◆ Category · 18 assets

AI Frameworks

Browse 18 AI Frameworks modes for AI coding agents — production-grounded, cited, installable. Part of the VIBE library.

🔎 Search within AI Frameworks
mode

anthropic-sdk-expert-mode

Master the Claude API — tool use, prompt caching, computer use, and agent loops

View → mode

autogen-expert-mode

Build event-driven, actor-model multi-agent systems with Microsoft AutoGen v0.4+

View → mode

crewai-expert-mode

Orchestrate role-playing autonomous agent crews with sequential and hierarchical processes

View → mode

dspy-expert-mode

Program — don't prompt — language models with DSPy's declarative Signatures, Modules, and Optimizers

View → mode

inngest-agent-kit-expert-mode

Build durable, observable multi-agent networks in TypeScript with Inngest AgentKit

View → mode

instructor-expert-mode

Extract validated, typed data from any LLM with Instructor and Pydantic

View → mode

langgraph-expert-mode

Build stateful, durable agent graphs with checkpointing, human-in-the-loop, and time-travel debugging

View → mode

letta-expert-mode

Build stateful agents with persistent memory blocks and self-editing context using Letta (formerly MemGPT)

View → mode

llamaindex-expert-mode

Build agentic document workflows, RAG, and query engines with LlamaIndex 2025

View → mode

mastra-expert-mode

Build TypeScript AI agents and workflows with Mastra's modern stack from the Gatsby team

View → mode

mem0-expert-mode

Build long-term, scalable memory layers for AI agents with Mem0

View → mode

ollama-expert-mode

Run, customize, and serve local LLMs with Ollama, Modelfiles, and GGUF quantization

View → mode

openai-agents-sdk-expert-mode

Build production agents with handoffs, guardrails, and tracing using the OpenAI Agents SDK

View → mode

outlines-expert-mode

Guarantee structured LLM outputs with regex, JSON schema, and grammar-constrained generation

View → mode

pydantic-ai-expert-mode

Build type-safe, validated LLM agents with Pydantic AI's RunContext, structured outputs, and dependency injection

View → mode

trigger-dev-expert-mode

Run durable AI background jobs and agents with Trigger.dev v3 — no timeouts, full observability

View → mode

vercel-ai-sdk-expert-mode

Build TypeScript LLM apps with streamText, generateObject, useChat, and tool calling

View → mode

vllm-expert-mode

Serve LLMs at scale with PagedAttention, continuous batching, and speculative decoding

View →