Custom agents

ASSUME - Agent-based Simulation for Studying and Understanding Market Evolution

Agent Skills for Claude Code and OpenCode

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

An embeddable cross-platform AI agent library written in C. Cloud and local LLMs, tool calling, long-term memory, voice, sessions, research mode, self-evolving loops. The SQLite of agent frameworks: small, portable, just works.

Git for AI agents — zero merge conflicts, any number of parallel agents, same codebase

Microsoft Foundry Local - Workshop - Build AI apps locally with Foundry Local - RAG, agents, and multi-agent workflows in Python, JS, and C#. No cloud required.

Ethicore Engine® is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blocked

OpenTiny NEXT-SDKs is a front-end AI and browser automation toolkit. It implements WebMCP + WebSkills to build AI-native apps, and leverages webmcp-cli to enable LLM agents to remote-control any webpage without source code modifications. OpenTiny NEXT-SDKs 是一套前端 AI 与浏览器自动化工具包。它通过 WebMCP + WebSkills 协议构建 AI 原生应用，并利用 webmcp-cli 实现了无需修改源码即可让大模型代理自动控制任

原生AI股票研究平台，支持多智能体分析、AI Agent 协作与实时辩论对抗，可配置的大语言模型（LLM）工作流、多源市场数据及报告导出功能。

Mailbox-native protocol and SDKs for asynchronous agent collaboration over email

Self-hosted AI code review for GitHub pull requests.

AI World Generator 2026: Create Self-Evolving Maps & Stories

Self-Tuning Multi-Agent AI Trading System 2026: 8-Source Signal Fusion & Kronos Model

⌚ 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒 | Approve your AI coding agent's risky actions from your Apple Watch, get buzzed when tasks finish

Some tools help. Some tools assist. Villani Code intervenes.

Open-source agent sandbox infrastructure for parallel coding agents: isolated workspaces, MCP/CLI control, observability, and atomic publication.

Deep research skill for AI agents: live web research, source reputation checks, safer URL fetches, and structured evidence feedback.

Agentic AI video generator — fully autonomous text-to-video pipeline with free TTS/voice-clone, auto-editing, captions, and 20+ single-task operations. Zero-cost, MIT.

Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn

Whip is an agent-native SSH mobile client, designed specifically for the Herdr multiplexer from day one

Google Antigravity 全生态中文本地化套件 | Universal Chinese localization suite for Google Antigravity ecosystem (Desktop 2.0, IDE & Extensions, CLI, Plugins).

Open-source AI alternative to Buffer and Opus Clip: Claude Code makes on-brand videos, posts them to 9 platforms and drafts replies. Self-hosted, your own keys.

Keep AGENTS.md and CLAUDE.md in sync across your projects.

Demonstrates how to build a streaming enterprise agent using Azure AI Agent Service. This sample integrates local HR and company policy documents, Bing for external context, and GPT-4o (though the service is model-agnostic) to deliver real-time Q&A and automated workflows.

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Chatbot framework

Scalable implementation of DREAM - Deep RL for multi-agent imperfect information games

谷歌5天AI Agents强化课程

Traefik with all the stuffing. Onramp is a docker compose setup designed to allow users to get up to speed quickly and securely using Traefik, LetsEncrypt, Cloudflare Tunnels and other popular self hosted home lab services.

[NeurIPS 2026] Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Official Neuron AI Laravel SDK

MAPF-LNS2: Fast Repairing for Multi-Agent Path Finding via Large Neighborhood Search

"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.

MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable into any model.

Multi-agent AI scientist that turns experimental data into > publication-ready research papers.

Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.

Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel

Interactive error analysis skill for AI agents. Studies LLM trace datasets, builds a review UI, monitors annotations, categorizes failure modes, proposes new samples.

The official code implementation of the paper “Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration“.

ZTE U60 Pro (MU5250) 5G router toolkit — Rust on-device REST agent + native iOS/Android/web companions. Reverse-engineered, 143-endpoint coverage, OpenWrt 23.05.

An open framework for designing and deploying custom AI-driven HW/SW co-design flows fast

Meeting recorder for your Mac with a live AI assistant. On-device transcription, answers from your own docs mid-call. Local-first and open source.

