GitHub agents

Agent skills for Hyperliquid trading bot automation

MCP server, CLI, and web dashboard for Ren'Py visual-novel development — inspect, drive and debug a running game from an AI agent or the browser

A neuroscience-backed learning partner skill for AI coding agents. Retrieval, spacing, reflection, interleaving, and more — while you build software.

Build ATS Friendly Resume and Cover Letter

Pipeline RAG com LangChain JS, Neo4j e OpenRouter — projeto de portfólio

Multilingual NCERT doubt solver powered by an OPEA-based RAG pipeline, delivering curriculum-grounded, citation-backed answers in English, Hindi and Urdu with zero hallucinations.

A local-first memory layer for AI agents — turns the files on your machine into bounded, verifiable memory any assistant can query over MCP. On-device, no cloud.

agentic workspace for CAD

Code for paper "Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval"

Lean Agentic AI

Self-hosted, open-source personal AI assistant — streaming chat with agentic tools, long-term memory, RAG, tasks & reminders. Go + Vue 3 + PostgreSQL/pgvector. AGPL-3.0.

SUPER WhatsApp chatbot with a ton of features (reveal view once media, AI assistant, translate, remove background, mass delete msgs, download media, web scraping, create stickers, etc)

Personal knowledge system with persistent memory and domain routing for Claude Code

💬🤖 A smart medical chatbot app built with Flutter, Dialogflow, and Firebase — offering 👨‍⚕️ health-related conversations, 🤒 symptom guidance, and ⚡ real-time interaction with a friendly AI assistant.

ldm_AstrBot — AstrBot 二次修改/优化发行版（AGPL-3.0）

AI projects from the Teach-A-Intern program, including a chatbot, digit recognition, and image classification.

Bot de WhatsApp que conecta estudantes da UTFPR a vagas de estágio e emprego (vagas online via jobspy + vagas locais de empresas da região). Projeto de iniciação científica — Django, Celery, WAHA.

Low latency framework for realtime conversations.

🎙️ 本地播客/视频蒸馏工具：贴链接 → 转录·分章·摘要·五类亮点·双语字幕。Local-first (FastAPI + Vue)，可插拔多 LLM（DeepSeek / OpenAI / Claude / GLM / 通义 / 豆包 / Kimi）。

Use OpenAI Codex models in GitHub Copilot Chat with ChatGPT OAuth

Dr. Émile Telegram bot: AI emotional-support assistant with FastAPI backend, PostgreSQL, Redis, admin dashboard, and safety guardrails. Not a licensed mental health professional.

Template agents.md templates for use with OpenAI Codex

Personal finance tracker with AI-assisted categorization. Self-hostable Next.js + PostgreSQL + OpenAI.

remove ads from mp3 files

Open-source AI-powered B2B outreach system — lead scoring, personalized cold emails, reply tracking & auto follow-up. Built with N8N, OpenAI, GLM-4, and Google Places API.

一个基于 LLM 的 Bilibili 视频总结命令行工具。CLI tool to summarize Bilibili videos via subtitles or audio transcription using LLMs.

面向中文标书（MD）的混合抽取：规则/NER 优先，仅将低置信或冲突片段交给 LLM——可审计、低成本、高效率。Hybrid extraction for Chinese tender docs (MD): rules/NER first, LLM only for low-confidence/conflicts—auditable, lower cost, higher efficiency.

SkyPortal SDK & CLI - Open Source

AI-powered career assistant with XGBoost ML model (78.14% accuracy) trained on 6K+ resume-job pairs. Features advanced NLP skill extraction, GPT-4 resume enhancement, and intelligent job matching with real-time predictions.

An AI-powered Discord bot that chats, stores user memories, and can execute terminal commands on Windows directly through Discord.

Codex-Pro-Launcher is an external enhancement launcher for the Codex desktop application.

Agentic AI-powered security finding triage for DefectDojo

Turn a how-to video into a reusable skill for your AI coding agent — watched locally, no API keys.

A configurable status line for Claude Code - model, effort, workspace, and live context/rate-limit, claude usage monitor bars.

Skill de Claude que convierte un lead B2B en diagnóstico operativo: mapa de procesos AS-IS, backlog priorizado de app a medida y tres entregables sincronizados (chat, HTML interactivo y Word).

