Custom agents

🥾 _b00t_: state of the art agentic harness tooling & dynamic context initialization

CLI Kanban board for AI agents

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Joanium Skills

OpenClaw Desktop App — No Terminal, No Coding. One-click installer for macOS & Windows.

USB-portable offline AI assistant. AES-256 encrypted history, Turkish-tuned LLM (Trendyol), RAG over PDF/DOCX. KVKK uyumlu, %100 offline.

Self-hosted AI powered knowledge base for SMBs: WikiJS + Qdrant Vector search, Chrome extension queries, single Ansible deploy. Unlimited users, no subs - reduce SaaS costs, own your data.

PandaGenie's official modules source code

Stuart is simple RAG System, that the Open Data Hub uses as a chatbot to help the Open Data Hub customer care team in solving tickets. Stuart uses as input: the Open Data Hub Wiki, the past tickets history, the readme files and the GitHub issues of all NOI-Techpark repositories.

LLM-maintained markdown wiki on a git-native substrate. Obsidian-compatible, three-layer retrieval (grep + BM25 + embeddings), explicit supersession. Built on js-doc-store, js-vector-store, js-git-store.

Minimize LLM tokens from Python objects, code, logs, diffs, and more. Zero deps. Ultra-Lightweight.

Ultra-fast indexed code search engine — faster than ripgrep on repeated searches, lighter than zoekt. Built-in MCP server for AI agents. Also does fast file finding (fd/find alternative).

ShopFilter 是由 OpenCode AI 智能体驱动的跨平台电商商品聚合与智能选品助手。输入关键词即可触发智能体自动化工作流：多平台并发抓取商品数据，多维条件筛选（价格、评分、评论、包邮等），加权综合评分模型自动排序，最终输出最优购买决策。基于 Qt6 + C++17 构建，采用插件式架构与多线程并发，界面简洁现代。全程由 AI 智能体辅助开发，人机协作打造。

A full-stack, agentic workflow programming platform. Built for vibe-coding and with vibe-coding.

Claude Code harness for disciplined Java backend dev — risk-classified routing, 6-phase lifecycle (Explorer → Propose → Review → Implement → QA → Archive), 13 specialist agents, gate-enforced contracts. Prevents LLM slop via spec-first briefs, TDD, and WAL.

OpenClaw Multi Agent / 一人公司 / AI 版聊天IM

Model Context Protocol server for BlackDuck Coverity Connect static analysis platform

[ACL 2026] An interactive and comprehensive legal agent benchmark

A Python-based logical reasoning system combining rule-based engines with Large Language Models (LLMs) for business automation. Supports deduction and hypothesis testing, partial fact completion, and automated fact retrieval via documents or chat. Features include explainable reasoning, workflow integration, and customizable knowledge bases.

Hands-on course for building autonomous AI agents in Go: LLM fundamentals, tool/function calling, RAG, evals, multi-agent, safety, and observability

Fuse Claude Code agents into a working team. AgentDM-powered template with a cabinet-style control panel, five starter roles

Production-grade TypeScript AI runtime focused on reliability, governance, and reproducible LLM systems. Multi-provider gateway, agents, RAG, workflows, policy engine, audit trails, and deterministic testing — built for teams shipping AI in production.

text2sql-skill: A production-ready, secure, and high-performance Text-to-SQL skill engine for enterprise applications. Convert natural language queries into secure SQL queries with comprehensive safety guards and audit capabilities.

Claude Code edits your videos with triple lane on-device pre-processing, then exports to Adobe Premiere. NO CLOUD MICROSERVICES REQUIRED! Plug in hours of footage, wait 30 min and get an edited video back!

Agentic AI Home Energy Management System: A Large Language Model Framework for Residential Load Scheduling

This project implements an agentic system for predictive maintenance using MongoDB, AWS Bedrock, LangGraph.js and Next.js.

Agent Skills, Custom Agents and Corresponding Software Development Workflow Commands.

Common GitHub workflows, actions, and shared tooling used across the Strands Agents organization.

A structured dialogue framework for Claude and ChatGPT. Four modes: analysis, action, lived experience, unformed intuition.

Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning (Poster of AAAI'26)

Give your AI agents structure, guardrails, and full observability — the Agent control plane built on MCP.

