AI Agents Directory

AI Agent Evaluation Framework

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. - ai-boost/awesome-harness-engineering

SciAgentArena

A benchmarking framework for evaluating AI agents in scientific research scenarios, focusing on their ability to handle complex, real-world tasks.

Mastra

Mastra is the modern TypeScript framework for AI-powered applications and agents. - mastra-ai/mastra

ToolRegistry

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (OpenAI, Anthropic, Gemini, LangChain, MCP) - Oaklight/ToolRegistry

RAG-PDF-Chat-Multi-Agent-Pipeline

A full-stack RAG demo you can run locally or deploy to a VPS: upload a PDF, build a per-browser vector index (FAISS), chat with an LLM using retrieved context. The UI is a React + TypeScript SPA; t...

Ask HN: Learning resources for building AI agents

A community-driven discussion on Hacker News about resources and frameworks for building AI agents, highlighting the growing interest and knowledge sharing in the field.

General AgentBench

A benchmark framework for evaluating general-purpose AI agents across various domains, focusing on their ability to handle complex tasks and utilize multiple skills effectively.

FlowCrew

The only open-source AI orchestrator that replaces $50k/yr enterprise tools. 8 autonomous agents, 7 languages, Vision-to-Code, 100% free on Groq. 🚀 - ParthivPandya/multi-agent-orchestrator

Ninja AI

Accomplish more everyday with the best AI tools for research, writing, coding, image generation, file analysis, and more. Try Ninja for free today.

Xemantic AI Tool Schema

AI/LLM tool use (function calling) JSON Schema generator - a Kotlin multiplatform library - xemantic/xemantic-ai-tool-schema

ToyAIKit

Minimalistic implementation for LLM-based chat assistants with Tool Use (function calling) and MCP - alexeygrigorev/toyaikit

Agents' Last Exam (ALE)

A benchmark designed to evaluate AI agents on long-horizon, economically valuable tasks, developed with input from industry experts.