刘晓燕风格四六级/考研英语 Claude Skill · 骂醒式教学 · 含 2026.6 六级三套真题校准

BibleMate AI + UniqueBible Data (running on Google Antigravity / Claude Code / Grok Build) - An integrated local workspace combining robust scripture databases, modular study skills, and specialized AI personas to streamline biblical research and writing on the Google Antigravity platform.

Model Context Protocol (MCP) server for VK (VKontakte) social network API

Self-hosted, privacy-tiered memory for your AI agents.

Local-first Agentic RAG knowledge base with hybrid retrieval, ReAct agent, Vue UI, Ollama/DeepSeek/OpenAI, MCP and Docker.

🍋 Local-first memory middleware for your Markdown — turn your Obsidian vault into memory for any AI (MCP), with Korean-first hybrid retrieval, keyless on-device search, and an interactive knowledge graph.

A curated collection of open-source Large Language Model (LLM) projects that are production-ready and can be used for solving real-world problems. This repository focuses on high-performance, scalable LLM solutions across various industries and applications.

Long-term memory for AI agents in Ruby, recall relevant facts and inject them into the prompt, stored in your own Postgres.

Cyclomatic complexity, but for LLM prompts

Production-grade pentesting lab — Docker Compose tool isolation, AI agent orchestration, WireGuard OPSEC, LUKS encryption, automated PDF reports

本地优先的 Personal AI Learning Companion，把目标、个人知识、真实实践与可验证证据连接成一条可恢复的 Agent 执行链。

One desktop for all your AI coding agents — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer, terminal & editor. Local-first. Built with Tauri + Rust + Vue 3.

Graal Script Agent is a Java library for adding AI-authored extensions to applications.

Address any node in your Markdown. A structured read/write engine for Markdown documents.

68 installable Star Trek-inspired profile distributions for Hermes Agent

Chrome Side Panel companion for OpenAB — a multi-agent chatroom with in-browser control for agents via MCP-over-ACP.

Superseded by coding-agent-workflows. Twenty-one experimental multi-agent workflow skills for Claude Code: parallel research, brainstorming, debate, planning, execution, and review, with Beads for cross-session task tracking.

Vault-native MCP server for Obsidian: let Codex, Claude Code, Hermes, and other agents read, search, and safely manage your notes.

Turn a website URL into a premium, beat-locked product promo video with Remotion — original design system every time, music-onset-locked scenes, self-verifying renders, 16:9 + 9:16 + thumbnails.

Senior-level knowledge base: 60 cross-linked guides for designing beautiful, usable, accessible, high-converting websites — built for humans and AI agents.

The n8n alternative without the bugs — faster, more reliable workflow automation.

9 powerful automation skills for the Hermes Agent. Break your AI out of the text box by letting it control your real Chrome browser to bypass login walls, perform OSINT, automate job searches, and run deep web research autonomously.

Instagram CLI for AI agents. Meta Graph API + instagrapi private API. JSON output, policy routing.

An engine for persistent machine minds — deterministic cognition, portable identity (PMA), an LLM as one component (not the substrate).

Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.

**A fully local, privacy-first LLM desktop application powered by llama.cpp**

Opt-in Codex Skill for practical coding and externally anchored delivery with elastic agent teams, task DAGs, isolated candidates, and one canonical writer.

Just an AI assistant for termux users with coding assistant abilities

macOS 悬浮仪表盘：监控 OpenAI Codex 与 Claude Code 的订阅额度余额、Token 消耗与多设备趋势，支持 Touch Bar 常驻显示

Emacs integration for OpenAI Codex CLI

Monitora a cota das contas Claude Code e Codex CLI e troca de conta automaticamente antes de bater o limite. Python stdlib puro, sem dependencia, sem servidor.

Self-hosted Python job-search pipeline for H-1B & visa holders. You run it on your own laptop — no server, no sign-up, no data ever leaves your machine. Screens out visa-sponsorship dead ends automatically, AI only where it's actually needed.

Path of Exile MCP Suite

Automatic model+effort routing for Claude Code: tiered subagents, escalation ladder, independent verifier

Docker stack: Open WebUI + LiteLLM + admin console — chat UI, OpenAI-compatible API, and ops panel for local & cloud LLMs in ~60 seconds.

Postgres MCP Server

A semantic search and retrieval system for local documents using vector embeddings. Powered by MCP (Model Context Protocol).

Open-source physical dashboard for Codex on Stream Deck: monitor tasks, switch threads, control Effort/Fast mode, and dictate on macOS.

把多会话 AI 协作组织成可接班、可审核、低上下文的部门制团队 · Codex Skill

Local-first CLI, package contracts, and execution evidence for portable AI employees across Agent Hosts.

开源 Android 手机自动化 Agent：用自然语言驱动多模态大模型理解屏幕、规划任务并跨应用执行操作，支持可复用 Skills。

🏆 专为电赛(NUEDC)及天猛星/地猛星开发板(MSPM0G3507/G3519)打造的 TI MSPM0 AI 编程神器 / Agent Skill for Codex & Claude Code

Hands-free, two-way voice for your coding agent (Claude Code, Codex, Antigravity, Ollama) from your phone — free for noncommercial use, source-available, no ElevenLabs. Browser Web Speech + a tiny Node bridge over Tailscale HTTPS.

An agentic Orchestration Setup named after the Greek God of Creation. One Slash command, scans your project, or plan, sets up all the necessary agents + Workflows + MCP tools + claude.md + Documentation Structure. Can be reused to update everything within the project to maintain Proper Context

Starter files and safety gates for handing real, recurring work to an AI agent — from a one-person company where every employee is an AI. Watch it run live.

A local-first multi-agent harness. Every agent runs in an isolated, auditable runtime backed by one SQLite file — a flight recorder for your fleet. Its memory self-tunes with use (neuroplasticity). And it is the only framework whose own mechanisms must pass pre-registered, falsifiable kill gates before they ship. Measured, not claimed.

Open-source deep research agent: multi-agent web search, scraping, source-credibility scoring, and citation-backed reports with any LiteLLM model

Solweaver: a Codex software team with GPT-5.6 Sol orchestrating Terra and Luna workers.

Pi extension for parallel panel review and judge synthesis

Own the Outer Loop. Evidence → Verdict → Answerability. Governance layer for agentic engineering.

多功能 AstrBot 插件（CurrentCortex）—— Pixiv 随机图片 ·网易云点歌 ·JMComic 漫画 ·小红书/B站/抖音媒体解析 ·每日一言 ·天气 ·男娘 ·DG-LAB（郊狼） 设备管理 ·跨群聊记忆 ·按群聊开关。基于 LeiZ API。

Local coding-agent control plane — MCP action governance + LLM-path protection + cost control. One Rust binary, no SaaS.

A command deck for your own agent. Voice in, voice out, tools, memory and cron — on your own model, or as the face for a self-hosted Hermes Agent.

LJHskill 老家伙工具箱：内容电商打品的 14 个 Claude Code skill，俗称老家伙 skill。第一句说清你卡在哪，第二句它带你跑对的工具。

A self-hosted web frontend and SSH gateway for the official Codex app-server.

Run opencode (open-source AI coding agent) natively on Android via Termux. aarch64/Bionic build with a patched Bun runtime — one-command install.

An agent runtime designed for tool-driven loop engineering.

Installable graph engineering for Claude Code, Codex, OpenCode, Cursor, and OpenClaw — dependency-graph execution with local caching, quality gates, selective retries, and live reports

Multi-agent Gold (XAUUSD) analysis platform -- chart, correlations, market structure, sentiment, risk, volume agents with GLM-5 AI

AI for end-to-end hardware design workflows

Silico makes building maintainable firmware for embedded devices simple using AI.

A flow-driven AI coding agent runtime. Write agent workflows in the .at DSL — Turing-complete, inspectable, deterministic. The LLM is one node; atman orchestrates the rest.

Adobe InDesign MCP — 183 tools. Full InDesign DOM control from any AI agent. MCP-native, TypeScript, 31 handlers.

Study guide for all four Anthropic Claude certifications: Associate, Developer, and Architect Foundations and Professional. Official exam guides, blueprints with domain weights, cheat sheets, 320 practice questions, three mock exams per exam, 110 flashcards, and a printable companion.