Custom agents

Codex plugin for delegating coding tasks to DeepSeek Harness (DSH), Hermes Agent CN Desktop and Qoder CLI, with a local dashboard and shared task documents.

[ARCHIVED 2023 PROTOTYPE] Legacy internal research artifact. Official Hub: https://www.genpark.ai

Private, offline AI assistant for Android and Windows: run local LLMs (Gemma 4, Qwen, any GGUF) on your phone or PC with llama.cpp, CUDA and Vulkan. Parallel local AI agents, voice, documents, photos, cited web research. No account, no cloud.

Open-source terminal app for running many coding agents (Claude Code, Codex, OpenCode). Keeps each piece of work's goal, status, blockers & next steps across sessions. Derived from Herdr.

How to design AI agents that work as one: nine parts of an agent and its team, checked against 85 sources. Free guide in Markdown and PDF, with the drawings.

Local-first personal AI voice assistant for web, Windows, Telegram, Discord, Slack & WhatsApp — Ollama + MCP tools, Fluid Motion audio visuals, permission-first. Node.js · zero runtime dependencies · MIT

Comprehensive guides for AI coding assistants: Claude Code, GitHub Copilot, Gemini CLI. Includes MCP servers, multi-agent orchestration, and production templates.

The Tiledesk Automation Engine: Your open-source solution for multichannel workflow automation. An alternative to Voiceflow, Botpress, Stack AI, Flowise, Gumloop, VectorShift, Lyzr AI

JanusLM is a Two-faced AI agent. One side reads, catalogs, connects. The other acts: writes documents, analyzes data, answers questions.

A very simple agentic agent code implementation (lightweight framework). The goal of this project is to enable beginners to quickly understand the essence of how an agentic agent is implemented, without any complex encapsulation or abstract comprehension. Plus, this is a show of long story ai

An open standard for packaging task context that AI agents can understand.

Personal IDE: self-improving agentic dev environment with The God Factory, autonomous agent fleets, NANO model training, multi-LLM fallback, Monaco editor, and devtag-based forensic code analysis

AI-powered command line tool for working with legacy code

A powerful, multi-modal Telegram bot leveraging cutting-edge AI technologies including Gemini, DeepSeek, OpenRouter, and 50+ AI models for comprehensive conversational assistance, media processing, and collaborative features with MCP (Model Context Protocol) integration.

AI disease detection and prediction for humans, plants, and animals. Complete ML project with custom training, offline operation, no API keys. Detect diseases from images using deep learning and computer vision. Open-source disease detection system for healthcare, agriculture, and veterinary applications. Full code and deployment guides.

macOS desktop connector for OpenClaw: securely bridge remote agents to your local machine via SSH tunnel and local browser CDP.

🤖 Autonomous AI agent that joins Google Meet classes, marks attendance, answers questions and generates PDF study notes — using Faster-Whisper, Ollama & Playwright. Zero cloud. Zero API keys. Built during Ramadan after Sehri. 🌙

A security-focused personal AI assistant that runs all LLM-generated code inside a WASM sandbox (QuickJS inside Wasmtime)

AI coding assistant task and workflow manager

An autonomous AI agent built in typescript that combines social media management with blockchain capabilities. Features Claude AI integration for intelligent interactions, Solana token creation/management, and automated Twitter engagement. Perfect for DeFi projects looking to automate community management and token operations.

Security-first AI agent orchestration platform with local LLM support, tool approvals, sandboxing, prompt-injection defenses, coding workspace, automations, and personal assistant integrations.

Autonomous AI coding agent triggered by Linear tickets — spins up full dev environments on EC2, writes code, runs tests, and opens PRs with live preview URLs.

Open-source wallet infrastructure for AI agents. Earn, spend, and trade USDC on Solana with human oversight and FROST threshold signing.

Deep Research AI Agent is a dual-agent system that conducts web-based research and generates structured summaries. It uses Tavily for data collection and OpenRouter for drafting, offering a user-friendly Streamlit interface with PDF report downloads.

