Custom agents

A governance harness for AI-assisted software delivery. You govern. Agents deliver.

Convert .docx to Markdown or semantic HTML — no external dependencies.

BuyWhere MCP server — search 300M+ products across US, Singapore & SEA via Model Context Protocol. Agents self-register a free key in one POST (no email): api.buywhere.ai/v1/auth/register?verify=false

The open-source alternative to Suno and ElevenLabs Music. Natural language music composition, run locally, own everything.

A user-friendly chat-based LLM assisted security research, pen test, and training suite. all-in-one.

she - scriptable smart home automation engine with AI assistance

Beast Agent is a TUI to an agent, much like Pi or Claude Code. But compiled. Containerized. Multi-model. Agentic. Perfect for long-horizon tasks.

Framework for orchestrating autonomous AI agents. LLMLight is lightweight, with many build-in options to tackling complex tasks.

Training-free agentic framework for analog circuit design automation: an LLM multi-agent system with self-evolving memory. KDD 2026 (AI4Science, Oral).

Vant: Versatile Autonomous Networked Tool - Durable agent OS + memory + cold storage + runtime, with generational evolution, stored with version control. Built for long-running autonomous sessions, using git based persistence.

Shared Python libraries that Foundry-built agents install and extend — core protocols & DI, config loading, FastAPI HTTP layer, and AWS Strands SDK adapter. Packaged as a uv workspace; each library is independently versioned and ships as a wheel on GitHub Releases.

可复用的 OpenClaw、Codex 与 AI Agent Skill 工具箱，附安装、验证和发布工作流

A skill for AI agents. A virtual beer and wine sommelier that learns your tastes and suggests the best choice.

Coding agent harness, achieved SWE Bench Lite resolve rate of 52.4%

European Parliament Political Intelligence Platform - Radical transparency - Democratic accountability - AI-generated news in 14 languages

Your own voice + text AI assistant, embedded with one script tag, running 100% in the visitor's browser.

AI API service to enable your apps with powerful AI models for free. (Deprecated Sorry, its not me its Google lol !)

AI context engine for Power BI models — turns .pbit/.pbip (TMDL) into indexed, queryable context for LLM agents (MCP server, CLI, docs). Zero dependencies.

Codex Skill for choosing and coordinating the smallest safe Agent setup.

A powerful and versatile AI-powered PBX for Asterisk, WhatsApp, Telegram, with text and audio support, built on Tibula.

Reactive chat bot framework

Claude Code의 영구 기억 시스템 — 4-layer 파이프라인 (세션 검색 + 메모리 회수 + Memory Compiler). Karpathy LLM-as-Compiler 패턴 실증판.

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-gated shell command execution, scoped to a single workspace root. Local-first, no cloud dependency, full audit logging. Built in TypeScript.

Your own AI super agent, ready to work for you with a powerful built-in model you can use for free.

Many-agent, quality-calibrated orchestrator for Claude Code and Kimi Code with 115 vendored official skill packages — a first-class agentic backbone (live ContextGraph, explicit state machine, forward-only rollback) over a deterministic 6-lens verification harness with pure pass/fail gates and human-gated output. No LLM ever computes pass/fail.

GoalOS AGIALPHA Ascension — Sovereign Machine Economy: proof-settled autonomous AI work, Evidence Dockets, validator-gated jobs, governed decision states, and reusable capability packages.

An AI client for MSX2 machines with a RAM Mapper and a UNAPI TCPIP device.

tool-eval-bench results for Prism ML Ternary-Bonsai-27B (Q2_0) — 8 trials, score 85, deployability 80

Run, fine-tune and serve real LLMs entirely in-process in .NET — on the CPU, on-device, offline. No Python, no GPU, no cloud.

Local-first memory engine for AI agents

Local multimodal RAG for PDFs: MinerU, embeddinggemma-2, FAISS, BM25, BGE reranking and Ollama. Runs on your hardware via web and desktop; summaries, outlines and quizzes of any document.

Codex-native TradingAgents-style multi-agent financial research plugin with no external LLM API keys

Agent Markup Language - an asynchronous TypeScript and JSX runtime for composing provider-agnostic agent workflows.

A free, open-source loop engineering curriculum: 14 steps, 20 loop kits, graded labs, and Loop Ready certification.

Python SDK for Lighton API, the 🇪🇺 European industrial-grade retrieval infrastructure powered by its frontier retrieval models developed in-house

OpenCode — an open-source, community-built VS Code client for the opencode CLI agent. Multi-tab AI chat, side-by-side diffs, checkpoints, cost tracking, and 75+ providers. Free (pay only your AI provider).

