Vybe Intelligence Vault

What is Vybe Intelligence Vault about?

Vybe Intelligence Vault continuously discovers emerging AI/ML resources, evaluates them with an LLM scoring engine, and commits the ranked results back to the repository every three hours. The result is a living knowledge base of over 82,000 indexed files covering AI agents, RAG architectures, MCP servers, and modern web tooling, always ready for instant retrieval by AI agents or developers.

How to use Vybe Intelligence Vault?

1. Prerequisites – Install Ollama, Node 18+, and Python 3.10+.
2. Clone & install:

   git clone https://github.com/sairaman436/vybe-intelligence-vault.git
   cd vybe-intelligence-vault
   ollama pull nomic-embed-text   # embeddings model
   ollama pull qwen2.5:14b        # scoring model
   npm install
   pip install -r requirements.txt
   

3. Start services – The helper script launches the MCP gateway, the index builder, and the 3D web UI:

   bash scripts/vault-init.sh
   

4. Verify – Run bash scripts/vault-status.sh and open http://localhost:3000 to see the interactive map.
5. Customize – Edit vault-core/config.yaml to adjust topics, token budget, and score thresholds. The GitHub Actions pipeline will automatically apply the new configuration on the next run.

Key Features

• Fully automated pipeline – GitHub Actions cron every 3 h discovers, scores, and commits resources.
• LLM‑driven scoring – Uses local qwen2.5:14b (fallback to cloud) to evaluate quality, RAG relevance, community velocity, and tech‑stack match.
• Semantic graph – Embeddings via nomic-embed-text; edges created on cosine similarity > 0.75 with weighted tags.
• MCP HTTP gateway – Exposes POST /inject on port 3456 to return LLM‑formatted context blocks for any vault file.
• 3D visualization – React 19 + WebGL map provides real‑time insight into the knowledge graph.
• Write‑lock & append‑only logging – Guarantees safe concurrent pipeline runs.
• Extensible configuration – Topics and thresholds are YAML‑driven.

Use Cases

• Agentic workflows – AI agents can pull the latest research or tool documentation directly into their context window via the MCP endpoint.
• RAG pipelines – Retrieve semantically similar resources to supplement prompts, improving answer relevance.
• Continuous learning – Teams keep a fresh, searchable vault without manual curation.
• Developer onboarding – New hires explore the 3D map to discover curated learning paths (e.g., 7‑Day Agent Builder, 7‑Day RAG Builder).
• Tooling integration – Connect the vector index to a FastAPI search service for ad‑hoc similarity queries.

FAQ

Q: How often does the vault update? A: The GitHub Actions workflow runs on a 3‑hour cron schedule, committing any new or re‑scored resources.

Q: Can I run the pipeline locally? A: Yes. Execute python scripts/evaluate_repo.py --url <repo> --dry-run to score a single URL, or run bash scripts/vault-init.sh to start the full stack.

Q: What models are required? A: qwen2.5:14b for content scoring and nomic-embed-text for vector embeddings, both available via Ollama.

Q: How does the MCP gateway work? A: Send a JSON payload with the path of a markdown file to http://localhost:3456/inject; the server reads the file, formats it for LLM consumption, and returns the text block.

Q: Is the repository open‑source? A: Yes, licensed under MIT. Contributions are welcome via pull requests.

vybe-intelligence-vault

Automated knowledge harvesting for AI engineers.
Scrapes. Scores. Commits. Every 3 hours. Zero manual effort.

Overview · How It Works · Architecture · Quick Start · Vault Stats · Contributing

📌 Overview

Most AI knowledge bases go stale the moment you stop updating them. Vybe Intelligence Vault doesn't — it runs itself.

A GitHub Actions pipeline wakes up every 3 hours, discovers emerging AI/ML resources, evaluates them with an LLM scoring engine, and commits the ranked results back into the repo. No human in the loop. No manual curation.

The result: a self-reinforcing knowledge graph of 82,397 indexed resources spanning AI agents, RAG architectures, MCP servers, and modern web tooling — always current, always queryable by local agents via an HTTP gateway.

Built for: AI engineers who want a living knowledge base they can plug into agentic workflows, not a static awesome-list that someone forked two years ago.

⚙️ How It Works

Every 3 hours:

  GitHub Actions Cron
       │
       ▼
  evaluate_repo.py          ← discovers candidate resources from configured topics
       │
       ▼
  LLM Scoring Engine        ← qwen2.5:14b (local) or cloud fallback
       │  scores: quality, rag_relevance, tech_stack match
       ▼
  vault-core/               ← ranked .md files committed back to repo
       │
       ├─▶ rebuild-index.yml  ← triggers on push
       │         │
       │         ▼
       │   nomic-embed-text   ← local Ollama embeddings
       │         │
       │         ▼
       │   vault-index.json   ← semantic node/edge graph (cosine sim > 0.75)
       │         │
       │         ▼
       │   React 3D Map       ← WebGL intelligence visualization (SWR polling)
       │
       └─▶ Orchestrator :3456 ← MCP gateway for agent context injection

Scoring Pipeline

Each resource is evaluated across 4 dimensions:

Semantic Graph

Embeddings via nomic-embed-text (Ollama). Two nodes are linked if:

• Cosine similarity > 0.75 → similar_to
• Shared tech stack → depends_on
• Same category + shared tags → references

Edge weight = cosine_sim + (shared_tags × 0.08)

MCP Gateway

HTTP bridge on :3456. Send a vault file path → receive a clean, LLM-formatted context block. Agents can pull any resource into their context window without reading the filesystem directly.

# Example agent request
curl -X POST http://localhost:3456/inject \
  -d '{"path": "ai/agents/tool-use-patterns.md"}'

🏗 Architecture

Key Design Decisions

Write-lock state management — state.lock prevents collision writes when multiple pipeline jobs run concurrently. All mutations are append-only to vault-events.log (JSONL). In-memory reads use a 30s TTL. → scripts/state-manager.js

Hybrid inference — Pipeline tries local Ollama first (zero cost, no rate limits). Falls back to cloud LLM if Ollama is unavailable. Scoring is deterministic via fixed seed. → scripts/evaluate_repo.py

Bot commits on heatmap — Git identity configured so automated commits register on the contribution graph. Pipeline runs as vybe-bot with a PAT scoped to repo only. → .github/workflows/harvester.yml

🚀 Quick Start

Prerequisites

• Ollama installed and running
• Node.js 18+
• Python 3.10+

Setup

# Clone
git clone https://github.com/sairaman436/vybe-intelligence-vault.git
cd vybe-intelligence-vault

# Pull required models
ollama pull nomic-embed-text   # embeddings
ollama pull qwen2.5:14b        # scoring

# Install dependencies
npm install
pip install -r requirements.txt

# Start everything (MCP server + orchestrator + web UI)
bash scripts/vault-init.sh

Verify

# Check service health, ports, and event log
bash scripts/vault-status.sh

Open http://localhost:3000 for the 3D intelligence map.

Configure Topics

Edit vault-core/config.yaml to control what gets harvested:

topics:
  - ai-agents
  - rag-architectures
  - mcp-servers
  - llm-inference
  - next-gen-web

token_budget: 4096
score_threshold: 0.65

📈 Trending Signals

Top rising resources based on momentum and community velocity.

• 🔼 Android Open Source Project • Rank: +92
• 🔼 Google for Developers | Build with Gemini • Rank: +1062
• 🔼 Firebase | Google's Mobile and Web App Development Platform • Rank: +128
• 🔼 SpeechifyAI - Voice AI Research Lab • Rank: +16
• 🔼 Godot Docs – 4.7 branch — Godot Engine (stable) documentation in English • Rank: +542

🌟 New Discoveries

Fresh intelligence recently indexed into the vault.

• 🆕 NYC may require landlords and realtors to disclose the use of AI in listings • Score: 452
• 🆕 AI Mania Is Eviscerating Global Decision-Making • Score: 188
• 🆕 What's the deal with all the random weekly quota resets for agents lately? • Score: 51
• 🆕 SpeechifyAI Agents: Real-Time Voice AI Overview | SpeechifyAI API • Score: 0
• 🆕 How to Opt Out - The NAI: Network Advertising Initiative • Score: 0

💤 Recently Inactive

Resources showing declined activity or relevance.

• 💤 Painting the sides of railroad rails white to reduce derailment
• 💤 In-toto: A framework to secure the integrity of software supply chains

The stats shown here are generated from the current vault content. They refresh automatically when the bot finds changes.

📚 Learning Paths & Builder Maps

The vault includes curated paths and essential guides to help you build faster:

8 Learning Paths

• 7-Day Agent Builder
• 7-Day AI Engineering
• 7-Day AI Frontend
• 7-Day AI SaaS Builder
• 7-Day Automation Builder
• 7-Day LLMOps
• 7-Day MCP Builder
• 7-Day RAG Builder

6 Best-Of Guides

• Essential 3D WebDev
• Essential Agent Building
• Essential AI Engineering
• Essential Automation
• Essential Frontend AI UI
• Essential RAG Stack

📁 Repository Layout

vybe-intelligence-vault/
├── .github/
│   └── workflows/
│       ├── harvester.yml        # Main 1h cron pipeline
│       └── rebuild-index.yml    # Triggered on vault-core/ push
│
├── vault-core/
│   ├── config.yaml              # Topics, token budgets, score thresholds
│   ├── vault-index.json         # Compiled semantic node/edge graph
│   └── vault-events.log         # Append-only JSONL event ledger
│
├── intelligence-map/            # React 19 + WebGL 3D dashboard
│
├── mcp-server/                  # FastMCP integration server
│
├── scripts/
│   ├── evaluate_repo.py         # Resource discovery + LLM scoring
│   ├── orchestrator/
│   │   └── context-injector.js  # MCP context formatter
│   ├── state-manager.js         # Lock-safe state writes
│   ├── build-index.js           # Embedding + edge compiler
│   ├── vault-init.sh            # Startup daemon (concurrent)
│   └── vault-status.sh          # Port + health diagnostics
│
├── ai/                          # Indexed resources by category
│   ├── agents/
│   ├── rag/
│   ├── models/
│   └── mcp/
│
└── search-index.md              # Flat searchable index

🗺 Roadmap

• Vector search API over vault-index.json (FastAPI endpoint)
• Discord/Slack bot that answers "what's new in RAG this week?"
• Contributor scoring — track who surfaces the highest-value resources
• Export to Obsidian vault format
• GitHub App so others can run their own vault instance

🤝 Contributing

PRs welcome. Read CONTRIBUTING.md first.

# Run the scoring pipeline locally against a single URL
python scripts/evaluate_repo.py --url https://github.com/your/repo --dry-run

Bug reports → open an issue
MIT License — see LICENSE