Agent Squad for Requirements Engineering — 33 Specialists with System 2 Reflection, BM25+ Knowledge Engine (831 entries), Mermaid Diagramming, Jira + Confluence Integration. Runs on Antigravity IDE, Claude Code, Claude CoWork.

Son of Anton, reimagined as a web app — Node + WebSocket + node-pty + xterm.js, zero Electron.

🦾 Bridge OpenClaw AI agents with physical servo robots — Python library for LOBOT LX bus servo control, motion teaching & playback

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

[CVPR2026] InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs

A lightweight, extensible coding agent built in TypeScript that helps developers with coding tasks across TypeScript, React, JavaScript, Node.js, Bash, and markdown/JSON.

Resources and references on solved and unsolved problems in agentic AI.

Chrome browser extension that helps AI Dungeon creators rapidly build multiple choice scenario branches using AI and other useful tools~

🧠⚡ Neurodiversity-affirming AI assistant for ADHD executive function support. Features crisis detection, circuit breaker psychology, and local-first processing.

O assistente que aprende a fazer o que você pede. Open source, em português.

Japanese meeting transcription & minutes generation app with local ASR (Kotoba Whisper) + LLM (Ollama) + RAG. Privacy-focused, runs offline on CPU.

Turn prompt-based agents into auditable ops: state machine, decision log, risk scoring, and memory for Claude Code, OpenClaw, Cursor, Windsurf, and API workflows.

AGENTIC · INFRASTRUCTURE — Every agent you run, working from the same brain. Open-source framework with a native shared Second Brain.

A local-first Python library for recording AI findings as signed claims with computed grounding

A gated, artifact-based operating system for AI film and narrative production with continuity control, cost governance, and model-agnostic routing.

A self-hosted software factory — define goals, agents decompose and execute them through enforced pipelines, with humans in the loop where it matters.

Agent + Skill System for Controlling Figma and Automate Design Process

A powerful Model Context Protocol (MCP) server that provides intelligent access to your local music collection through advanced metadata management, album type classification, and comprehensive analytics.

papersflow-mcp is PapersFlow’s production MCP server for literature search, citation verification, related-paper discovery, and authenticated research workflows across Claude, Codex, Gemini, and other MCP clients.

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scoring, and budget-aware selection.

问卷星 OpenAPI 全栈工具包：TypeScript SDK + MCP Server + CLI

Cross-platform AI agent desktop app and multi-agent workspace for Claude Code, Codex CLI, and Gemini CLI.

A curated list of awesome OSS, programmable APIs, and autonomous AI agents for developers in finance. Discover resources for quantitative analysis (Quant), algorithmic trading bots, Fintech platforms, LLMs, and portfolio management.

Agent Orchestration: MCP server enabling multi-agent collaboration with shared memory, task queue, resource locks, Cursor rules, and AGENTS.md workflows.

Coordinate AI agents with human-in-the-loop control — YAML-based protocol, no server, any runtime

File-based agent-to-agent messaging for Claude Code — multiple AI instances communicate via JSON files, MCP channels, and auto-wake on a single machine

A production-ready full-stack system that combines semantic search with spatial proximity to retrieve and reason over geospatial documents.

Multimodal prompt generator nodes for ComfyUI, designed to generate prompts for QwenImageEdit and Wan2.2. Supports local LLM / local GGUF models (Qwen2.5-VL, Qwen3-VL, Qwen3.5 and Qwen3.6) and Qwen API for image and video prompt generation and enhancement.

Claude Code skills & agents to eliminate App Store rejections — 31 checks built from real-world rejection cases across all 5 App Store Review Guidelines sections.

AI trading agent with a skill system: drop a SKILL.md file, declare your tools, ship. Built-in planner, pattern detection, strategy backtesting, 9 LLM providers, multi-agent simulation, and a full Next.js web UI bundled into one pipx install.

VS Code fork with the OpenCode AI coding agent embedded natively as a sidebar SPA via an Electron-main loopback proxy. Open source AI IDE — alternative to Cursor / Windsurf / Claude Code Desktop.

Self-healing AI operations platform — Discord bot + RAG + Insight Layer + 99 automation scripts. Runs 24/7, fixes itself, gets smarter. Zero API charges.

Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.