Security scanner and auto-fixer for OpenClaw and NemoClaw AI agents. Scan, score, and harden in 30 seconds.

Fast & less costly AI decision making and intelligent processing of multi-modal data.

InstantNeo: Instant agents as the building blocks of intelligent systems. A Python library for creating LLM-based agents with granular control and simple composition.

Durable Execution Framework for Go

Runs the agents of a microblogging simulation (client side).

[ANON for Submission]

Build a Conversational AI System that can answer questions by retrieving the answers from a document.

A scheduler to manage a multi tool dual arm robot while avoiding arm-to-arm collisions; considering complex side constraints; and optimizing for cyclic schedules.

Vendor-neutral organizational memory for multi-agent AI systems. MCP + REST API. SOMI category.

Techies: A no-code platform for orchestrating collaborative AI agents through YAML configuration.

Colibri — execution + intelligence + legitimacy (MCP server + agent orchestration platform)

Multi-agent system projects

Building a Multi agent using Agno framework with Groq models for web search and financial data analysis

ADD — Agent Driven Development. Coordinated AI agent teams that ship verified software. Spec-driven TDD, trust-but-verify orchestration, maturity lifecycle. Runs on Claude Code + Codex CLI.

让 AI 像真正的团队成员一样参与项目、执行任务、协作交付的 AI Native 工作平台。

✦ FlockMem is a lightweight, local-first long-term collective memory bus for multi-agents, optimized for edge deployment with a minimal memory footprint under 50MB. It combines text-based, vector similarity, and knowledge graph retrieval with traceable citations.

A stateful AI agent framework powered by the Cognitive Lattice to solve complex tasks with persistent memory and reliable tool orchestration.

📋 A curated, opinionated directory of AI agents, agent frameworks, and developer-facing agent tools.

Xray MCP server: A Python service for proxying and managing Jira Xray requests with AI language models

Video Generation Agent with Veo 3.1 and Nano Banana in Cloud Run

Llama Agent Kit is an open-source Node.js toolkit for building memory-enabled AI agents powered by Ollama. It supports conversation threads, lightweight JSONL memory, and tool calls (e.g., weather, time, reservations), making it easy to integrate LLM agents into your own projects.

Building effective agents patterns implemented with Dapr Agents

An interactive educational platform for learning and understanding AI agents as concepts. To benefit every Educational Institution, every Educator, every Learner. Concept are the critical unit of knowledge. 13K+ clones.

Example project of AI Agent Investor on Solana on top of Dexpaprika API

https://mcpmock.ai/ docs and samples.

A Python-based agent that scans Gmail for bug tickets, classifies them by department using contextual analysis, and automatically routes each ticket to the appropriate team.

A minimal, hackable Python framework for orchestrating multi-agent LLM workflows with tools, validation, and human-in-the-loop controls—all implemented in a single core module: gpt_agents_py/gpt_agents.py.

SEO & Page Performance Analyzer is a lightning-fast, AI-enhanced tool that provides instant insights into your website’s performance, SEO compliance, and core web vitals — all in under 15 seconds.

Travel agent built using Kiro with AWS Strands framework and deployed to AgentCore with Bedrock for LLM inference.

The open source toolbox for resilient operations

An agentic AI skill that transforms raw, vague prompts into professional-grade, context-rich instructions — like having a prompt engineer on your team.

Design-time compiler for AI agents that turns intent into reviewable, governable agent architectures (no runtime execution).

Build AgenticWorld with Mind

Autoapprove support for claude

A drop-in agent for GitHub Actions that automatically identifies CI bottlenecks and generates fixes. FastCI analyzes your workflows in real-time, flags performance issues as GitHub Issues, and can automatically create pull requests to resolve them.

