Custom agents

A local-first, Pi-powered AI agent workspace for Desktop, WebUI, and CLI

A multimodal personal assistant that allows Large Language Models (LLMs) to run code locally, acting as an autonomous agent capable of completing and automating tasks via self-prompting

MCP Server for Bear note taking app available as Claude Desktop extension or standalone server for any other AI tool

Multi-agent equity research system with deterministic signal fusion — 3 specialized agents (ReAct, FinBERT, Plan-and-Solve + RAG) produce BUY/NEUTRAL/SELL decisions through a mathematical Decision Hub. No LLM in the critical path.

Antidote for fluffy specs, a toolkit for fact-driven development with AI agents

Skywork Agent Skills for AI office suites, including AI PPT, AI Document, AI Excel, AI Image, AI Search/DeepResearch and AI Music. These skills can be used by any skills-compatible agent, including Claude Code, Codex CLI and OpenClaw.

[COLM 2025] Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale

One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows.

Yuan (元) — a unified destiny-reading skill for Codex, Claude Code, and Agent Skills runtimes. One input surface, six methods (BaZi / Cheng Gu / Numerology / Western / Vedic / Zi Wei), production-grade output.

Agent-driven pipeline that turns raw material (PDFs, slides, syllabi, papers, URLs) into structured, teaching-quality Obsidian notes: ingest, compile, distribute.

OpenVibeCoding is the command tower for AI engineering: plan, delegate, track, resume, and prove long-running work across Codex and Claude Code.

High performance multithreaded task execution and optimization engine for agents and dweb apps

Authoritative, source-cited Claude Code plugin/skill that lets a coding agent autonomously build production-grade AI agents on AWS (Strands Agents, Amazon Bedrock, Bedrock AgentCore) with official best practices.

A menu bar app that keeps a written record of what you worked on.

⚡ Tell your PC what to do. Capri is a cyberpunk AI agent that works with your files, projects and code through Claude Code, Codex or Antigravity. Windows installer, no terminal. Fan-made, not affiliated with CD PROJEKT RED.

Your own Google TV home screen and phone remote, with an optional Claude assistant. Set it up by handing this repo to your AI agent.

AI-native cross-platform sandboxes for developers, featuring multimodal cloud runtime and expert agents.

Opsy - Your AI-Powered SRE Colleague

FruityC2 is a post-exploitation (and open source) framework based on the deployment of agents on compromised machines. Agents are managed from a web interface under the control of an operator.

A model-agnostic Ruby Generative AI DSL and framework. Provides base classes for building Generators, Actions, Tasks, and Agents that can be used to build AI powered applications in Ruby.

Clarvis - 3D Printing Made Easy

Convert an AI Agent into a A2A server! ✨

A practical roadmap for mastering LLM internals, training, inference, RAG, agents, evaluation, and production architecture.

Agentic Coding with Claude Code, published by Packt

Persistent memory extension for pi with daily logs, scratchpad, and optional qmd‑powered semantic search.

Black-box, open-source red-team testing for AI agents. Point it at any HTTP, gRPC, or browser-using agent endpoint; run 205 probes mapped to OWASP LLM Top 10 / MITRE ATLAS / NIST AI RMF, incl. payment and MCP tool-abuse families whose verdicts come from captured evidence, not LLM opinion. Reports state what was NOT tested. SARIF, CLI, GH Action.

Turn your computer into an AI agent workstation you can steer from your phone.

一个面向全网研究与复杂数据分析的云端智能体，能在公开网络、YouTube、BiliBili、X、小红书、Hacker News上研究任何主题 。项目wiki：https://zread.ai/OWWZO/ai-agent

88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemini CLI, and DeepSeek Harness.

Updated weekly — until humanity achieves AI4AI. 965 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.

🔮 Neuro.js is machine learning library for building AI assistants and chat-bots.

Self-hosted 3D virtual office for Hermes Agent — your profiles become AI employees who sit at desks, chat, hold meetings, work kanban cards and run cron jobs, while your team shares the office in real time.

🎨 Agentic skill for Qwen-Image-2.1: Rewrites and optimizes text-to-image and multi-image editing prompts using official Alibaba specifications. Compatible with skills.sh and all AI agents.

Design cognition loop for Codex, Claude Code, and Pi-compatible agents — frame, diverge, see, reframe

Drop in replacement for the OpenAI Assistants API

A GPT-J API to use with python3 to generate text, blogs, code, and more

🤖 Headless IDE for AI agents

A guided tour on how to use HuggingFace large language models on Macs with Apple Silicon

Implementation for the paper "ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems".

A MCP Server for a small scale engineering agents with multi-provider LLM support.

A Practical Course on Embeddings, RAG, Multimodal Models, and Agents with Amazon Nova.

Execution engine powering Flowbaker, a no code platform to build, connect, and automate workflows.

Repo containing my GitHub Copilot Agent & Skills - continually experimenting!

Hive compute for coding agent swarms - expand your personal compute by adding on-demand agentic swarms

Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.

Distributed Announce and Discovery of Multi-Agentic-Systems

The command center for Hermes Agent — chat, steer, browse files, manage skills, and monitor everything from a single glassmorphic HTML app.

X (Twitter) scraper API & X API alternative with REST, MCP, SDKs & webhooks. Not affiliated with X Corp.

Hand-drawn Excalidraw diagrams from natural language. 5 patterns, 8-color semantic palette, Kroki API or local CLI. PNG/SVG, multi-agent.

Your coding agent starts every session blank. Rekal is the memory your team is missing

A privacy-first AI agent that sanitizes your prompts locally with a local LLM before forwarding to remote LLM APIs.

Iron-Man-style voice assistant + holographic HUD for Hermes Agent. Local Whisper STT, ElevenLabs voice, agent-summoned media panels, runs on your own hardware.

Make Claude Code work like a disciplined engineer: OODA, multi-party adversarial review, tiered model routing, fail-then-pass — token-efficient by design (route heavy work to smaller models, isolate sub-agent context). Distilled from Fable to reinforce the Opus harness.

CI-native agent CLI tool for deterministic pipeline gating.

A smart AI telegram bot for searching and auto-saving.

孙学，零成本安装。孙宇晨两期访谈（邵艾伦、金明）的带时间戳全文，能动手的观点每个配一篇 AI 教程，工具都有国内能用的版本

研迹 Trail｜本地优先的 AI 投资研究工作台。连接行情、K 线与深度研究，让判断可追溯、风险可复核。Local-first AI investment research desktop with an evidence-grounded copilot.

Repository of instructions for Programming-specific GPT models

OpenVibeCoding is the command tower for AI engineering: plan, delegate, track, resume, and prove long-running work across Codex and Claude Code.

RAG orchestration framework ⛵️

Persistent runtime for long-running AI agent tasks with durable checkpoints, lease-based workers, retries, dead letters, and operational visibility

Unofficial Claude API supporting direct HTTP chat creation/deletion/retrieval, messages with multiple file attachments and auto session gathering using Firefox with geckodriver.

Terminal Live — monitor and chat with AI coding agents (Claude Code, Codex) from Telegram, Discord & Feishu

Manage / Proxy / Secure your MCP Servers

Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work

LLM agents for working with the SRA and associated bioinformatics databases.

[NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

The repository of VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework.

Run tested, autonomous agent workflows on your data for meaningful decision-making

Git-native memory for coding agents. Repo memory before the diff.

AgentSeek is an application development lifecycle toolkit for AI ecosystem apps, built by OceanBase OSS Team.

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

Curated collection of modular agent skills for LLM-based agents

ISO 24495 Plain Language skills and plugin

A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.

Idiomatic Go HTTP client for Max Bot API — zero dependencies, context support, structured errors

A simple and trans-platform agent framework and tutorial

Qiscus provide everything you need to power up your app with chats. And it's now made simple.

🔮 Neuro.js is machine learning library for building AI assistants and chat-bots.

A Node.js library for creating bots and sending/receiving messages using the Whatsapp Cloud API.

NLPGym - A toolkit to develop RL agents to solve NLP tasks.

Index the world's undocumented APIs

Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.

The Station is an open-world multi-agent environment where AI agents pursue autonomous scientific discovery and build a shared literature.

Distribb CLI, Claude, Codex, Hermes, OpenClaw skill for AI-powered SEO. Write content with your own AI, publish through Distribb's backlink network.

Python toolkit for PowerPoint ↔ HTML, built for AI. Round-trip fidelity preserves formatting across every edit loop — ideal for RAG ingestion, LLM agents, and AI-assisted slide editing.

A minimal, readable reference implementation of the Operational Ontology pattern. Palantir Foundry is one implementation; this is the concept, minimized.

Reusable AI coding workflows for Claude Code and VS Code to ship auth, billing, and landing pages faster.

多Agent兼容LLM智能网关与效率工具

Agent accuracy measurements for LLMs

Crowdsource EGO robot data capture, contribution, and public-safe edge-host bring-up.

AI powered cli coding agent that monitors your dev/test server and fixes errors and adds features

Launching the "Agent Creation Toolkit", providing developers with an intuitive and efficient Development Environment, supporting the rapid construction of intelligent agents. The toolkit will integrate RAG (Retrieval-Augmented Generation) Knowledge Base and LLMOps toolchain.

Persistent memory plugin for Claude Code. Tiered memory system with write gates, correction propagation, and slash commands.

Runtime for building and managing AI agents and Workflows. Easy to learn, fast to build, High Performance, Reliable by design, Intuitive UI, Production Ready.

ESAA-Security applies the ESAA architecture to automated security auditing. LLM-based agents execute a structured audit across 16 security domains, governed by the same immutable append-only event log, boundary contracts, and hash-verified projections that ESAA provides for software engineering workflows. Every finding, classification, and remediat

DarkGPT Chat Explorer is an interactive web application that allows users to engage in conversations with various GPT (Generative Pre-trained Transformer) models in real-time. This repository contains the source code for the application.

Compendium of over 50 benchmarks for evaluating AI agents, categorized into Function Calling & Tool Use, General Assistant & Reasoning, Coding & Software Engineering, and Computer Interaction.

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity