Show HN: Friday – Self-hosted persistent memory for AI coding agents (MCP)

An open-source project called Friday launched as a self-hosted persistent memory layer for AI coding agents, connecting to tools such as Cursor, Claude, Copilot, and VS Code through the Model Context Protocol (MCP). Friday runs on a FastAPI backend combining Mem0 semantic memory, ChromaDB vector search, and Neo4j knowledge graph, exposing four MCP tools — add_memory, add_fact, memory_search, and get_context — and claims targeted retrieval cuts token use by 90% while developers spend up to 40% of their time rebuilding context without persistent memory.

The open-source, self-hosted persistent cognitive memory layer for AI coding agents. Cursor forgets. Claude forgets. Copilot forgets. Friday doesn't. | 🚀 Quickstart -60-second-quickstart | 🔌 IDE Setup -ide-setup--10-seconds | ✨ Features -features | 📡 API Docs -api-reference | 🏗️ Architecture -architecture | 🗺️ Roadmap -roadmap | Live Neural Studio — Obsidian-grade knowledge graph visualizer mapping real AI cognitive memory constellations. You're deep in a session with Cursor. You've explained your entire auth architecture. Your JWT strategy. Your database schema. Your preferred patterns. You open a new chat. You: "Add a refresh token endpoint using our JWT pattern." Cursor: "Sure What JWT library are you using? And how is your auth structured?" You: 😤 again. for the 47th time this week. Every AI coding assistant suffers from the same critical design flaw: no persistent memory. Each session starts at zero. Your AI gives you generic advice instead of deeply personalized, project-specific insight. You're repeating yourself constantly. The result? You're spending up to 40% of your time just rebuilding context — instead of building product. Friday is a persistent cognitive memory backbone that plugs into your existing AI tools via the Model Context Protocol MCP https://modelcontextprotocol.io . It runs fully self-hosted on your own infrastructure — your data never leaves your machine or your server. ┌──────────────────────────────────────────────────────────────────────┐ │ YOUR AI AGENT Cursor / Claude / Antigravity / VS Code │ └──────────────────────────────┬───────────────────────────────────────┘ │ 4 MCP Tools stdio transport ├── add memory ├── add fact ├── memory search └── get context │ ▼ ┌──────────────────────────────────────────────────────────────────────┐ │ FRIDAY BRAIN FastAPI │ │ │ │ Layer 2: Mem0 Layer 3: ChromaDB Layer 4: Neo4j │ │ ┌──────────────────┐ ┌─────────────────┐ ┌───────────────┐ │ │ │ Semantic Memory │ │ Vector Search │ │ Knowledge │ │ │ │ │ │ │ │ Graph │ │ │ │ • Cross-session │ │ • 90% fewer │ │ ────────── │ │ │ │ persistence │ │ tokens via │ │ ● WebApp │ │ │ │ • Contextual │ │ targeted │ │ ● Auth │ │ │ │ similarity │ │ retrieval │ │ ● Payments │ │ │ └──────────────────┘ └─────────────────┘ └───────────────┘ │ │ │ │ ⚡ Auto-Graph Engine │ │ ┌─────────────────────────────────────────────────────────────┐ │ │ │ Every memory → LLM extraction → Neo4j nodes + edges │ │ │ │ Zero manual linking. Your knowledge base wires itself. │ │ │ └─────────────────────────────────────────────────────────────┘ │ │ │ │ 🎨 Neural Studio │ │ ┌─────────────────────────────────────────────────────────────┐ │ │ │ Obsidian-grade live knowledge graph browser │ │ │ │ Spread slider • Filters • Inspector drawer • Full CRUD │ │ │ └─────────────────────────────────────────────────────────────┘ │ └──────────────────────────────────────────────────────────────────────┘ | Capability | Without Friday | With Friday | |---|---|---| | Remembers architecture decisions across sessions | ❌ | ✅ | | Recalls your exact coding preferences & style | ❌ | ✅ | | Knows your full project stack & dependencies | ❌ | ✅ | | Persists knowledge across chat resets | ❌ | ✅ | | Visual knowledge graph of your codebase | ❌ | ✅ | | Versioned facts ledger with full audit trail | ❌ | ✅ | | Self-hosted — data never leaves