基于 ACP 协议的多 Agent Web 网关，让 CLI Agent 也能在浏览器中使用。

Turn Claude Code into an agentic SEO operator for your own site — audit, measure, daily loop, AI visibility, scheduled runs. Free path, no paid keys.

An AI-powered 24/7 automation solution purpose-built for Xianyu, featuring multi-expert collaborative decision-making, intelligent price negotiation, and context-aware conversations.

LLM-powered AI Data Analysis Agent with tool calling and reusable analytical skills.

睡前消息知识库 | 视频节目文稿 | 问答AI Agent | 马前卒工作室 | 睡前消息 | 参考信息 | 高见 | 讲点黑话 | 产经破壁机

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

AI-run shop: Medusa v2 + Next.js + Payload CMS operated by Fox, the built-in AI assistant. Open-source free edition of Vulpy Commerce.

Normify · DSH 插件：把项目架构写成归一化的分形模块树，三层校验（写时 / 校验 / 冻结回执）、30 个 normify_* 工具 + normify-gen 技能，一键渲染单文件交互式架构图；支持伴随式开发（change_open → brief → check → 实施 → refresh → change_close）。

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, routines, gateway.

Rust ASC is a super FAST and lightweight Android decompiler designed for Agents/Mobile Researchers.

Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.

面向高校教学、学习与科研的开源知识与 AI Agent 协作平台 | Open-source platform for education and research

A tool for comparing tokenizers

One-click installer for OpenClaw AI agent. macOS & Windows.

TensorSwarm: A framework for reinforcement learning of robot swarms.

A simple API to integrate chatbots written in Javascript with WhatsApp Web :speech_balloon::calling: (Store hotfix https://github.com/Zibri/WhatsAppWebApi/blob/master/zstore.js)

[EMNLP 2024] LongRAG: A Dual-perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering

HexAgent – An Agent harness that gives any LLM a computer to complete tasks the way humans do

Claude Code agents for the TALL stack, powered by Laravel Boost.

Python Agent DEvelopment framework

[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

Production-ready AI chat interface starter template with tool calling, streaming, and multi-provider support

Scalable and extensible reinforcement learning for LM agents.

Minimal and educational implementation of an LLM agent.

Connect LLMs and AI agents to Auth0 Management APIs via an MCP server. Use natural-language commands to create apps, deploy Actions, and query logs—runs locally and supports interactive tenant authentication for secure Auth0 administration from AI tools/CLIs.

Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.

Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding (AIJ-22)

Open-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native scheduling

Zero-dependency JavaScript AI chat widget with SSE streaming, search, page context, accessibility, and theming.

TUI automation for AI agents. Control any terminal app from code.

DecisionBox connects to your data warehouse, runs autonomous AI agents that write and execute SQL, and surfaces validated insights and actionable recommendations — without you asking a single question.

A high-performance Android automation CLI, built for agents and humans

Ai Chatbot RTL Resolver

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

Multi-Agent AI Task Orchestrator 2026

Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.

Automate viral reel/tik-tok videos via AI multi-agent system. ~$0.1/reel.

Content Writing Agent. Simple & Extendable. Use with any model so your content doesn't sound like Claude.

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the open verification layer.

Agent Skill + Remotion pipeline: brief/script → review receipt → narrated 9:16 explainer. RC: video-explainer skill.

Turn a goal into a supervised run.

Coding Agent | ReAct Loop | Web UI | Mobile Supported

Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.

An autonomous agentic harness for Kubernetes. Proactive fleet audits, declarative GitOps remediation, and ChatOps in one place.

This Skills Exercise is about Agent Orchestration through the CLI

Turn vague product or feature ideas into clear, checkable requirements before planning or coding—mapping rough descriptions to professional terms, exposing ambiguities, and aligning goals, flows, and boundaries. 这是一个需求澄清 Skill：把说不清的想法整理成一份清晰、可核对的需求清单，在执行任务前对齐目标、流程与边界等。

CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs, escalation and verifiable evidence logs.

Local AI agent with a Go runtime and TypeScript terminal UI. Tools, memory, MCP, and multi-agent workflows.

A tool calling chat bot built with Jev and no LLM.

CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

An agentic workflow with a focus on reliability and developer experience