Custom agents

🔬 Agentic deep research application template on AWS

카카오톡 MCP 서버 — Claude Code에서 카카오톡 대화를 읽고, 보내고, 요약합니다

RootTron: Your Unrestricted AI Cybersecurity Assistant. Engineered to provide raw, high-fidelity answers to any security query, from complex exploit logic

LyraNote 是一款以 AI 为核心的研究笔记应用，面向知识工作者做“可检索的个人知识库 + AI 写作/研究助手”。

CLI tool for building production RAG systems from Markdown, CSV, and PDF documents using hybrid search (BM25 + vector) with OpenSearch. Features MCP server, Slack bot, Web UI, multi-source ingestion (local/S3/GitHub), and multi-provider embeddings (Bedrock/Gemini).

Stop your AI agent from generating Tailwind CSS v3 code. 20+ rules for v4 syntax, CSS-first config.

TypeScript SDK for self-custodial multi-chain wallets with MPC security, cross-chain swaps, and AI agent support. 40+ blockchains, no seed phrases.

Fleet AI Security Posture Management (AI-SPM): client agents on each developer machine score their AI coding agents' guard surfaces (Claude Code, Cursor, Codex, Gemini CLI — permissions, hooks, sandboxes, mcp.json) and ship hash-anchored events to a central server + your SIEM. Fleet-wide posture; measures, doesn't block. Rust.

Expose Codex through A2A with an inbound server surface and embedded outbound client.

The first Minecraft AI that doesn't just talk—it lives in your world. High-performance Gemini-driven cognitive companion for Fabric 1.21.1.

Agentic loops and AI agent capabilities for the Laravel AI SDK

Repositório com minhas skills para Claude, Claude Code, Antigravity, Gemini Spark, Manus, Perplexity, Agno, ADK, OpenClaw, Windsurf, Qwen Code e demais sistemas agênticos.

Intelligent FFMPEG agent node for ComfyUI - transforms natural language video editing prompts into automated video transformations

Code intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, smart context assembly - in single tool calls. 54 languages + PLC exports. 69.8% R@5 / 43.6% R@1 on dual-judge code-search eval. Daemon mode (3-19ms). MCP server, 30 read tools, full schemas. Local-first, GPU-accelerated.

Local message bus for Claude Code, Codex, and other MCP agents — one SQLite file, 20 tools, no daemon, no cloud.

AI agent skills library built by OpenSite AI. A single git repo that keeps Claude, Codex, Cursor, Copilot, and Perplexity Computer in perfect skill sync, with persistent cross-session memory and automated cloud upload via Playwright.

Open-source agent orchestration platform with stigmergic coordination, AOA heartbeats, dynamic model routing, and custom agent personas. Fork of Paperclip, used to build Ancilis.

CodeGraph MCP - Give persistent learning to your coding agent for a codebase across teams & token saving superpower to the coding agent

Convai Desktop Pet is a fun desktop companion app that brings animated chibi-style characters to life on your screen. These little friends don't just sit there — they walk around, climb your windows, fall with gravity, and best of all, you can have real conversations with them using AI!

A Python-based voice-controlled AI assistant for Windows using Google Gemini API, featuring speech recognition, text-to-speech, AI chat, and system automation.

Optimised BAAI/bge-m3 serving with dense + sparse + ColBERT embeddings, async dynamic batching and pipeline GPU inference

Static scanner for MCP-connected AI agent pipelines. 303 rules across 12 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.

Typed Kotlin DSL framework for AI agent systems.

Organised collection of resources for local AI agents - covering CLIs, tooling, and more.

A manual-first, human-in-the-loop workflow harness for AI-assisted development—aligns plans, approval gates, validation, and project state across Claude Code, Codex, Antigravity, and Cursor.

The issue tracker that lives in your repo. Built for AI agents. Works for humans.

Open-source engine for turning documentation sites into searchable, MCP-accessible context for humans and coding agents.

Agentic SQL & RAG engine (MCP server) for Oracle Fusion. Features local schema caching, semantic search, and real-time SQL execution for AI agents

Hermes Agent 中文增强包：一条命令安装中文补丁，支持 v0.14.x、v0.13.x 和 legacy 老版本。

agent-replay is a 100% local, SQLite-powered CLI tool for time-travel debugging AI agents that lets you replay execution traces, diff behavioral changes, fork runs to test fixes, and run AI-powered evaluations or safety guardrails to eliminate hallucinations and production failures.

Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.

Pi extension that turns one coding session into a multi-agent team with background RPC worker agents.

Agentic OS done right — create agents, chat, delegate work, stay safe. Self-hosted control plane with pluggable memory, guardrails, and execution.

Zouk - collaborative AI agent platform

An NLP-powered chatbot that processes user messages using rule-based responses and AI-generated replies via Hugging Face's Transformers.

The measurement layer for machine minds. Reads what a model means and whether it holds the truth; certifies every claim re-runs. meaning_diff + OATH certify + mind profiles + live grounding signal + the cognometric instruments. No torch, no LLM in the loop for the core; MIT, open at the core.

Equip your AI agent with professional Modern Android Development patterns. Optimized for high-throughput coding with Antigravity, Cursor, Windsurf, and more.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

A universal Agent Skill for deep, multi-source learning across 18+ AI coding agents

Meshy: The leading AI 3D Content Generator. This serves as a central hub for Meshy tutorials, workflows, and best practices.

A Go framework for the microagents architecture with dynamic discovery — specialized agents and tools that register their capabilities with a shared registry, find each other by logical name at runtime, and coordinate without a central conductor.

A curated list of principles and technologies related to Agentic AI systems.

backlog: Your AI agent forgets between sessions. Backlog remembers.

A Codex skill that turns 'do everything' into safe scope, defaults, memory, and AI observability.

Connect agents across runtimes, frameworks, and teams.

Amin's Smart Telegram Bot — An intelligent automation assistant integrating AI, Docker, WSL2, and n8n into a unified Telegram interface. Enables real-time email management, Google Drive access, Python execution, and multi-model AI interaction through a secure, containerized workflow.

Claude Code skill: turn raw requirements, engineering PRDs (incl. Feishu docs), or competitor analysis into a concise, coding-agent-ready PRD for vibe coding

The next-generation software-first operating harness for AI agents.

AI agent orchestration plugin bringing LazyCodex-style skills, hooks, and maintainer workflows to Google Antigravity/Gemini CLI.

Multi-agent AI platform for biomedical & genomic research — query PubMed, ClinVar, Ensembl, UniProt and 10+ scientific databases with natural language.

[ICML2026] The official code of "Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale"

How I scored top 10 on Optimization Arena negotiation + prediction market challenges by reverse-engineering the leaderboard via the public API

Bitcoin wallet with account management, Lightning integration through different providers and smart contracts for asset issuance

0.1MB macOS system tools for AI Agents. Native Apple frameworks. AI friendly with JSON/YAML output. Minimal context with maximum flexibility.

MCP server for the Linux desktop 🐧🤖

Watercooler: your team's shared reasoning layer for agentic coding. Preserve the "why" around your code.

Automated auditing pipeline for LLM and agent benchmarks — surfaces task ambiguity, environment conflicts, and evaluation bugs.

Native macOS control panel for Flutter — for editors (Zed/Neovim/terminal) and agentic coding without a Flutter plugin

Customize and enhance the UX/UI of ChatGPT and Gemini via user scripts. / ChatGPT・GeminiのUX/UIをカスタマイズするユーザースクリプト集

Project of Saonumi in FPT University

An opinionated framework for deploying a fully self-hosted AI chatbot interface with integrated document processing, document search, and web search.

Official Roadmap for Catalyst – Track upcoming features, improvements, and releases. Submit feature requests and help shape the future of Catalyst

Botkit(Web-bot) is an open source developer tool for building chat bots, apps and custom integrations for major messaging platforms.

Full-stack GraphRAG application with Django backend and React frontend. Build knowledge graphs, detect communities, and chat with documents using hybrid retrieval and LLM-powered reasoning.

your glass-box company brain — tells you what it doesn't know (deterministic gap analysis). MIT core · MCP · PGLite→Postgres.

The data layer for AI with Vector, Graph and Vector-Math built into one single rust engine

Portable Ethereum identity for your AI agent. Its soul, memory, and skills live onchain via ERC-8004 + IPFS and snap back into any session.

QuickerAgent: AI desktop assistant for Quicker. Monorepo with QuickerRpc plugin + qkrpc CLI — headless action create/edit/run via MCP, HTTP, or JSON CLI (StreamJsonRpc named pipe).