your infra | ❌ | ✅ | | Works with Cursor, Claude, VS Code, Antigravity | ❌ | ✅ | | Token cost per task | ~8,000 tokens | ~800 tokens | | Context recall accuracy | ~30% | ~94% | Requirements: Docker https://docker.com + Docker Compose https://docs.docker.com/compose/ installed. That's literally it. No Python setup. No database config. No services to manage manually. Clone and configure git clone https://github.com/itskie/friday.git cd friday cp .env.example .env Fill in your .env — takes 60 seconds Set your own master password to protect your self-hosted server FRIDAY API KEY=pick any secret password you want DeepSeek ultra-affordable — $0.14/M tokens Get yours at: https://platform.deepseek.com DEEPSEEK API KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Mem0 — generous free tier available Get yours at: https://mem0.ai MEM0 API KEY=m0-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Neo4j password — you choose this NEO4J PASSWORD=change to something strong Launch everything in one command docker compose up -d This starts: - 🧠 Friday Brain on http://localhost - 🕸️ Neo4j on http://localhost:7474 - 🎨 Neural Studio at http://localhost Verify it's running curl http://localhost/health {"status":"healthy","layers":{"neo4j":"ok","mem0":"ok","facts":"ok 0 entries "}} Store your first memory curl -X POST http://localhost/add \ -H "X-Brain-Key: your key" \ -H "Content-Type: application/json" \ -d '{ "content": "We use JWT with 15min access tokens + 7-day refresh. Implementation in gateway/auth.py. Never store tokens in localStorage — httpOnly cookies only.", "project": "MyApp" }' Your AI now remembers. Forever. ✅ Friday is designed to be the central cognitive memory for all your AI coding tools . Whether Friday runs locally on your machine or on a remote 24/7 cloud server AWS EC2, VPS, Homelab , every agent connects to the same unified memory via the Model Context Protocol MCP https://modelcontextprotocol.io . ┌───────────────────────┐ │ Cursor Desktop │──┐ └───────────────────────┘ │ ┌───────────────────────┐ │ │ Claude Code CLI │──┼── MCP Protocol stdio transport └───────────────────────┘ │ FRIDAY URL="http://your-server-ip:8000" ┌───────────────────────┐ │ BRAIN API KEY="your secret key" │ Antigravity IDE │──┤ └───────────────────────┘ │ ┌───────────────────────┐ │ │ Codex / Custom Agents │──┘ └───────────────────────┘ ▼ ┌──────────────────────────────┐ │ FRIDAY CENTRAL BRAIN │ │ Self-Hosted on Cloud/EC2 │ │ FastAPI + Mem0 + Neo4j │ └──────────────────────────────┘ 💡 Shared Brain Superpower : An architectural rule or decision stored by Claude Code in your terminal is immediately accessible to Cursor , Antigravity IDE , or Codex on your desktop. Zero manual syncing. One brain across your entire toolchain. Pick your client below, paste the configuration, and restart your agent: ⚡ Antigravity IDE Add Friday to your Antigravity global MCP configuration at ~/.gemini/config/mcp config.json : { "mcpServers": { "friday": { "command": "python", "args": "-m", "mcp.server" , "cwd": "/path/to/friday", "env": { "FRIDAY URL": "http://localhost:8000", "BRAIN API KEY": "your key from env" } } } } If Friday runs on a remote server/EC2, change FRIDAY URL to http://<your-server-ip :8000 🤖 Claude Code CLI Connect Claude Code to your Friday brain with one terminal command: claude mcp add friday -e FRIDAY URL="http://localhost:8000" -e BRAIN API KEY="your key from env" -- python -m mcp.server Or configure directly in ~/.claude.json under "mcpServers" : { "mcpServers": { "friday": { "command": "python", "args": "-m", "mcp.server" , "cwd": "/path/to/friday", "env": { "FRIDAY URL": "http://localhost:8000", "BRAIN API KEY": "your key from env" } } } } 🖱️ Cursor Create or edit .cursor/mcp.json in your project root or add globally in Cursor Settings → MCP → Add New Server : { "mcpServers": { "friday": { "command": "python", "args": "-m", "mcp.server" , "cwd": "/path/to/friday", "env": { "FRIDAY URL": "http://localhost:8000", "BRAIN