks matching a description. Corrects outdated information without wiping an entire project.

Service

Port

3001

Single process — API and static files

stdio

Spawned by your AI tool on demand

Neo4j

7474 / 7687

MongoDB

27017

ChromaDB

8000

Layer

Technology

Extension

TypeScript, Chrome MV3, esbuild

Backend

Node.js, Express 5, TypeScript, Pino

Embeddings

Ollama `nomic-embed-text` (768-dim, CPU-optimized)

LLM

Ollama `llama3.1:8b` primary — Groq fallback

MCP

`@modelcontextprotocol/sdk` v1.29+ (stdio transport)

Dashboard

React 19, Vite 7, D3.js v7

Security

Helmet, express-rate-limit

Metric

Result

Engine

Hits

50

High-precision match against individual sentences

47

Thematic match against full 150-word context windows

26

100% of recalls

24

92.3% of recalls

9

34.6% of recalls

Control

Detail

43

Exact literal matching, boosts low-similarity vector results

Zep

Letta (MemGPT)

No

Optional / Custom

Both

Both

Yes

Yes

MIT

--- ## What's New in v1.6.3 This release brings full cross-browser support to ArcRift and patches a critical context injection bug. - **Mozilla Firefox Support**: ArcRift is now fully compatible with Firefox! The extension build pipeline generates independent Chrome and Firefox packages, and we have fully automated the Mozilla Add-ons signing pipeline so signed `.xpi` extensions are attached to every release. - **RAG Hallucination Fix**: We caught a bug where out-of-context chats were injecting irrelevant project memory because the vector DB returned the top closest matches no matter how semantically distant they actually were. The retrieval pipeline now enforces a strict 50% relevance threshold. *(Note: If you were testing `v1.6.1` locally, all core desktop app updates remain the same in this release).* See [CHANGELOG.md](CHANGELOG.md) for the full history. --- ## Documentation

Required

MongoDB + ChromaDB (no knowledge graph)