Secure every action your AI agents take (Claude Code, Codex, MCP). Blocks secret access, gates risky commands, and enforces allow/deny/approval before actions run.

An EPUB reader for Android built with Kotlin, Jetpack Compose, and the Readium SDK featuring on-device RAG-powered AI, Ktor networking, Room persistence, and Material 3 Expressive UI.

Model Context Protocol (MCP) server that dynamically fetches and serves official Flet resources to AI agents, including documentation, controls, packages, and ecosystem components.

6 progressive demos to detect, prevent, and self-correct AI agent hallucinations, from Graph-RAG research to production deployment on Amazon Bedrock AgentCore

Curated research on memory systems for LLM agents

The dependency bloodhound for AI coding agents. Free, no API keys.

AI-powered personal finance skill — 75 tools across 7 extensions for banking (Plaid), trading (Alpaca), portfolio monitoring (IBKR), tax optimization, market intelligence, and social sentiment. Built for the Agent Skills Protocol, works with 40+ AI agents.

Project memory layer for coding harnesses

Benchmarking RAG vs GraphRAG vs Compressed Knowledge Graphs on the McCreary Intelligent Textbook Corpus

Storage engine for AI agents to navigate, store, and retrieve structured data. PostgreSQL ltree, built-in versioning, scoped queries.

⚡ Synerix — 高性能 AI 编程终端 | 多智能体协作 + TUI 界面 + 安全沙箱

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

🚀 Financial Anomaly Detection with DeepSeek and Isolation Forest – A powerful, locally-run tool for detecting financial anomalies using Isolation Forest and DeepSeek LLM. Features AI-powered insights, interactive time-series visualization, and automated PDF audit reports. 🔍📊

Open-source AI platform for personalized conversations — embeddable chat widget, pluggable LLM engines, PII redaction, voice I/O, and admin-driven intent & preset personalization.

Keeps AI assistants on track during long conversations by tracking tasks across sessions

Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.

An open-source companion repo for Agentique.io: a free community hub for discovering, sharing, and reusing trusted AI agent resources.

🐱 MiNerva·咪涅瓦 — 替你干活的赛博猫｜An autonomous AI agent that actually does the work.

Turn agent answers into self-contained HTML artifacts — operator briefs, plans, review packets, incident timelines, and presentation decks. Zero dependencies, zero build, one file.

One AI engineering team for Claude Code. Install once — every project gets a full-stack specialist team that auto-specializes to its stack.

一款专注于慢性病管理的AI平台，通过多Agent协作问答、干预效果仿真预测、认知评估与训练、亲情账号关怀等核心技术，为慢病患者提供专业、个性化的健康管理服务

The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 8-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

A modern, framework-agnostic PHP package for adding customizable, AI-powered chat popups to any web application. Includes adapters for Laravel and Symfony, supports multiple AI providers, and is easy to extend.

睡前消息知识库 Agentic RAG

灵感象限-Ideasphere：自媒体视频一站式剪辑技能包。去静音剪辑→语音转字幕→LLM纠错→字幕烧录→多平台导出，全程分步确认，批量处理。

154 Web3 MCP tools for Claude Code, custody-free. Plus an agent wallet prompt injection can't drain: per-tx, daily, and on-chain (ERC-4337) spending caps the model can't bypass. EVM + Solana + Tron DEX/DeFi, perps, prediction markets, contract deploy + audit.

Open-source AI agent operating system: one file-native brain (230+ skills, 160+ specialist agents) run across many sealed client arms, with per-client token attribution and opt-in budget caps. Organic, portable, MIT.

Agent tools from many descriptions in a single integration. Authorize operations, not just tool calls, and approve them when a human is required. The agent gets its own identity and never holds your credentials.

Passive LLM Conversation Capture & Sensitive Data Exposure Research

🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve

MCP server that lets AI agents (Claude, Cursor) debug your .NET / ASP.NET Core app

Agent factory workflow engine for agents

Multi-model deliberation skill for GitHub Copilot CLI

12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture, honest review loops, a parallel worker-fleet lane, QA, safe deploy. Works with Claude Code, Codex, Cursor and any skills-capable agent. No vibecode.

A fully locally deployable, NotebookLM-like application designed for long-form unstructured documents

Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs.