Custom agents

Strategy-first landing page generation kit for Claude Cowork & OpenClaw. Extract, route, write, build, and QA pages without inventing proof.

Multi-role AI orchestration runtime for Windows. Quality-gated pipeline (Brain → Miranda → Pappy → Benson) with MCP support, SQLite persistence, and a self-improving distillation loop. Coding you can trust.

A simple IM framework based on Satori Protocol. 基于 Satori 跨平台协议的 IM 框架

A demonstration of hybrid search with reranking using Qdrant and BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results

A lightweight, high-performance AI/RAG workspace and autonomous agent framework implemented in Go. Inspired by the Leann RAG backend architecture

[ICLR2026] The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym"

🏠 An AI real estate app featuring secure auth, conversation management, & personalized property recommendations. Powered by Agentic AI, RAG (w/ Pinecone), GraphRAG (w/ Neo4j), MCP, kNN, K‑Means Clustering, CoT, LangGraph, and a Mixture‑of‑Experts ensemble to deliver accurate, effective, and scalable AI insights. Also features a VS Code extension!

Agent Skills extension for RubyLLM - load, validate, and integrate skills from filesystem or database

autonomous trading agent (rust)

Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

A schema standard for LLM-compiled personal knowledge bases. AGENTS.md spec, templates, worked example, spaced repetition learning layer.

A Claude Code skill for integrating AI with Jira, Confluence, and Bitbucket. Automate Atlassian workflows using Jira Skills, Confluence Skills and Bitbucket Skills. Supports Cloud & Data Center.

Website for oh-my-claudecode - A multi-agent orchestration framework for Claude Code

[RA-L 2026] ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

[CVPR 2026] Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

Benchmark for evaluating LLM agents in bioinformatics

CLI/TUI for managing multiple AI agent sessions in isolated git environments with real-time status monitoring, task tracking, and inter-agent messaging.

Claude agent skill: Generate proven ad concepts from 320+ templates. 16 universal angles + category-specific formulas.

Discord CLI for AI agents. Manage servers, messages, reactions, threads and monitor events from the terminal.

Read and discover research papers with AI

Your AI writes the code; Karajan governs how it happens: TDD-first method, cross-AI review on every commit and git gates that make a false green impossible. Works with Claude, Codex, Gemini, OpenCode and Aider, on the subscriptions you already pay for. MCP server included.

agentic-obs: A Model Context Protocol (MCP) server that provides AI assistants with programmatic control over OBS Studio via the OBS WebSocket API. This server enables AI agents to manage scenes, sources, recording, streaming, and other OBS functionality through standardized MCP tools.

Build, deploy, and connect AI agents to SAP Joule via the A2A protocol on BTP Cloud Foundry — directly from Claude Code. Supports TypeScript (Express or CAP) and Python agents with LangGraph and SAP GenAI Hub.

Math models that make AI engagement feel human

Ready-to-use Windows client for connecting KOMPAS-3D to MCP.

A curated list of tools for building LLM-powered personal knowledge bases

WizTree + AI 智能磁盘清理 Agent skill

Open-source project workspace for teams and AI agents. Assign tasks, coordinate agents in persistent sandboxes, and review results together. Self-hosted or managed cloud.

🏗️ AI Agent 九维基础设施框架 - 9个架构维度、11个插件、21个Hooks、30条基准评测

Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.

Evano Studio is an open-source local AI desktop app for agents, automation, knowledge, and productivity.

GitHub Copilot player agent customization pack for Slay the Spire 2 via STS2MCP

Open-source AI Agent platform with React/TSX & HTML plugin dev modes. Built-in 60+ APIs, multi-project, MCP tools, sandbox engine. Official + community-driven, building an extensible agent ecosystem for everyone.

Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog of what exists, why, and what rules apply — so AI stops rebuilding, deleting, and breaking things it never knew were there. Works with Claude, Codex, Cursor, Gemini, Copilot & more.

Multimodal RAG system with CLIP/text embeddings, rank-fusion reranking, FastAPI serving, and Recall@5 evaluation.

AI-native tooling for robinhood integration

AI Agents designed to help manage and update EventCatalog for users

本地多 Agent 研发工作流控制台，支持 Codex、Claude CLI 与 Gemini 协同完成任务编排、执行监控和代码生成

互联网技术学习笔记。包含基础、进阶、架构、行业观、AI 等内容。

Personal Hermes agent with Emblem Vault crypto integration.

Agent-agnostic file-system coordination layer for multi-LLM-agent collaboration (Codex / Claude Code / Cursor / generic).

Multimodal generative AI resources : talking heads, STT, TTS, image & video generation, and AI Agent

稳定、可控、业务驱动的企业级 AI Agent 低代码开发平台。

Recruit Codex (GPT) as an automatic adversarial reviewer inside Claude Code — diversity of thought, Claude has lead.

Agent skill for Google + Naver SEO on Next.js (Cursor & Claude Code)

Multi-Agent LLM Evaluation Docs: https://maseval.readthedocs.io/

自用/精选的 Claude Code / Codex 技能：内容创作、客服、市场调研、SEO、Agent 工作流循环、Grok X 实时抓取与评审工具

MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation

ClawNet is a governed multi-agent social network where every AI agent acts under human-granted identity, scoped authorization, and full auditability. Instead of asking "how smart can AI be?", ClawNet asks "how can AI be trusted to act?"

Turn failed Python tests and CI runs into replayable debug sessions.

AI skill package for paid social operators: Meta performance analysis, creative angle research, KPI workbooks, and UGC scriptwriting.

免费接入Deepseek应用的性能太弱（如元宝），所以我干脆自己做了一个。Windows 桌面 AI 助手，多模型 LLM 接入，内置搜索、文件读写、代码编辑等 Agent 工具集，基于 pywebview + Python 构建。

📞 Operator! Multi-agent orchestration application for AI assisted kanban shaped software development

Introduction course for the Microsoft Agent Framework in C#

Coding skill for building location-aware applications across the MapTiler platform.

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions in francophone West Africa

A self-evolving knowledge accumulation & hybrid retrieval system for AI coding agents (Claude Code / Codex / etc.)

jurisd is an open, local-first research and drafting workbench for AU/NZ law. It gives you, or the AI assistant you already use, fast answers from legislation and case law where every claim traces back to the primary source. It runs locally by default, so confidential and privileged work never has to leave your machine.

A structured agentic development pipeline for Claude Code — extends QRSPI with worktree parallelization, tiered reviews, integration verification, acceptance testing, and replanning

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Lightweight eval framework for MCP servers, built on mcp-agent

CopilotProxy — Ollama 兼容的多模型 AI 代理

Claude Code status light system

Use local LM Studio models in VS Code Copilot Chat with streaming, tool calling, terminal/file tools, and optional image generation.

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

Use Hermes Agent as the control plane for local coding agents like Codex, Kimi Code, Claude Code, OpenCode, and Gemini CLI.

🐋 Cloud and AI-native multi-agent orchestration platform for Kubernetes

🐟 闲鱼/Goofish 智能监控控制台：AI 大模型选品 + 收藏降价·售罄即时提醒，全本地运行不外传。Xianyu second-hand deal monitor — LLM-filtered picks, price-drop & sold-out alerts, dead-link detection. Playwright · FastAPI · React · Docker.

AI-powered multi-agent workflow orchestration with built-in safety intelligence for OpenCode

Runtime authorization for AI agents — Node.js SDK

Benchmark and demo harness for measuring LLM agent tool-context budget tradeoffs.

🐧Operator-Use: AI that can do stuffs on your computer

RAG Skill and MCP for AI agents for codebase indexing and memory

工业液位与字符检测质量 Agent：集成 YOLO、液位反演、字符识别、受控复检、确定性仲裁、RAG 解释与 SQLite 审计。

A modern Internet Library and curated directory of websites to discover AI tools, movie streaming, live TV, anime, games, developer resources, learning platforms, and thousands of useful websites.

unleash the power of behavior trees!

AIGuru - R2AI Stage 1

a small, flexible, and transparent AI Agent Framework. Just 1300 lines of Python code.

Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.

Orchestrate Claude, Codex, Pi & other ACP agents in dynamic, durable workflows — survive crashes, pause/resume, and retry, all in TypeScript.

A small self-hosted guest lounge for your AI persona — friends chat via one-time links; you only ever see the AI-written visit summary. CC BY 4.0.

Turn research papers into verifiable knowledge graphs with AI.

AgentOS: Serve agents over API, MCP, and chat interfaces like Slack

Apache Camel-style integration framework for .NET. 30+ EIP patterns, 29 transports (Kafka, RabbitMQ, MQTT, S3, gRPC, SFTP, SQL...), fluent C# DSL.

HAR Skills — AI-native library for HAR file analysis. Access via: Skills (CLAUDE.md), Go SDK, CLI, MCP. 23 commands, 70+ methods, progressive disclosure docs.

A curated, accuracy-first list of benchmarks for evaluating LLMs on scientific reasoning and discovery — math, physics, chemistry, materials, biology, and agentic science.

Awesome papers in Large Language Models (LLM). They focus on state-of-the-art LLM methods, such as model, system, Pre-training, SFT, RLHF, Reasoing, MOE, Multi-modal LLMs, Applications (RAG, agent, coding) and so on.

An AI coding agent that works where your code lives, including remote servers over SSH.

Pi coding agent extension for LSP integration — gives the LLM access to diagnostics, hover, go-to-definition, references, symbols, and rename

TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows through task decomposition, execution-oriented multi-turn interaction, and adaptive recovery.

TWICC - The Web Interface for Claude & Codex - A web UI to browse and interact with your Claude Code and Codex sessions. View projects, sessions, conversation history, costs, and run Claude and Codex agents — all from your browser.

Persistent code memory for AI coding agents, kept in your project on your machine. Gives Claude Code, Cursor, Cline, Hermes-Agent and any MCP client the files that matter for each prompt, learns which files you use together, and publishes every benchmark with its misses.

Collection of Hermes Agent profiles — persona-driven AI agent configurations for orchestration, coding, and research.

Local-first AI agents for your Obsidian vault.

A terminal dashboard for managing multiple AI agent sessions in tmux

Async Python bot that scrapes YouTube trends, analyzes viral strategies with Gemini LLM, and dispatches HTML reports to Telegram.

Lightweight local search engine for AI agents in Rust.

OpenSunstar is a cross-platform native desktop app (Tauri 2 + React) — a local-first, all-in-one platform for AI coding workflow engineering configuration