API KEY": "your key from env" } } } } For a remote server, change FRIDAY URL to http://<your-server-ip :8000 📟 Codex & Autonomous Agents CLI / Scripts Any custom agent, Codex script, or CI loop can interact with Friday in two ways: Option A: Via MCP stdio Run the MCP server directly as a subprocess using standard JSON-RPC 2.0. Option B: Direct HTTP REST API zero client dependencies Store memory from any agent script curl -X POST http://<your-server-ip :8000/add -H "X-Brain-Key: your key" -H "Content-Type: application/json" -d '{"content": "Refactored payment gateway to Stripe SDK v2.", "project": "MyApp"}' Retrieve relevant context before starting a prompt curl -X POST http://<your-server-ip :8000/search -H "X-Brain-Key: your key" -H "Content-Type: application/json" -d '{"query": "How is payments structured?", "project": "MyApp"}' 💻 VS Code Cline / Roo Code Add to your VS Code settings.json or via Cline MCP settings : { "cline.mcpServers": { "friday": { "command": "python", "args": "-m", "mcp.server" , "cwd": "/path/to/friday", "env": { "FRIDAY URL": "http://localhost:8000", "BRAIN API KEY": "your key from env" } } } } 🖥️ Claude Desktop Edit your Claude Desktop configuration: - macOS : ~/Library/Application Support/Claude/claude desktop config.json - Windows : %APPDATA%\Claude\claude desktop config.json { "mcpServers": { "friday": { "command": "python", "args": "-m", "mcp.server" , "cwd": "/path/to/friday", "env": { "FRIDAY URL": "http://localhost:8000", "BRAIN API KEY": "your key from env" } } } } 📁 Pre-built config templates for all clients are available in examples/ https://github.com/itskie/friday/blob/main/examples . Every memory you store is automatically analyzed by an LLM DeepSeek Flash . Entities and relationships are extracted and wired into your Neo4j knowledge graph without any manual input from you. Input: "MyApp uses Stripe for subscriptions. Plans: Free $0 , Pro $19/mo , Team $49/mo . PayPal handles international. Webhooks at /api/payments/webhook." Auto-extracted graph: MyApp ────USES────────▶ Stripe MyApp ────USES────────▶ PayPal MyApp ────HAS PLAN────▶ FreePlan price: $0 MyApp ────HAS PLAN────▶ ProPlan price: $19/mo MyApp ────HAS PLAN────▶ TeamPlan price: $49/mo Stripe ───WEBHOOK AT──▶ /api/payments/webhook No YAML. No manual tagging. Just store memories, and your knowledge graph builds itself. A browser-based visual explorer for your AI's knowledge — built with the same graph engine that powers Obsidian https://obsidian.md 's graph view. What you can do: - 🌌 Explore your entire knowledge base as a living constellation - 🔍 Full-text search — camera auto-follows, inspector slides open - 🎛️ Spread slider 1–10 — breathe space into dense graphs in real-time - 🏷️ Project filter chips — isolate WebApp vs Auth vs Payments constellations - 🖱️ Click any node → right-side inspector with facts, edges, actions - ➕ Add / ✏️ Rename / 🗑️ Delete / 🔗 Connect — full CRUD via UI - ❄️ Freeze physics to lock a layout, Fit View to reset camera - ⚡ Live auto-refresh as new memories arrive Discrete facts rules, preferences, constants are stored with immutable version history . Old versions are superseded, never deleted. You always have a full audit trail. Store a fact POST /facts → {"content": "We deploy on Ubuntu 22.04 LTS + systemd"} id: "a3f9e1b2", created at: "2026-09-01", superseded: false 3 months later — upgraded POST /facts → {"content": "We deploy on Ubuntu 24.04 LTS + Docker Compose"} Old fact: superseded: true ← preserved for history New fact: superseded: false ← active version Your AI always gets the active version. Past versions auditable via API. GET /facts?include superseded=true Instead of dumping your entire memory into every prompt, Friday uses ChromaDB vector search to retrieve only the most relevant context for each query. Traditional RAG — expensive and noisy context = all memories 10,000 tokens of everything Friday — surgical precision context = memory search "JWT refresh token implementation" Returns: exactly the 3-5 memories about JWT, nothing else Cost: ~200 tokens vs 10,000 → 95% reduction Once connected, your AI agent automatically calls Friday's tools. No prompting required. ┌──────────────────────────────────────────────────────────────────┐ │ Tool │ When Your Agent Uses It │ ├──────────────────┼───────────────────────────────────────────────┤ │ get context │ At session START — loads all active facts │ │ │ + recent memories for instant orientation │ ├──────────────────┼───────────────────────────────────────────────┤ │ memory search │ Before answering architecture/design Q's │ │ │ "What's our auth pattern again?" │ ├──────────────────┼───────────────────────────────────────────────┤ │ add memory │ After implementing features, fixing bugs, │ │ │ making architectural decisions │ ├──────────────────┼───────────────────────────────────────────────┤ │ add fact │ For atomic rules that never change: │ │ │ stack choices, team preferences, standards │ └──────────────────┴───────────────────────────────────────────────┘ Suggested system prompt addition: At the start of every session, call get context to load my preferences and project context. Before answering any technical question, call memory search with the relevant topic. After implementing features or making decisions, call add memory to persist the context. friday/ │ ├── 📡 gateway/ │ └── main.py FastAPI backbone — auth, routing, all endpoints │ ├── 🧩 layers/ Pluggable memory backends swap any layer │ ├── layer2 mem0.py Semantic memory — Mem0 cloud API │ ├── layer3 chroma.py Vector store — ChromaDB local │ └── layer4 neo4j.py Knowledge graph — Neo4j │ ├── ⚡ pipelines/ Background intelligence │ ├── auto graph.py LLM entity extraction → Neo4j wiring │ └── extract facts.py S3-style versioned fact management │ ├── 🔀 orchestrator/ │ └── router.py Query routing — picks best layer per query type │ ├── 🔌 mcp/ │ └── server.py MCP stdio server JSON-RPC 2.0 │ ← This is what your IDE connects to │ ├── 🎨 studio/ │ └── index.html Neural Studio — 1,400 lines, zero dependencies │ force-graph + d3 + vanilla JS │ ├── 🐳 docker-compose.yml Neo4j + Friday Brain — production-ready ├── 🐳 Dockerfile python:3.11-slim, multi-stage ready ├── 📦 requirements.txt Pinned dependencies └── 🌱 seed/ Demo data to bootstrap a fresh install ├── facts.example.json └── blueprints/demo architecture.md Data Flow: Your IDE → MCP call: add memory "We use Redis for rate limiting" → gateway/main.py → Mem0 store sync → auto graph.py background → DeepSeek: extract entities → Neo4j: MERGE Redis node → Neo4j: CREATE edge :App - :USES - :Redis ← {"status": "added", "mem0 id": "abc123"} All authenticated endpoints require the X-Brain-Key header. 🌐 = public endpoint no auth required . | Method | Endpoint | Auth | Description | |---|---|---|---| | GET | / 🌐 | — | Serves the Neural Studio UI | | GET | /health 🌐 | — | Health check — reports status of all layers | | GET | /docs 🌐 | — | Interactive Swagger UI | | POST | /add | ✅ | Store a memory + trigger auto-graph wiring | | POST | /facts | ✅ | Add or supersede a versioned fact | | GET | /facts 🌐 | — | List all active facts | | GET | /facts?include superseded=true 🌐 | — | Full history including superseded | | POST | /search | ✅ | Semantic search via Mem0 | | POST | /ingest | ✅ | Ingest a document / architecture blueprint | | GET | /api/graph-data 🌐 | — | All nodes + edges for Neural Studio | | GET | /api/search-quick?q=term 🌐 | — | Fast fuzzy node name search | | POST | /api/node/create | ✅ | Create entity node in graph | | DELETE | /api/node/{id} | ✅ | Delete node + all relationships | | POST | /api/node/rename | ✅ | Rename an entity node | | POST | /api/link/create | ✅ | Create a typed relationship edge | Full interactive docs: http://localhost/docs | Variable | Required | Default | Description | |---|---|---|---| | FRIDAY API KEY | ✅ | — | Your self-hosted server secret set by you to protect endpoints | | DEEPSEEK API KEY | ✅ | — | LLM key for auto-graph extraction | | MEM0 API KEY | ✅ | — | Mem0 key for semantic memory | | NEO4J PASSWORD | ✅ | — | Neo4j DB password you set this | | NEO4J URI | — | bolt://neo4j:7687 | Neo4j connection string | | NEO4J USER | — | neo4j | Neo4j username | | DEEPSEEK BASE URL | — | https://api.deepseek.com | LLM API base URL | | DEEPSEEK MODEL | — | deepseek-chat | LLM model name | | FACTS PATH | — | /app/facts/facts.json | Path for facts ledger file | | HOST | — | 0.0.0.0 | Server bind address | | PORT | — | 8000 | Server port | Where to get your keys all have free tiers : | Service | Link | Cost | |---|---|---| | DeepSeek | platform.deepseek.com https://platform.deepseek.com | ~$0.14/M tokens — cheapest capable LLM | | Mem0 | mem0.ai https://mem0.ai | Generous free tier | | Neo4j | Bundled in Docker Compose | Free & local | v1.0 — Foundation ✅ shipped - FastAPI memory gateway with full REST API - Neo4j knowledge graph integration - Autonomous graph extraction engine DeepSeek + Neo4j - Neural Studio UI — Obsidian-grade graph browser - MCP server — Cursor / Antigravity / Claude Desktop / VS Code - S3-style versioned facts ledger - Docker Compose — 1-command self-hosted setup - ChromaDB semantic search layer - Full CRUD via Neural Studio add / rename / delete / connect - Per-project constellation namespacing v1.1 — Multi-User & DX 🚧 in progress - Multi-user support with isolated namespaces - Python SDK pip install friday-client - TypeScript/JavaScript SDK - friday CLI — friday add "..." , friday search "..." from terminal v1.2 — Integrations 📋 planned - GitHub Actions bot — auto-store PR summaries as memories - Slack integration — /friday remember ... from Slack - Jira / Linear sync — auto-import tickets as project context - VS Code extension — sidebar memory panel v2.0 — Cloud 🌐 future - Friday Cloud — managed, zero-infra option - Team workspaces — shared memory across your engineering team - Private beta waitlist Friday is built in public and we'd love your contributions. Fork & clone git clone https://github.com/YOUR USERNAME/friday.git cd friday Set up environment cp .env.example .env pip install -r requirements.txt Run tests — all must be green before PRing python -m pytest tests/ -v ✅ 9 passed in 0.34s Create your branch git checkout -b feat/your-amazing-feature Commit using conventional commits git commit -m "feat: add X that does Y" Push & open PR git push origin feat/your-amazing-feature See CONTRIBUTING.md https://github.com/itskie/friday/blob/main/CONTRIBUTING.md for full guidelines. Browse good first issue https://github.com/itskie/friday/issues?q=label%3A%22good+first+issue%22 labels to find where to start. Friday is designed for self-hosted deployment. A few notes: - API Key auth — all write endpoints require X-Brain-Key header - Public read — /health , /facts read , /api/graph-data , and Neural Studio are public by default. If you expose Friday publicly, consider adding reverse-proxy authentication e.g., Nginx basic auth or Cloudflare Access . - Secrets — never commit your .env . It's in .gitignore by default. - Network — by default, Friday binds to 0.0.0.0 . For local-only use, change to 127.0.0.1 in .env . Found a vulnerability? Please open a private security advisory on GitHub rather than a public issue. MIT © 2026 Friday Contributors — see LICENSE https://github.com/itskie/friday/blob/main/LICENSE for details. Built for the AI-native developer generation. If Friday saved you from AI amnesia, please consider giving it a ⭐ It helps more developers discover the project and keeps us motivated. ⭐ Star on GitHub https://github.com/itskie/friday · 🐛 Report Bug https://github.com/itskie/friday/issues/new?template=bug report.md · 💡 Request Feature https://github.com/itskie/friday/issues/new?template=feature request.md · 💬 Discussions https://github.com/itskie/friday/discussions <sub Made with ❤️ by developers who were tired of repeating themselves to their AI.</sub