Custom agents

A phase-aware operating system for coding agents that helps them explore, ship, harden, and verify without losing the plot.

Ngent wraps command-line agents that speak the Agent Client Protocol (ACP) into a web service, making them accessible via HTTP API and Web UI.

Interact with your instance of AnythingLLM from the terminal.

Super Publisher 是一个专为 Agent 设计的插件，旨在实现自动化的多平台内容发布。

A self-evolving memory layer for LLMs.

A Claude Code operating system for running a structured agency team. 25 specialized roles across four councils (Creative, Technical, Hardware, Delivery), enforced quality gates, PM-driven workflow, multi-client workspace governance, and per-project sprint tracking.

Per-task isolated worktrees for parallel Apple development with AI agents. Run multiple Claude / Codex / Copilot / Cursor sessions on the same Xcode project without build.db locks, DerivedData thrash, or simulator collisions.

AI agent security harness, adversarial testing: 649 executable tests in the v4.28.2 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Four target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 crosswalk (2026-10-15), NIST AI 800-2.

🦞 ClawBox — Your private AI assistant on NVIDIA Jetson. Setup wizard, dashboard, and 580+ skills. Plug in, scan QR, done.

Model Context Protocol (MCP) server for Amazon Seller Central - Access sales data, inventory, returns, and reports through the Amazon SP-API

122 AI Agent Skills for full-lifecycle product development (PM × UI × Backend) | 覆盖产品全生命周期的122个AI Agent技能，从探索发现到增长运营，覆盖产品×设计×后端三大领域

ZulipChat MCP Server - A Model Context Protocol server that bridges AI agents with Zulip Chat. Built with FastMCP for lightning-fast performance, featuring comprehensive chat management and intelligent summarization. Transform your Zulip workspace into an AI-powered collaboration hub!

Loop-Driven Development with OpenCode

Black-box web penetration testing automation framework for AI Agents

🏛️ Belief Archaeology - An AI Agent skill that excavates hidden worldviews from YouTube videos instead of summarizing them. For Antigravity / Gemini CLI.

Headless agent orchestrator with deterministic state machine — processes a bead queue, dispatches to any LLM CLI, handles every outcome. Rust.

Superpowers & Beads task memory for AI coding agents - supports Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Kimi Code, Antigravity, Factory Droid, and Pi.

自进化量化选股系统 — Kronos K线预测模型 + Hermes Agent 自进化闭环 + A股三池漏斗选股

Agentic AI plugin that transforms a dashboard request into a Tableau specification — with interactive HTML mock, implementation blueprint, and experimental .twbx generation. Works with Claude Code, Cursor, and other AI coding tools

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

The infrastructure for the AI economy: primitives for inference, agents, and decisions.

为 DeepSeek 前缀缓存定制的终端 Code Agent（纯 Go），缓存命中率 95-99%，输入成本降至 1/50。A terminal coding agent optimized for DeepSeek prefix caching — 95-99% cache hit, 1/50th the cost.

The financial operating system for AI agents. A single HTTP client that intercepts '402 Payment Required', routes across x402, L402, and MPP, persists credentials as recoverable assets, enforces per-envelope budgets, and emits a structured trace.

Local-model-first AI agent framework — Router + Specialist architecture for Ollama

Open APA (Open Agentic Process Automation) is built on top of our first-place performance in the OSWorld Benchmark. It provides a practical and extensible framework for building computer use agents that can reliably execute long-horizon, real-world tasks across applications, interfaces, and workflows.

Conversational black-box reverse-engineering agent on the pi coding agent — analyzes apk/.o/.hex/exe with a self-provisioning toolchain (radare2 · Ghidra · angr · jadx). Static analysis. Claude Code & Codex compatible.

A private, offline 'second brain' for the people, projects, and decisions you juggle — and it keeps score of whether your judgment was right. 本地私密的人际情报与决策记忆系统。

Agent Library personal knowledge base with a search and retrieval system MCP Server and CLI. Preconfigured local models and support for Text, images, OCR/vision, and code embeddings. Use over MCP with (Claude, Cursor, Codex, ChatGPT, etc)

md2video is a small agent-friendly workflow for turning source content into a narrated slide video.

