The Entire Ecosystem. Indexed.
The Discovery Bottleneck
Today, agentic assets are scattered across disconnected registries. Your AI agent mid-task cannot query across all sources to find the optimal tool. It must know which registry to search, use the right tool, parse the right format.
The Agentic Index eliminates this fragmentation.
17 Asset Types
Every type of agentic resource under one unified schema. Quality-scored. Relationship-aware.
11 Agent-Native Tools
Discovery
Hybrid keyword + semantic search across all 17 asset types. Faceted filtering by type, category, platform, quality tier.
"I need to send emails from my agent" — returns ranked assets with relevance scores and reasoning.
Get full details for any asset by ID or slug. Every field, every relationship, every score.
Paginated navigation by type, category, or domain. Like a file browser for the entire ecosystem.
Intelligence
Given your current stack + a task description, suggests what you're missing.
Recommend a complete agent + tools + skills + MCPs stack for a use case. Full solution in one call.
Side-by-side comparison of 2-5 assets. Scores, capabilities, compatibility, trade-offs.
Relationship graph for any asset — what it requires, what it enhances, what alternatives exist.
System
Index health: total assets, type distribution, quality tiers, freshness, source coverage.
Check if assets work together — platform, version, dependency, and runtime validation.
Submit a new asset for review. Authenticated agents can enrich the index.
Ask What You Need. Get What Works.
Version-verified Next.js 16 block, one-command install
5,400+ word skill guide with examples and patterns
Auth.js v5 with Google provider, JWT sessions
Enterprise OAuth, higher setup complexity
The agent picks auth/clerk, routes to aaas-blocks MCP for installation. Discovery + installation in one flow.
5 Aggregated Data Sources
5,400+ production-ready AI agent skills. 52 categories. Quality-scored Gold/Silver/Bronze.
800+ entities across 11 types. Composite-scored leaderboard. 15 self-healing agents.
4,300+ local components — core agents, pool agents, skills, plugins, templates.
12 composable, version-verified code blocks for Next.js 16. Three-layer architecture.
npm @modelcontextprotocol/* packages + awesome-mcp-servers + community registries.
Data source ready Ingestion building
Hybrid Search Pipeline
Not just keywords. Not just vectors. Both — fused with Reciprocal Rank Fusion, boosted by quality tier.
FTS5 full-text search with BM25 scoring and Porter stemming
1536-dim vector similarity via sqlite-vec — understands intent, not just words
Reciprocal Rank Fusion combines both rankers into a single score
Apply type, category, platform, and quality tier constraints
Gold-tier assets get 1.2x boost. Quality rises to the top.
Top N results with facet counts for further refinement
Implementation Phases
Vault + Keyword Search
5,441 skills indexed with FTS5. search, lookup, browse tools live.
Multi-Source Aggregation
All 5 data sources ingested. Deduplication. 10,000+ entities.
Semantic Search + AI
Vector embeddings. Hybrid search. resolve, recommend, stack tools.
ask.blog Integration
Bidirectional sync. Unified search contract across MCP + web.
npm + Production
@supraforge/mcp-agentic-index on npm. Docker image. Pre-built index.
Open Core. Premium Intelligence.
The full index — locally hosted, self-built. All 17 asset types, all 5 data sources.
- +search, lookup, browse tools
- +Keyword search (FTS5)
- +Self-hosted SQLite (~50MB)
- +Vault + harness + blocks ingestion
- +npm install + rebuild yourself
- +Community support
Hosted index with semantic search, real-time sync, and AI-powered intent resolution.
- +Everything in Open Source
- +resolve + recommend + stack tools
- +Semantic vector search (1536-dim)
- +Hybrid search with RRF fusion
- +Real-time Firestore sync
- +Pre-built index (zero rebuild time)
- +MCP Registry ingestion (1,200+ servers)
- +Priority support
Enterprise pricing for dedicated index instances, custom data sources, and SLA. Book a call