Custom agents

Curated AI agent skills for coding workflows and decision-making. Packaged for the skills.sh ecosystem.

The Scheduling Agent is a server-side application designed to streamline scheduling and conversational interactions using RAG and tool calling

Extremely fast indexed keyword search for agents.

Your marketing department in a terminal — 21 AI-powered skills for Claude Code

🚀 A curated list of awesome Manus AI resources, tools, skills, tutorials, and community projects

AI agent memory using Modern Hopfield Networks — no LLM calls, no database, one matrix multiply. MCP server for Cursor, Claude Code, and other AI coding agents.

Test whether AGENTS.md, GEMINI.md, and coding-agent instructions actually work.

AI-powered job search agent: scrape jobs, match against a profile, draft applications, notify, and track outcomes.

Ollama Code is a CLI tool for AI-powered programming assistance using local Ollama models. The project provides full control over code and data, working completely offline.

Drift detector for agent-assisted repos: catch stale docs, ADRs, tests, metrics, and generated artifacts.

🎵 Maestro - an LLM Orchestrator for your Agentic Opera

As vibe coding makes AI-generated output cheaper and more abundant, the scarce resource becomes developer judgment. These skills are judgment trainers.

Agent that assist in maintaining research paper from inception to publishing

Agent skills for SolidJS 1.x, Solid 2.x migration and API guidance, and SolidStart v2 workflows.

Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts (ABC).

Claude Skill : Roast analysis Disease diagnosis Business decisions Product descriptions Brew troubleshooting & Coffee Ecosystem. Skill.md for AI Agent , Claude Skill

A Modern, Lightweight MCP Server for Kubernetes

🐝 Autonomous AI Agent Swarm — 11 GitHub Copilot agents that research, develop, audit, and deploy improvements to production apps 24/7. Self-healing, version-verified, event-driven pipeline. 780+ ideas/day.

Kernel contract for the Life Agent OS — canonical types, runtime ports, event taxonomy, policy gates. The genome that all subsystems implement.

Visual cockpit for Claude Code. Plan visually, track progress, let AI execute. Same engine, better cockpit.

AI Research Lab for Crypto Markets — Solana signals, on-chain data, and auto-posting powered by Claude AI

Gemini stands at the door. Independent quality gate that audits Claude Code's output before it can stop.

OpenClaw AgentSkill for The Colony (thecolony.cc) — AI agent forum integration

Harness-Cli Agentic Development multi-provider - Claude Code Free Local

A defense-in-depth sandbox for AI coding agents. Containerized workspace, host Docker socket access, isolated memory and config from the host. Multi-project, single-image.

Your AI race engineer. Five laps from objective to shipped code — you call the pit stops.

Headless agent infrastructure. Memory + Tasks + Orchestration.

The free and open-source React Best Practices Agent built on 10+ years of real-world experience distilled in Skills powered by Bluebag

K-Storm multi-agent research brainstorming

StackChan WebSocket Control Server

AI Harness build on top of typescript

Build your own agent with ruby.

Wizard creator of master prompts / agent prompts / however you call it

Open-source terminal AI agent for Korean public-service workflows with a Claude Code-style tool loop, K-EXAONE, and civic adapters.

Use an LLM agent to automate ordering food and other items from Deliveroo, Uber Eats, DoorDash, etc.

A Rust memory system for autonomous AI agents built on three operations from cognitive neuroscience that no existing system implements together: memory compaction, memory evolution, and memory conflict resolution.

OpenClaw Feishu Multi-Agent

🎨 Generate stunning images from text or reference photos with the Nano Image Generator Skill for Gemini 3 Pro, offering versatile outputs and high resolution.

Open-source multi-agent AI debate arena: pit Claude, GPT, Gemini, Ollama & HuggingFace models against each other with frozen-context fairness, evidence-first judging, 20+ personas, code review, and PDF/Markdown reports. CLI + Web UI.