MCP server: Project PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.

QevosAgent is a minimalist agent runtime for real tool-calling workflows with persistent artifacts, recoverable memory, and observable execution.

A reinforcement learning framework with verifiable aesthetic rewards for improving aesthetic slide generation capabilities in LLM agents.

打破Claude对中国的歧视，做一个对接N个CLAW，并且实现多AGENT的可视化操作工具！

A toolkit for systematically checking proofs in statistics and ML-theory paper appendices using coding agents. Includes severity framework, phased parallel execution, auto-planning prompt, and a complete worked tutorial.

OpenClawMU — Multi-Tenant Fork of OpenClaw

An open-source agent workflow engine & meta-harness: orchestrates Claude, Codex, and Pi to run multi-step work as a folder-as-agent pipeline. Its flagship coding workflow turns a rough idea into a merge-ready PR; ships content too, and runs the workflows you author.

AEO tracking toolkit (CLI + dashboard) built for AI agents like Claude Code, Cowork, Codex, OpenClaw, Gooseworks

A rich web UI layer for AI agent interactions — human-in-the-loop, click-to-edit, preference learning. Built for Claude Code, CodeX and OpenClaw.

Mobile-native agent SDK for building on-device AI agents with sandboxed execution, extensible tools, and x-app / x-agent / x-channel connectivity.

Autonomous AI experiment loop CLI -- run research overnight with any coding agent

Guardian Agent and Token Savings for Claude Code

LoopCraft runtime harness plugin for Hermes with evidence-first execution, verification-first workflows, and self-correcting AI agent behavior. Installs as proofrail for compatibility.

Run Pi coding agent isolated in a Docker Sandbox microVM with a local llama-server as the inference backend

Port of pi-mono to Python; AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pod.

On-device AI SDK powering ToolNeuron — LLM chat & tool calling (llama.cpp), Stable Diffusion image generation (QNN/MNN), image processing (upscale, segment, inpaint, depth, style), and TTS. Native C++ + Kotlin JNI. Fork or clone to use in your own app.

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

Reina 桌面 AI Agent 发行仓库（仅安装包） | Release distribution for the Reina desktop AI agent — installers only. Windows x64 & macOS arm64, in-app auto-update.

A knowledge graph your AI agents build, query, and grow. Built for agents that need structure beyond vectors

申根签证 AI Agent 技能 — 按身份定制清单、跨会话记忆，带你跑完办签全流程

微博群聊消息自动归档 · 原生桌面应用（应用内扫码登录）+ 本地可视化查看器，含 AI 每日摘要与 Agentic 问答

Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.

Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.

Semantic F# for AI coding agents (Claude Code · Cursor · Copilot · Codex) — an MCP server that gives LLMs real FCS/FSAC compiler intelligence (find, check, types, rename) instead of grepping F#.

On-Device Mobile Agent: Control your phone directly with Vision Language Models, untethered from any PC. 手机直接调用视觉大模型 ，无需连接电脑，让 AI 直接操作你的手机！

Aurict is an open-source terminal AI coding agent built for real developer workflows: sandboxed tools, subagents, multi-provider LLMs, patch safety, and fast CLI UX.

AI-powered multi-agent classroom that turns any topic into an interactive learning experience

Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

面向中文食谱问答的端到端 RAG 工程实践，覆盖数据清洗与索引构建、混合检索、多轮状态管理、结构化生成，以及基于真实大模型服务的 Live E2E 测评闭环。

An AI-powered B2B lead generation system. Private preview available

SOTA communication-efficient, fast, and robust map merging using 3D point cloud (@ IJRR'26)

An autonomous AI agent for recruitment workflow automation.

a control tower for your Claude agents

Evidence-centered academic literature workflow for topic definition, search, PDF download routing, Zotero management, paper writing, citation audit, and polishing. 面向中文/双语论文写作的证据闭环工作流。

Local-first multi-agent market research desktop workspace built with Tauri, Next.js, and an embedded TradingAgents-compatible core.

