gemini
π―Skillfrom ssdeanx/agentstack
|Enables interaction with Google's Gemini AI model, providing advanced language generation and multi-modal capabilities within the AgentStack framework.
Part of
ssdeanx/agentstack(8 items)
Installation
git clone https://github.com/ssdeanx/AgentStack.gitnpm run devnpm run buildnpm run startnpx vitest -t "polygon" # Filter (e.g., financial tools)+ 1 more commands
Skill Details
Overview
# π AgentStack   [](https://nodejs.org/) [](https://www.typescriptlang.org/) [](https://nextjs.org/) [](https://react.dev/) [](LICENSE) [](src/mastra/agents) [](src/mastra/tools) [](src/mastra/workflows) [](src/mastra/networks) [](ui/) [](https://vitest.dev/) [](https://zod.dev/) [](https://eslint.org/) [](https://github.com/ssdeanx/AgentStack) [](https://gitmcp.io/ssdeanx/AgentStack) [](https://wakatime.com/badge/user/7a2fb9a0-188b-4568-887f-7645f9249e62/project/e52d02a1-f64a-4f8d-bc13-caaa2dc37461) AgentStack is a production-grade multi-agent framework built on Mastra, delivering 60+ enterprise tools, 31+ specialized agents, 15 workflows, 13 agent networks, 65 UI components (30+ AI Elements + 35+ base), and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, secure governance, and AI chat interfaces. [](https://www.npmjs.com/package/@mastra/core) [](https://www.npmjs.com/package/@mastra/pg) [](https://www.npmjs.com/package/@mastra/rag) [](https://www.npmjs.com/package/@mastra/memory) [](https://www.npmjs.com/package/@mastra/ai-sdk) [](https://www.npmjs.com/package/@ai-sdk/google) [](https://www.npmjs.com/package/@ai-sdk/react) [](https://langfuse.com/) [](https://github.com/pgvector/pgvector) [](https://ai.google.dev/) [](https://openai.com/) [](https://anthropic.com/)
π― **Why AgentStack?**
| Feature | AgentStack | LangChain | CrewAI | AutoGen |
| ---------------------------- | ---------------------------------------------------- | ------------- | ------------- | ---------- |
| Production Observability | β Full Langfuse tracing + custom scorers | β οΈ Partial | β Basic | β Limited |
| Financial Tools | β Polygon/Finnhub/AlphaVantage (30+ endpoints) | β None | β None | β None |
| RAG Pipeline | β PgVector HNSW + rerank + graphRAG | β οΈ External | β Basic | β None |
| Multi-Agent | β A2A MCP + parallel orchestration (30+ agents) | β οΈ Sequential | β Sequential | β Custom |
| Governance | β JWT/RBAC + path traversal + HTML sanitization | β Custom | β None | β None |
| TypeScript | β Zod schemas everywhere (94+ tools) | β οΈ JS/TS mix | β οΈ JS focus | β Python |
| UI Components | β 65 components (AI Elements + shadcn/ui) | β None | β None | β None |
| Tests | β Vitest + comprehensive test suite | β οΈ Partial | β Sparse | β οΈ Partial |
Built for production: Secure, observable, testable agents with zero-config PgVector RAG + enterprise financial APIs.
β¨ **Core Capabilities**
- π° Financial Intelligence: 30+ tools (Polygon quotes/aggs/fundamentals, Finnhub analysis, AlphaVantage indicators)
- π Semantic RAG: PgVector (3072D embeddings) + MDocument chunking + rerank + graph traversal
- π€ 31+ Agents: Research β Learn β Report β Edit β Analyze (stock/crypto/copywriter/evaluator/data pipeline/business-legal/charting/image/coding/dane/social media/SEO/translation/customer support/project management)
- π 15 Workflows: Weather, content, financial reports, document processing, research synthesis, learning extraction, governed RAG (index + answer), spec generation, repo ingestion, stock analysis, marketing campaign
- π 13 Agent Networks: Primary routing, data pipeline, report generation, research pipeline, content creation, financial intelligence, learning, marketing automation, DevOps, business intelligence, security
- π A2A/MCP: MCP server coordinates parallel agents (research+stockβreport), A2A coordinator for cross-agent communication
- π¨ 65 UI Components: AI Elements (30 chat/reasoning/canvas components) + shadcn/ui (35 base primitives)
- π Full Observability: Langfuse traces + 10+ custom scorers (diversity/quality/completeness) + TanStack Query for state management
- π‘οΈ Enterprise Security: JWT auth, RBAC, path validation, HTML sanitization, secrets masking
- β‘ Extensible: Model registry (Gemini/OpenAI/Anthropic/OpenRouter), Zod schemas everywhere, MastraClient SDK integration
ποΈ **Architecture**
```mermaid
%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#58a6ff', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#30363d', 'lineColor': '#58a6ff', 'sectionBkgColor': '#161b22', 'altSectionBkgColor': '#0d1117', 'sectionTextColor': '#c9d1d9', 'gridColor': '#30363d', 'tertiaryColor': '#161b22' }}}%%
graph TB
subgraph "οΏ½ Frontend (Next.js 16)"
UI[AI Elements + shadcn/ui
β’ 30+ AI Components
β’ 35+ Base Primitives]
App[App Router
β’ React 19
More from this repository7
Configures and manages plugin-specific settings and preferences within the AgentStack multi-agent framework.
Generates and refines Claude Code skills by analyzing requirements, creating structured skill templates, and iteratively improving their implementation and documentation.
Skill
Synchronizes and translates network configuration data between Managed Cloud Platform (MCP) systems and the AgentStack agent framework, enabling seamless multi-cloud network management.
Enables web browsing and interaction with web pages by retrieving content, parsing HTML, and executing browser-based actions for AI agents.
Develops and generates custom command structures and implementations for agents within the AgentStack framework, enabling modular and extensible command creation.
Defines and manages a modular plugin architecture for dynamically loading, configuring, and extending agent capabilities within the AgentStack framework.