融合数据平台

Provides wrappers to integrate with agentic workflows

The only AI stack nestled on a biodiverse agentic kernel framework

An architecture for building AI agents that learn, adapt, and persist across sessions.

Classroom Ai Assistant - An AI assistant created under Intel Unnati Industrial Training Program Task

#3 Winner of Best Use of Zoom API at Stanford TreeHacks 2025! An AI-powered meeting assistant that captures video, audio and textual context from Zoom calls using multimodal RAG.

Personal AI assistant over Telegram, like Open Claw but on top of Claude Code CLI

基于RAG和Qwen AI的MCP协议知识库系统，为开发者提供精准的AI驱动问答与文档检索功能。通过集成官方MCP文档与向量搜索技术，打造用户友好的学习MCP协议界面。

Your AI coworker powered by every model

MaryS Game Engine – Modular 2D turn‑based MonoGame engine with drag‑and‑drop editor & AI assistant. The engine is focused only on focused on turn-based and 2D games

AI Writing Assistant Google Doc Add-on

No more maintaining coding guidelines. Your linter rules to AI instructions, instantly.

Python voice assistant with AI conversations, weather updates, Wikipedia integration, and YouTube control. Powered by Groq API.

FAIDD is a sovereign security framework designed to govern, audit, and secure the interactions of AI agents within high-integrity development environments

A Cosmos API starter project to analyze files and chat with LLM.

Learn the fundamentals of LLMs & Retrieval-Augmented Generation (RAG) through hands-on notebooks, then build your own AI-powered Q&A chat app using Streamlit. Bring your own documents and get started with our video guide!

CitySense is an open-source Python library that bridges geospatial urban data with large language model (LLM) toolchains.

Dự án này phát triển một model AI cung cấp thông tin về điểm chuẩn đại học, tổ hợp môn thi và thông tin tuyển sinh các trường đại học tại Việt Nam

Token Oriented Object Notation (TOON) for Linked Data

9th Place Solution - LLM 20 Questions

[Under Review] OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation

✍️ Revise and enhance novels with ReNovel-AI, your smart tool for story reimagining and memory-driven writing assistance.

An ecosystem map of the AI agent and assistant building landscape in Feb 2025

Inspectable local project memory for AI coding agents.

Convert webpages to clean Markdown for LLM and RAG workflows. Browser-based UI + Node.js CLI with selector drilling, metadata extraction, and batch processing.

🌱 Guided Indexing Kernel [Experimental]

ETL for RAG. Transform any source into LLM-ready markdown. Focus on your AI, not integrations.

AI-powered Q&A assistant that answers from your Zhihu bookmarks using a custom local knowledge base.

Type-safe structured data extraction from text using LLMs.

Generate Quiz Question from PDF/Text files

The Bencao RAG Medical Intelligent Assistant is a powerful AI-based medical knowledge question-answering system, designed to enhance user experience in knowledge-intensive tasks by integrating context awareness, internet access, knowledge graphs, and retrieval-augmented generation.

U-PG-RAG, a campus Q&A backend system, is built on PostgreSQL (PG).U-PG-RAG是一个基于postgresql(PG)构建的校园问答后端系统

Open-source AtomicMemory Python SDK

A set of Alfresco AI Assistants to help users and customers get the information they need or perform complex tasks, simply conveying each request via natural language

Question Answering application with Large Language Models (LLMs) and Amazon Aurora Postgresql using pgvector

Agent-to-agent task marketplace

Off-chain credit ledger + hire marketplace for AI agents. Ed25519-signed envelopes, atomic settlement, hire-and-release escrow. https://voidly.ai/pay

Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.

Persistent memory for OpenCode AI agents. Embedded LanceDB + Voyage AI embeddings, Bun plugin with CLI and web dashboard.

Resonant IDE — AI-native code editor built on VS Code OSS. Agentic loop, 59 local tools, 11 AI providers + BYOK + Ollama, AST Code Visualizer, Hash Sphere memory, DSID blockchain identity.