NOVA AgentOS — 本地优先、证据优先、用户可控的桌面 AI Agent。把目标转化为真实文件、测试与可追溯交付。

Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Open-source client SDKs (Python/TypeScript/Go), CLI, API docs, and prebuilt binaries for Mnemovela. Apache-2.0.

Run a flock of AI coding agents, each in its own git worktree, started by your ticket queue, merged by you. Work assigned to you in Jira, Linear, GitHub Issues, Shortcut or Asana becomes a seeded, already-running session; you review the diff and click it home.

Google Cloud Cortex Framework v7 provides solution accelerators that help you build trusted, high-quality data products ready for advanced analytics and agentic use cases. The framework uses Google Cloud's products including BigQuery, Dataform, Knowledge Catalog, and Gemini Enterprise Agent Platform.

LLMForge is probably the most modern AI vulnerability lab for OWASP VulnerableApp — real-LLM-backed labs for prompt injection, LLM-orchestrated BOLA, and RAG attacks.

基于langgrahp的多智能体协作小说生成框架，四个专职AI智能体接力完成从创意到成稿的全流程。

多 Agent 协作平台 — supervisor 调度、@ 直连成员、Agentic RAG、Skill 沙箱产出物

Pi extension for parallel panel review and judge synthesis

Official implementation of "Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning" (CVPR 2026)

The `npx serve` of Android Emulators

Collaborative travel planning SaaS — plan itineraries on a map, vote on stops, and split expenses fairly.

Your AI agent, fluent in Australian tax.

JiuZhang · ALGOR — a local multi-agent quant research terminal for A-share investors. 多智能体量化投研平台。

🎬 AI plans your shot list like a director, then generates the film. LLM storyboard planning + cross-shot character consistency + multi-provider video/image/TTS (Doubao Seedance, Pexels, Piper). From a 30s sci-fi short to a 2-min animated fable.

Orchestrator, reusable multi-agent workflows and observable, attachable sub-agents for the Pi coding agent.

Everyone deserves a chief of staff - your personal jarvis | not a chatbot. not another ai agent. | beta

Source code for "Terminal Agents Suffice for Enterprise Automation"

Pure-Rust port of CerebroCortex — brain-analogous AI memory system with ACT-R/FSRS activation, associative networks, 8-phase dream engine, and MCP-over-stdio. Drop-in replacement for the Python version, Pi-native, zero Python runtime.

EverLingo is an AI language companion that helps you learn in context and remember what you learn. It captures meaningful moments as you explore words, sentences, and ideas, turning them into useful notes. Later, EverLingo recalls those notes when relevant, making your learning more personal, connected, and effective.

Local CLI for auditing AI agent skills, conflicts, duplicates, safety risks, and context cost across coding agents.

Tells parallel AI coding agents when their in-flight work would break each other — before either lands. Catches the case git merges cleanly.

yogsgehlot/Chatbot-Song-Recommender-System

OpenWand - A LLM chat interface optimized for AI co-work for your desktop. Press a key, pick an intent, and OpenWand reads the right context, then streams an answer without making you leave what you're doing. Local-first, voice in/out, bring your own model provider.

铁锈战争单机 LLM 指挥链：javaagent 实时取数 + Python 分层多 agent 决策（纯单机研究项目，严禁用于多人对战）（后期架构大改变，现阶段有些狗屎）

Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git commits and diffs, and project docs into a local SQLite database, and serves back a token-budgeted slice on demand. No cloud, no account.

Open Reasoning & Computing Agent for Windows: coding, everyday work, local AI, and Computer Use.

Open-source agentic SDLC harness for structured requirements and application design with Codex, AI-DLC, independent review, Product Design, and human approval gates.

JMComic3 APK 逆向修改 AI Skill：自动化去除广告、移除游戏电影板块。一份面向 LLM 的结构化知识文档。

SGME 拾光记忆引擎：AI 全面接管记忆、技能库、WIKI 知识库三大模块，跨会话、多智能体共享记忆，AI 会一直记得你的偏好。ShiGuang Memory Engine · AI takes full charge of three core modules — memory, skills, and wiki knowledge base. Memory is shared across sessions and multiple agents, so your AI always remembers your preferences.

UniSearch 是一款基于 AI 的多平台公开内容采集与调研桌面工具。 通过自然语言描述调研目标，由 AI 自动规划任务流程，并发调度底层连接器进行公开数据采集与清洗。

A Graph-Based Adaptive Education System — Personalized tutoring that makes any LLM smarter about each specific learner

Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs.

长任务，不刷屏：关键进度清晰可见，完成后自动折叠，详情随时展开。 Long agent tasks, without transcript clutter: focused progress, auto-folded history, details on demand.

AI 原生人机协同研发操作系统的最小运行内核：以意图为方向，以约束为边界，以 Agent 为执行能力，以证据支持裁决，以遥测推动持续改进。

Rel.AI MCP - a local coding agent for ChatGPT Web. Let ChatGPT read and edit repositories, run commands and tests, review changes, and use Git through MCP.

Evidence-assisted Yu-Gi-Oh! rulings for OCG and TCG, with card-text checks and cited sources. TCG public preview.

Automate video, note, product-link and scheduled publishing across social media and e-commerce platforms.

Local session transcript memory for Claude Code and Codex — search past sessions with FTS5 + semantic vectors.

Hosted Instagram MCP server from HasData. Public profile and post-feed tools by handle, structured JSON, for Claude, Cursor and any MCP client.

Distribute and safely manage a cross-host personal harness and durable work state.

Agent-first pipeline from raw drone footage to a finished film: OpenCV motion analysis, shot selection, pacing, crossfade montage, color grading, AI music and YouTube publishing assets. Built for Claude Code, works as a plain CLI too.

针对 [`deepseek-harness`](https://github.com/deepseek-ai/deepseek-harness) 仓库的交互式学习地图：架构分层、依赖脉络、核心流程、模块深读（含**关键源码片段**）、**双源文档库**（官方文档中文优先 + Claude 解读文档）、源码浏览。

Azimuth — multi-venue concentrated-liquidity LP bot. Automated pool screening, entry and exit for Meteora DLMM on Solana and Uniswap v3/v4 on Robinhood Chain.

Run Claude Code, Codex and Gemini side by side — and let them hand work to each other. Portable Windows terminal for AI CLIs.

🤝 Symbio Basic — A symbiotic AI agent desktop companion. screen vision, sandboxed file tools, and support for Hermes Agent & Local LLMs.

网友红领巾的公考决策、复盘、选岗与来源核验 Codex Skill

A hands-on guide to building, orchestrating, and maintaining multi-agent workflows in Microsoft Foundry.

A local, open-source capability gateway for AI agents — one AI-native self-describe endpoint so any agent can discover, understand, be granted, and call the software on your machine, under a trust model you can see, scope, and revoke.

Hermes Herald — dispatch tasks across Hermes profiles with fail-closed model routing, SSE auto-delivery, approval relay, and per-call subagent model selection.

A framework that enables humans and AI agents to collaborate effectively on complex workflows.

⚡ TidyFactor Architecture Ecosystem , AI-Native Web Architecture, Design Systems & Agent Skills .

Lossless context folding for the Pi coding agent: only the oldest context changes; the fresh window stays untouched.

Local-first Agentic RAG engine - GraphRAG, hybrid retrieval (BM25 + dense + RRF + rerank), multi-agent orchestration, MCP-native, 100% local inference via Ollama.

An agentic coding CLI. It reads your code, edits it, runs your tests, and asks when the request is ambiguous — in a terminal UI, with every mutating action gated behind an approval prompt.

Agentic Latex for Researching, Editing & Drafting

The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated floor, mail, task board, chat with the boss.

ClawCall：面向 OpenClaw 的 AI 外呼、智能外呼与电话机器人 Skill，支持中文通话、呼入接待、转写和通话记录；执行时支持中国大陆手机号。

Multi-agent CLI to install, update, repair, and remove Agent Plugins 1.0 and Agent Skills 1.0 across Codex/ChatGPT, Claude, Cursor, Gemini, Copilot, Qoder, Pi, OpenCode, and more. 1,500+ plugins. SDK for universal plugins (hooks, detect, install/manage)

AI Skill that auto-generates tutorials from any URL — screenshots, steps, video with TTS narration. Works with Claude Code, Hermes, Gemini CLI, Codex, OpenClaw.

A high-performance, zero-trust AI agent in Rust. Single binary featuring CLI assistant, Concourse CI, collaborative Markdown MCP hub with built-in AI chat, and browser extension.

Android 悬浮窗 AI 聊天助手：帮你想下一句怎么说，不代聊、不代发。

Persistent, quality-gated, resource-aware execution plans for DeepSeek Harness agents