2026 美团 AI Hackathon / 美团 AI 黑客松 作品「饿了幺」：面向吃饭、多人约饭、周末规划的 AI 本地生活管家 / AI local-life butler

AI-powered novel writing system with dual-system support (male/female-oriented), framework agents, and multi-dimensional quality evaluation.

.NET Framework to enable the easy creation of production ready AI Applications

Agent-ready CLI for static page inspection, search triage, and browser handoff.

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.

Precision-aware retrieval benchmark for LLM memory systems.

Fast headless browser and native app automation CLI for AI coding agents — persistent Chromium via Playwright, camoufox stealth runtime, session multiplexing, MCP server, and Android/iOS/macOS app automation.

Zero-human full-stack deployment as a bundle of /sc-* Claude Code slash commands — GitHub + Convex (self-hosted & Cloud) + Dokploy + Vercel + Hostinger DNS, source to verified live URL. Node ≥18, no runtime dependencies. 8 skills implemented, 5 stubs.

MindWiki — 10 顶级专家组团的决策追问系统 Skills（张小龙、乔布斯、马斯克、张一鸣、芒格、王兴、雷军、梁宁、Naval、毛泽东）。带工具调用和自我验证测试。

Claude Code plugin that makes coding agents measurably cheaper over time: collect token costs, distill candidate rules, benchmark them on a frozen golden suite, and keep only rules that earn their context rent.

Open re-implementation of Claude Code's built-in Dynamic Workflow: a script-driven runner for agent-authored JavaScript workflows — agent(), parallel(), pipeline(), token budgets, git-worktree isolation, deterministic resume — plus pandacode, a pluggable executor for codex, claude, and domestic LLMs. Auto offline HTML execution-graph reports.

Zero-hallucination reference verification for Claude Code — live CrossRef/S2/PubMed verification, verbatim abstract traceability, retraction check

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve brownfield; learn from failures; re-verify until closure.

Eliminates generic AI slop and enforces premium UI/UX design via 10 sequential gates, ratio-based layout/composition audits, and open-design craft integration.

A calm command centre for a founder who works with more than one AI tool. Eleven rooms, agents as colleagues, honest data. Point your agent at this repo and build your own.

SkillBill packages your engineering judgment into governed skills, then uses a durable Kotlin runtime to ensure agents actually execute that process consistently, resumably, and with bounded context.

The chunking benchmark

a rag-based wiki skill with obsidian just like karpathy-llm-wiki

[ICML 2026] Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation

Kata builds the best AI agent for a subnet through open competition — so anyone can mine that subnet with a proven, optimized agent.

AI-assisted reverse engineering orchestration platform for IDA Pro and x64dbg with live synchronization and MCP agent workflows.

Bilingual hands-on roadmap for production-aware AI agents: MCP, memory, RAG, workflows, evaluation, safety, and agent colonies.

PreAct: Computer-Using Agents that Get Faster on Repeated Tasks (arXiv:2606.17929). Compile successful runs into verified state-machine programs and replay them 8.5–13× faster with no per-step LLM calls.

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

Universal AI Agent skill for downloading videos from YouTube/Bilibili/Douyin/Xiaohongshu/Kuaishou/Weibo/Twitter/Vimeo/TikTok. Works with Codex, Claude Code, Cursor, Cline.

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source LLM (Qwen2.5-Coder) on vLLM, with AddressSanitizer as a ground-truth oracle.

Detent is board-driven agentic work orchestration, shipped as a single Go binary — it watches a GitHub Projects board and runs each ready issue through an isolated Git worktree, a coding agent, your validation gate, and a serialized merge train, live on web and terminal dashboards.

An Always-On Autonomous AI Software Engineering Team built with LangGraph, FastAPI, and Next.js that operates natively within your GitHub repositories.

The open-source alternative to Ironclad + Harvey. Self-hosted, AI-native contract lifecycle management — your contracts never leave your servers.

A comprehensive Android staff management application featuring role-based access control (RBAC), real-time chat, and a RAG-based AI assistant powered by Gemini API.

生产级通用 Text-to-SQL 服务：基于 FastAPI + LangGraph + RAG，将自然语言转换为安全可执行的 SQL，内置 SQL Guard、few-shot/schema 检索、限流、缓存、Langfuse 追踪、Prometheus/Grafana 监控，并基于 CSpider 做准确率评测。

VERA — Virtual Engine Reasoning Agent: an AI co-pilot inside the Unreal Editor. Multi-provider, plugin-based, free & local.