GenAI Resources

A collection of GenAI Resources (primarily open source/free) that I have used or have come across so far.

Software Development With Agents

1. Spec-driven Development

   • Spec Kit: https://github.com/github/spec-kit
   • BMAD: https://github.com/bmad-code-org/BMAD-METHOD
   • BoundaryML (BAML): The First Language for Building Agents: https://boundaryml.com

2. Dev Agents & IDEs

   • Goose- A local, extensible, open source AI agent that automates engineering tasks: https://github.com/block/goose
   • Github Copilot
   • Claude Code
   • Amazon Kiro
   • Google Antigravity
   • Opencode- https://opencode.ai/docs/

3. Protocols

   • LSP
   • LSAP: https://github.com/lsp-client/LSAP

Reference Resources

• https://www-cdn.anthropic.com/58284b19e702b49db9302d5b6f135ad8871e7658.pdf
• https://claude.com/blog/how-anthropic-teams-use-claude-code

Agent Workflows & Orchestration

1. Agent Development Frameworks

   • Langgraph/DeepAgents/Langchain: https://docs.langchain.com/oss/python/deepagents/overview
   • CrewAI: https://crewai.com/open-source
   • Microsoft AutoGen: https://github.com/microsoft/autogen
   • Pydantic AI: https://github.com/pydantic/pydantic-ai
   • AWS AgentCore: AWS AgentCore

2. Agents & Skills

   • Agents.md: https://agents.md
   • Agent Skills (SKILL.md): https://github.com/agentskills/agentskills
   • Tessl: The package manager for agent skills and context: https://tessl.io
   • Design.md: A design system document that AI agents read to generate consistent UI across your project: https://stitch.withgoogle.com/docs/design-md/overview

3. Low-code/No-code

   • Langflow: https://github.com/langflow-ai/langflow

Deployments

1. Langgraph: https://www.langchain.com/blog/deep-agents-deploy-an-open-alternative-to-claude-managed-agents

Protocols

• Agent Protocol: https://github.com/langchain-ai/agent-protocol

• Agent-to-Agent Protocol (A2A):

  • https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/
  • https://github.com/a2aproject/A2A

• Agent Payments Protocol (AP2):

  • https://cloud.google.com/blog/products/ai-machine-learning/announcing-agents-to-payments-ap2-protocol
  • https://github.com/google-agentic-commerce/AP2

• Agentic Commerce Protocol (ACP):

  • https://www.agenticcommerce.dev/docs
  • https://developers.openai.com/commerce

• Universal Commerce Protocol (UCP):

  • https://ucp.dev

Computer Use

• Anthropic Computer Use: https://www.anthropic.com/news/developing-computer-use
• OpenAI Operator: https://openai.com/index/introducing-operator/
• Amazon Nova: https://aws.amazon.com/blogs/aws/build-reliable-ai-agents-for-ui-workflow-automation-with-amazon-nova-act-now-generally-available/

LLMs

1. Local LLMs
   • Ollama: https://ollama.com
   • LMStudio: https://lmstudio.ai

Observability

• Langfuse: https://github.com/langfuse/langfuse

Evals

• DeepEvals: https://github.com/confident-ai/deepeval
• Pydantic Evals: https://ai.pydantic.dev/evals/
• Terminal Bench (Agent benchmarking): https://github.com/harbor-framework/terminal-bench-2
• Harbor Framework (Agent & LLM Evals): https://github.com/harbor-framework/harbor?tab=readme-ov-file
• OpenEvals: https://github.com/langchain-ai/openevals

Evals Learnings

• https://blog.langchain.com/evaluating-deep-agents-our-learnings/

MCP Development

• FastMCP: https://github.com/PrefectHQ/fastmcp
• OpenAI MCP: https://github.com/modelcontextprotocol
• WebMCP: https://developer.chrome.com/blog/webmcp-epp
• MCP Apps: https://modelcontextprotocol.io/extensions/apps/overview

MCP Servers List

• https://github.com/PipedreamHQ/awesome-mcp-servers?tab=readme-ov-file
• https://modelcontextprotocol.io/examples
• https://github.com/modelcontextprotocol/servers?tab=readme-ov-file#%EF%B8%8F-official-integrations
• https://github.com/modelcontextprotocol/servers?tab=readme-ov-file#-community-servers
• https://mcpmarket.com

MCP Types:

• MCP 2.0: ?

Agent Generated Code Execution Sandbox

• Daytona (AGPL 3.0 license): https://github.com/daytonaio/daytona/blob/main/LICENSE

Guardrails

• Nvidia NeMo Guardrails: https://github.com/NVIDIA-NeMo/Guardrails
• Langchain Guardrails: https://docs.langchain.com/oss/python/langchain/guardrails
• Guardrails AI: https://github.com/guardrails-ai/guardrails

Knowledge Bases

1. RAG
   • PGVector: https://github.com/pgvector/pgvector
   • ChromaDB: https://github.com/chroma-core/chroma
   • Qdrant: https://github.com/qdrant/qdrant

RAG Types

• Corrective RAG: ?
• Self RAG: ?
• Adaptive RAG: ?
• Lean RAG: ?
• ComoRAG: ?
• REX RAG: ?
• RAG-Agency: ?
• RAG 3.0 : ?

2. Graph RAG
   • Microsoft Graph RAG: https://github.com/microsoft/graphrag
   • Vectorless Tree RAG: https://github.com/VectifyAI/PageIndex
   • FalkorDB: https://www.falkordb.com

Graph RAG Resources

• https://neo4j.com/blog/genai/graphrag-manifesto/

UI

• AG-UI: https://github.com/ag-ui-protocol/ag-ui
• Agent Chat UI for Langgraph Agents: https://github.com/langchain-ai/agent-chat-ui
• Deep Agent Chat UI for Langchain Deep Agents: https://github.com/langchain-ai/deep-agents-ui
• Gradio: Web Interface for ML models: https://www.gradio.app

Techniques and Best Practices

Agents

• https://www.anthropic.com/engineering/building-effective-agents
• https://openai.com/business/guides-and-resources/a-practical-guide-to-building-ai-agents/
• https://github.com/humanlayer/12-factor-agents
• https://www.ibm.com/think/ai-agents#605511093

Prompt Engineering

• https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices
• https://www.promptingguide.ai
• https://cloud.google.com/discover/what-is-prompt-engineering#prompt-engineering-overview-and-guide
• https://developers.openai.com/cookbook/examples/gpt-5/codex_prompting_guide?ref=blog.langchain.com
• https://www.promptingguide.ai
• https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-engineering-guidelines.html
• https://brightpool.notion.site/ChatGPT-Prompt-Pack-ddaaee466a434527a58a4d6fc3027fb5
• https://brightpool.notion.site/fe947b16fe894c3e8a8a19a6b81aec2c?v=9b1d189283d54b6bba80882239ecbb1a

Context Engineering

• https://www.promptingguide.ai/guides/context-engineering-guide
• https://blog.langchain.com/context-engineering-for-agents/
• https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
• https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus
• https://cognition.ai/blog/dont-build-multi-agents

Harness Engineering

• https://blog.langchain.com/improving-deep-agents-with-harness-engineering/
• https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
• https://openai.com/index/harness-engineering/

Links to other great resources

• https://github.com/genieincodebottle/generative-ai
• Google AI Labs: https://labs.google
• https://www.anthropic.com/learn
• Patterns for Building Generative AI Applications on Amazon Bedrock: https://builder.aws.com/content/2dhKdwyY1kzhFTg9CTLbaJ9MmTN/patterns-for-building-generative-ai-applications-on-amazon-bedrock
• https://aws.amazon.com/blogs/machine-learning/automate-the-insurance-claim-lifecycle-using-amazon-bedrock-agents-and-knowledge-bases/
• Designing Agentic AI Systems, Part-1: Agent Architectures: https://vectorize.io/blog/designing-agentic-ai-systems-part-1-agent-architectures
• https://www.langchain.com/blog/human-judgment-in-the-agent-improvement-loop

Domain Agents

• Finance
  • LangAlpha: Financial market analysis and supporting investment decisions: https://github.com/ginlix-ai/LangAlpha

Platforms

• DATAGEN: https://github.com/starpig1129/DATAGEN
• Swarms.ai: https://github.com/kyegomez/swarms
• LiteLLM: AI Gateway to provide model access, fallbacks and spend tracking across 100+ LLMs. All in the OpenAI format. : https://www.litellm.ai

Enterprise AI Platforms

• OpenAI Frontier: https://openai.com/business/frontier/
• Anthropic Claude Cowork: https://claude.com/product/cowork

GenAI KPIs

• https://cloud.google.com/transform/gen-ai-kpis-measuring-ai-success-deep-dive
• https://cloud.google.com/transform/kpis-for-gen-ai-why-measuring-your-new-ai-is-essential-to-its-success
• https://cloud.google.com/transform/the-kpis-that-actually-matter-for-production-ai-agents