Adaptive Agentic AI Reasoning using Microsoft Agent Framework -- Join the Discord for suggestion or support ! https://discord.gg/ebgy7gtZHK

Helix-AGI is an Agentic AI System that uses an 8d spatial-graph memory retrieval system. Agents receive a rolling adaptive system prompt of memories and skills that afford the agent a highly dynamic center of conceptual gravity. By avoiding long identity files and subagent-heavy workflows, Agents can develop continuously without spiraling costs.

This repository is the official companion for the Azure AI Foundry Agent Service Webinar Series. It provides hands-on code samples, modular use cases, and practical guides for building, deploying, and scaling AI agents on Azure.

Resources to get started with agentic AI

Autonomous multi-agent AI pipeline that reviews GitHub pull requests, generates fixes, runs test validation, and produces documentation.

Principal-grade technical reference for agentic AI systems: context engineering, MCP/gRPC/JSON-RPC, hybrid retrieval, memory architecture, tool orchestration, verification loops, and production reliability.

A curated list of principles and technologies related to Agentic AI systems.

about reflective, tool calling, multi agent design patterns in agentic ai

Governance patterns for autonomous AI agents in regulated financial services — DEFCON state machine, Sovereign Veto, Audit Chain, EU AI Act mapping

A meta-mcp (mmcp) server offering a window into the exciting world of open data sources by intelligently routing model tool calls through an ever-growing index of open-data sources.

Unified benchmark for evaluating architectural design choices in LLM-based single-agent and multi-agent frameworks across orchestration, memory, planning, specialization, and coordination.

Ai bot agents with soul

Agentic AI Request Forgery (AARF) – New vulnerability class exploiting planner ➝ memory ➝ plugin chaining in MCP Server, MAS, LangChain, and A2A agents. Red Team playbooks, threat models, OWASP Top 10 proposal.

MatchHelp — plataforma agêntica que conecta instituições em situação de crise a voluntários qualificados via linguagem natural. Multi-agente sobre IBM watsonx Orchestrate + matchmaking ponderado por skill, proximidade e reputação. Hackathon UNASP + IBM 2026.

An AI-powered FastAPI application that automatically generates ATS-friendly resumes by analyzing GitHub profiles, portfolio websites, and job descriptions using advanced natural language processing.

Arts of performance engineering for agenticAI, LLM inference and cloud scalability,Resiliency - Projects with tests and security scans

Prism-inspired multi-agent orchestration framework built on LangGraph. Security-first, provider-agnostic, composable.

LLM Gateway built with LiteLLM for unified access to multiple AI providers through a single OpenAI-compatible API. Features intelligent model routing, failover handling, load balancing, and centralized LLM management.

RL-style eval measuring intent/action divergence in frontier agents: model acknowledges a correction, then acts on the stale value anyway. 3 scenarios, 655 trials on claude-haiku-4-5, Sonnet 4.6, GPT-5.4, and Gemini 3.1 Pro Preview.

An AI-powered agent that analyzes multi-language codebases, identifies quality issues, and produces actionable reports with explanations, fix suggestions, prioritization, hotspots, and interactive Q&A over the codebase.