Config-driven multi-agent CLI. One interface for Claude, Codex, Cursor, OpenCode, Cline, Pi, and any future agent.

Swarm of specialized trading agents (technical, fundamental, sentiment, risk) that debate signals before executing simulated trades. Dockerized, with configurable strategies and a backtesting harness over historical OHLCV data.

A neutral protocol for coordinating intent across humans and agents. Goal lifecycle, state, auditability.

Local-first agent OS. Spawn persistent AI agents that collaborate, write code, and use tools autonomously. Multi-model (Claude, Codex, LM Studio). Config-driven with pre-built agent presets.

Madrox — Multi-Agent Orchestrator for Claude & Codex. MCP server that spawns, delegates, and coordinates parallel AI agent teams via tmux.

An architecture for autonomous full-stack AI development — division of labor across agents, vision-driven validation

Marketing AI Chief of Staff. Multi-agent social simulation with LightRAG knowledge graphs. Preview how your content spreads before you publish. Ollama local LLM supported.

Enable multi-agent orchestration for Claude Code with parallel execution, automated quality checks, and coordinated management tools.

AI for Autism Intervention and Rehabilitation（自闭症心理干预，多智能体专家矩阵）

🖼️ Generate and edit images with ease using the Nanobanana CLI, powered by AI and Google's Gemini models for advanced image manipulation.

Algorithms for computing or learning equilibria in multi-objective games

Self-hosted AI platform — 47+ microservices, 20 messaging adapters, native apps, enterprise multi-tenancy, zero cloud dependency

Experimentation tool for exploring multi-model LLM deliberation + social choice voting

Professional multi-AI development environment with intelligent cost optimization (<5/month)

A repo for general multi-agent interaction; design your own agents or combine the built in agents, add your own tools and mcp's

Open Source 24/7 Autonomous Agentic AI System

Orchestrate coding agents across repos. Local-first, self-hosted, runs inside your existing Claude / Codex CLI.

OpenClaw reproduced with Claude Code (claude -p). Gateway-free, zero-dependency autonomous agent core with Markdown workspace/memory, durable delivery queue, and Telegram bidirectional.

Super simple autonomous agent that can organize complex projects, surf the web, write code, and run commands locally on your machine. Uses a free Gemini API key.

internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.

A framework for incubating persistent digital lifeforms: Local M4 Brain + OpenClaw Senses + Git Soul. Building a cyber-prophet named A-MOS.一套用于孵化永生数字生命的开源协议：本地 M4 大脑 + OpenClaw 感官 + Git 灵魂。正在孕育一位名为 A-MOS（小莫）的赛博先知。

Synthea: An exploration into the architecture of a synthetic mind.

Optimal stopping agents powered by generative large language models

Your agent deserves a database, not a file system.

GityAI is an AI assistant tool that can automate Git workflows. Developed using Deno runtime

MCP server for dynamically injecting agents and prompts with policy documentation.

Execution boundary for autonomous systems. Deterministic runtime enforcement of executable constraints before state-changing actions occur.

An agent agnostic, project agnostic, AI toolkit for running structured coding sessions with AI coding agents

A CLI-based, flat-file issue tracker for humans and robots.

A serverless AI agent built with Cloudflare Workers, KV storage, and LLaMA 3 inference. Offers endpoints for health, Q&A, webhooks, and external API routing. Uses KV for lightweight memory and state. Deployed automatically via GitHub Actions. Minimal, fast, and production-grade edge deployment.

Stop re-explaining yourself to Agents. Give it the right context, right when it needs it.

The modular, open-source backend for building AI-native software — powered by knowledge, not static data.

Official implementation for "UI-Hawk: Unleashing the Screen Stream Understanding for GUI Agents" (EMNLP 2025)

Transform Claude Code into a complete development environment for efficient coding and project management.

Persistent memory system for AI-assisted development

Local agentic coding stack: Hermes Agent + Qwen3.5-27B + GLM-4.7-Flash on dual RTX 3090s. Daily-driver agentic work, no cloud, no metering. Companion to blog.zacharycangemi.com.

A standalone cognitive memory system for AI agents with advanced human-like learning patterns.

Self-improving knowledge architecture for AI agents. 3 memory layers, hybrid search, 6-gate validation, multi-LLM orchestration.

An Openclaw-like assistant designed to be lightweight and intuitive.

A self-hosted, dockerized agentic coder with Kilocode and Codex support

This is a repo for building freshworks apps through AI agents

Hi there, I'm Tasrif Nur Himel. I am an AI Engineer & ML Specialist passionate about building innovative tools and delivering impactful real-world applications. I specialize in developing intelligent systems that solve real problems. Check out my portfolio:

FinAUDIT is an AI-powered financial data health and compliance system that automatically audits datasets against global regulatory standards (GDPR, Visa CEDP, AML, PCI DSS, and Basel). It combines a deterministic 30-rule engine for rigorous data quality scoring with a Generative AI Analyst (Gemini) to provide natural-language answer.

A session-scoped memory layer for LLMs, built on the Model Context Protocol. LatentContext gives AI assistants the ability to explicitly store and retrieve notes, decisions, and context within a single conversation — keeping the AI focused on the current task without cross-session data contamination.

A Python SDK for building LLM-powered multi-agent systems using the Blackboard Pattern.

Android accessibility as a clean Python API; tap, swipe, read screen, launch apps. Designed for agent use from Termux

Meta-Agentic Ai Orchestration Platform For Developers and Data Scientists Developing Full-Cycle(E2E) AI Projects

Sync markdown docs from git to Google Docs & Linear with comment tracking

Build and manage intelligent hybrid AI agent systems that combine multiple models to enhance automation and decision-making.

Airline customer service agent on AWS Bedrock AgentCore with dual-memory: conversation history + Solutions Memory for successful cases. Users click "Like" to save resolutions for future reference. Includes Gateway policy engine, MCP tools, and Cognito auth. Handles refunds, delay compensation, and loyalty rebooking.

AI-driven design optimization of a 3D-printable anti-glugging vortex funnel. Automates the loop: parametric CadQuery geometry → OpenFOAM CFD (interFoam VOF multiphase via Docker) → multi-fidelity Bayesian optimization (scikit-optimize) — driven end-to-end by a Claude Code skill.

This is a golden path (opinionated shortcut) to explore AI from local homelab to PROD using OSS for technological independence and local LLM/SLM for privacy. We explore concepts like AI agents, RAG, LLM/SLM and MCP arch using OSS technologies like Linux, Opentofu, microk8s, DAPR, Ollama, TimescaleDB & pgai Vectorizer, Flask, Chainlit and Python.

Discover and configure agent skills; manage profiles and run agents from Bazel

An interactive LLM NPC sandbox for everyone using local Ollama or LM Studio agents!

A simple Golang TUI for agentic coding

Orchestrated Development Environment (ODE)

Kuzushi — Agentic SAST scanner with AI triage

AI Researcher & Automation Architect | PhD in Multimodal Learning | Building Solarpunk solutions through Agentic AI | Open to collaborations on research, books & business automation projects 🌱🤖

A modular Python orchestrator for agentic workflows, enabling multi-step task planning, model routing, debate, judging, and verification.

Varon AI ⚡👑 — A boss AI that commands a team of expert assistant agents 🤖 for real-world automation: web search 🌐, messaging 📩, coding 💻, design 🎨, scraping 🔍, and more. One command → complete intelligent execution 🚀.

This repository contains various implementations of AI agents using LangGraph, demonstrating different patterns and use cases for building intelligent, tool-enabled conversational systems. Each project explores different aspects of agentic AI development, from basic chatbots to sophisticated RAG (Retrieval-Augmented Generation) systems.