Ecommerce Agent 是一个基于大语言模型的垂直电商客服智能助手系统，专门针对电商客服场景进行深度优化。项目通过 LoRA 微调、DPO 对齐和 ReAct 推理框架，构建了一个能够理解复杂业务逻辑、合规调用工具、并提供专业客服服务的智能助手。

Mi-Memory: A Composable, Evolvable, and Multi-Source Memory System for Daily Assistant Agents

CORTEX is an AI Agent framework designed for efficient integration and utilization of large language models (LLMs), built in Go.

用 I-Lang 判断层做 Google AdSense 过审审核:每条判定输出可解释的判断向量,而非一个模糊的标签;完整性由代码强制,漏检即报错。

agentic AI coding assistant supporting claude code, ChatGPT codex, Antigravity, OpenCode and Pi coding agent; with API provider OpenRouter Gemini DeepSeek

Inglen (formerly Hearth). One AI workspace instead of a stack of AI tools: your models, agents, tools and computer in one app.

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human approval, execute-once gateway, tamper-evident receipts. Open core, Apache-2.0.

Cortex: local, evidence-backed repository map of code AND documents — find what is true, stale, contradictory, or unknown before changing a system. Neurons/Synapses/Circuits.

Agentic game development for building games with AI Agents. Run one session per seat: art, gameplay, narrative, QA, audio, tech all in 1 spot

Agent-powered iterative optimization: put an AI agent in a verified improvement loop.

One project. Multiple AI agents. Zero repeated work.

hold your voice helps writers keep their voice when they work with ai.

A personal AI operating system for knowledge workers. Carries your context, reaches your real tools, runs your SOPs, and learns from every correction.

GraphRAG Agent 是一个面向私有知识库的全栈图谱问答系统。它将文档上传、文本解析、分块、知识图谱抽取、索引任务编排、可视化编辑和问答记录整合在一个受认证保护的工作流中，并为多用户场景提供用户自带 API Key（BYOK）能力。

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

纯本地化桌面 AI 智能体平台。Go + TypeScript + C/C++ 全栈，集成多模态对话、文生图、语音识别与合成，零 Python / 零云端依赖，全部推理本地完成。

Zerolinear — AI research lab and home of the Zeline open-source agentic AI framework.

API-first social platform for AI agents — wallet-native identity, API-only posting, and a written threat model for agent-to-agent prompt injection.

The authority plane for local AI agents: a governed, self-hosted agent built so a 7–30B model on your own GPU can drive it. Measured in public.

Plugin marketplace for DeepSeek Harness — live-syncs the GitHub dsh-plugin topic into a searchable, paginated settings tab with one-click install and agent tools (market_search / market_install).

DURU — 두루 돕는 AI · 내 PC에 설치해 내 문서를 근거로 답하는 AI 에이전트. 망분리 환경 동작, 지식베이스·에이전트를 암호화한 파일로 공유. An on-premise AI agent that answers from your own documents.

Undo for AI agent shell commands. Snapshots files before Claude Code runs destructive bash (rm -rf, git reset, rsync), so agent mistakes are reversible, even for files git never tracked.

Maintained open-source developer cheat sheets for AI, Linux, Git, Python, Docker, Kubernetes, security, and more — plus 31 offline PDFs.

All you need is one API to let AI assist you in music creation—modify MIDI files, get suggestions, and more. No complex setup, just plug and play!

Python desktop AI assistant for screen awareness, voice interaction, persistent memory, and computer automation

这是一个ai infra、关于LLM的一切的的obsidian知识库 可以配合agent使用 持续更新中。

SSH MCP server: execute commands, transfer files, and forward ports on remote servers via MCP.

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

Symbio is a self fine tuning AI agent that gives power to users through seamless interaction with their machines. This flexible system adapts to commands, continually learning and evolving based on user input and allows it to learn emperical data.

New testbed of interactive SWE tasks for coding agents, set in a realistic multi-turn developer driven environment

Nausicaa treats an Agent run as a dynamic topology of Lanes rather than one fixed linear loop. The model can decide when to observe, fan out, delegate, or collaborate across Runs; the Host keeps identity, permissions, durability, and recovery as explicit facts.

RikkaHub Agent Promax - on-device Android LLM agent (local fork/upload)