Custom agents

MCP server implementation for @voxos-ai/clink-mcp-server

An airline customer service AI agent demo built on AWS Bedrock AgentCore with Strands Framework, featuring Gateway policy enforcement and Memory (STM/LTM). 基于 AWS Bedrock AgentCore 构建的航空客服智能代理演示系统。

Agentic reasoning research: how IDE-embedded assistants plan, select tools, and iterate — arXiv-style framework paper, trace-capture templates, and agent-runtime operating notes

🎓 Turn Claude into a CBSE board examiner. 80+ AI skills, 15 agents, 200+ notes. Target: 495+/500.

SkillSpec is a DSL that adds types, contracts, composition, and tests around agent skills, then compiles back down to the same SKILL.md that existing runtimes already understand. Once a skill works and you want to make it production-ready, you codify it into a .agent file and get versioning, structural diffs, type checking, and a path to CI/CD.

A full-stack AI research agent that breaks complex questions into parallel research threads, searches the web, summarizes findings, and synthesizes a final report - all streamed live to the UI.

AI Coding Agent, Agentic Harness, Semantic Code Search Engine

Ollama based AI chat buddy

🦾 Enable autonomous research and synthesis with Gemini-Claw, a platform that analyzes, gathers, and controls data to deliver precise answers effortlessly.

Open-source gateway and community to make AI agents interoperable using Google's A2A protocol – like Hugging Face, but for agents.

made by Hmida71

Open-source vision stack with stereo camera hardware, GPU processing, and AI agent for training video classifiers.

Interactive AI-native textbook platform with Agentic RAG, personalized learning, and humanoid robotics curriculum.

Desktop Stitch pet with local Claude CLI chat on macOS

NostrMind is a config-driven Nostr monitoring worker with AI classification and optional DM alerts.

Agentic AI system that ingests PSX market data and financial news, resolves conflicting signals, and constructs a justified investment portfolio with simulated execution.

Finance research agent

Plugin Claude Code para Protheus e ADVPL/TLPP — base 155k+ registros, Agent Teams, compilação TDS-CLI, testes TIR e MCP PO-UI

A Deep Learning model for Limit Order Book price prediction

This is the frontend client application that turned to be a monorepo project by integrating backend server in /backend folder for the Rumi-AI project

An agentic RAG framework in Python, developed as the thesis project for a Master in Data Analytics. Based on the Linden library.

AI-Powered cryptocurrency price movement prediction agent.

AI Agent development using Google's Agent Development Kit (ADK) - Building intelligent agents with Gemini models and Google Search integration

Minimalistic extensible agent for Cloudflare serverless infrastructure

MCP server that analyzes TypeScript codebases, detects code health issues, fetches system incidents, and generates actionable remediation plans. Supports dual transport (STDIO for local dev, SSE for cloud deployment). Built with ts-morph, Express, and Zod validation.

AI-powered tool that reads, summarizes, and checks compliance of insurance-related documents (PDFs, images, scans).

Secure, zero-knowledge secret manager for autonomous AI agents with human-in-the-loop approval.

Plaintext Commons is the working manifesto for keeping long-form knowledge in durable, human- and agent-friendly files.

My tools for working with AI coding agents

CRDFAgent is a modular Python framework for multi-step question answering, combining clarification, routing, decomposition, retrieval, and aggregation to deliver accurate, reproducible answers for complex tasks like financial document QA.

Compound AI System for Journals – Automation API (AI Agent) A FastAPI-based automation system for creating, enriching, and managing journal articles. It integrates Google Gemini, Groq’s LLaMA, and the CORE API to deliver a seamless pipeline — from metadata input to fully structured, AI-generated journal outputs.

Bachelor Thesis of IU International University, Germany 🇩🇪

An Identity, Security, and Governance Framework for autonomous agents

MoneyFyi is an AI-driven financial intelligence dashboard that analyzes uploaded bank statements, invoices, and UPI data to detect fraud, identify compliance risks, and predict cashflow issues for Indian SMEs.

A Python dictionary that uses semantic similarity for key matching instead of exact matches. This library allows you to retrieve values using keys that are semantically similar to the ones stored, making it ideal for natural language interfaces, etc.

your first-ever RAG + agentic AI assistant, embedded directly in VS Code. Deployed on the marketplace for downloads.

A universal protocol for symbiotic collaboration between humans and autonomous AI agents. HAP enables AI agents to request human decisions in a structured, auditable, and latency-safe manner. Agents never block — they create tickets with defined timeout behaviors, allowing graceful degradation or escalation.

This repository contains the full hands-on material used in the Google Vertex AI Agent Workshop Series, delivered during the Tunisia AI Universities Tour 2026 . It demonstrates how to build agentic AI systems step by step, starting from a local AI agent and progressing toward cloud-scale agentic workflows on Google Vertex AI.

Advanced token reduction and prompt optimization framework for LLMs, featuring linguistic, algorithmic, and architectural patterns.

Deep dive into ANYTHING!

Empirical evals of agentic docs consumption

This guide is designed to help you master Generative AI through a structured, multi-phase journey

Research and development environment for building autonomous AI agents. Features practical implementations of agentic frameworks, cognitive architectures, and specialized tools for creating AI systems with enhanced reasoning capabilities.

An ai agent that critically reviews PRs

An autonomous shopping agent that definitely won’t bankrupt you (probably).

Local-First AI Research Assistant for ArXiv Papers - Built with Praval Agentic Framework (pravalagents.com)

Multi-Agent, Plugin-First Framework

Scalable webhook processing system using .NET 8, Kafka, and MongoDB with secure delivery, retry handling, and event-driven architecture.

Agent communication UI sdk

.NET reference implementation for GenAI observability using OpenTelemetry semantic conventions, OTEL Collector, and agent evals

Event-driven Agentic AI demo for healthcare using InterSystems IRIS for Health and FHIR

A proactive, headless intelligence layer designed for the hospitality sector. It predicts the impact of the external acoustic environment on the guest experience, moving from passive awareness to proactive yield management.

A production-grade demo of a multi-agent system showcasing Agent Communication Protocol (ACP) and Model Context Protocol (MCP) capabilities through a collaborative research workflow.

Infrastructure for Web4 Autonomous Agents.

Your AI Product Operating System

An autonomous Morning Briefing agent built with Gemini 2.0 Flash and the Model Context Protocol (MCP). Features proactive reasoning, multi-turn tool use, and local-first privacy

🧠 Multi-agent AI colony simulation where agents interact, compete & evolve | 🔥 PRIORITY: Seeking contributors!

AI code agent sandbox for Mac Users

FreeU 是AI的文件收纳师

Agent Skills Curator Boilerplate for Antigravity Developments

Recollect is a memory layer for AI agents that provides robust context compaction for long-running chats.

Agents 🧟 awake on trigger and provide an outcome

Building an AI Agent from scratch 🐥 Designing the brain, memory, tools, and reasoning system step by step.

AI-powered system that analyzes Freelance contracts using AWS services.

Aegis is a fully local, privacy-focused AI assistant platform that orchestrates chat, document retrieval, and tool integrations.

🤖 Enhance programming education by fine-tuning the Phi-3 Mini model to deliver well-structured, documented code responses, ensuring best practices in coding.

🤖 Evaluate AI systems effectively with our comprehensive guide to methods, tools, and frameworks for assessing Large Language Models and agents.

AI-powered flight info assistant using Flask, MongoDB & Llama 3.3 70B. Supports natural queries, user roles, and admin dashboard for flight data management.

Simulating creative government policy generation in agent-based economic models using LLMs.

Code developed during Hackathon "MIT Global AI Hackathon 2025".

The Phidata Video AI Summarizer Agent revolutionizes video content analysis by offering fast, AI-driven summarization and insightful query-based information retrieval. Built with the advanced capabilities of Google’s Gemini 2.0 Flash Exp and integrated with Phidata,

Deploy OpenClaw AI assistant to AWS EC2 with one click. Terraform infrastructure, automated setup, and cost-optimized scheduling included.

htop for AI coding agents

FORGE: Federated Orchestration & Resource Generation Engine — intelligent control panel for AI coding agents. Rust.

Human-AI Interaction Design • Optimizes collaboration between humans and AI

🐣 TinyAgent that thinks in python and execute it in the cloud with extendable hooks

AI-Powered Multi-Agent System for Smart Kitchen Renovation. Built with Vertex AI, ADK, MCP Toolbox, and Gemini 2.5, this project simulates intelligent collaboration between agents to optimize kitchen renovation tasks.

Master Edition: A resilient, self-healing Multi-Agent AI Operating System. Features autonomous task orchestration (Navigator, Curator, Evaluator), Glass-Box observability, and a custom Circuit-Breaker auto-failover pattern (Gemini 3.0 → Llama 3/Qwen) for guaranteed 100% uptime.

SEO crawl budget manipulation methodology as a Claude Skill — fast indexing for low-competition long-tail keywords

Evidence-native finance mission control that turns raw exports and docs into a Finance Twin and CFO Wiki, then answers finance questions with decision-ready evidence packets.

My dotfiles ~/.*

AI agents - performance comparison using major LLMs.

prompt to SQL, NoSQL and GoogleDrive task executing agent

A self-healing AI orchestration layer that enforces deterministic validation and security over LLM pipelines to prevent hallucinations and unsafe outputs.

The Open-Source AI CFO — Analyze, recommend, and execute.

RustyFlow is a lightweight, high-performance agent framework built in Rust for developers who need reliable, efficient, and type-safe AI workflows. A complete rewrite of the Python-based PocketFlow, RustyFlow brings memory safety, fearless concurrency, and zero-cost abstractions to agent-based systems.

Workflow-oriented Kubernetes MCP for AI agents. Deploy, diagnose, and operate clusters with less manual kubectl.

An agentic AI travel planner using local LLMs (Ollama), tool orchestration, preference-aware scoring, and human-in-the-loop booking handoff.

The repair layer for AI agents. Validates and fixes malformed API calls in <30ms before they crash your production systems.

Equip AI agents with internet access to gather real-time data from restricted or hard-to-reach online sources.

An autonomous, state-persistent recovery agent for stranded travelers. Powered by MongoDB Atlas Vector Search & LangGraph.

IntelliJ experiment for AI-assisted Java unit-test generation and verification.

Community-oriented social media platform for South Asian movie fans

Cas d'usage application vision de reconnaissance de vêtements modèle CNN (référence dans la reconnaissance) + recommandations de vêtements à la demande.

A structured workflow process for Claude Code with slash commands

A powerful, pluggable vector memory and Model Context Protocol (MCP) server for local semantic search and long-term memory.

CLI that runs builder, validation, and independent reviewer agents in a bounded loop for local AI coding workflows.