Custom agents

AI 驱动的个人第二大脑 — 通过智能代理自动化任务、过滤高价值信息、以技术杠杆提升生产力

A general-purpose distributed agent cluster framework

A composable multi-agent AI framework for Go that makes it easy to build production-ready AI applications.

A2SPA — a security protocol enforcing cryptographic authorization at execution time for agentic AI systems.

List of AI tools that can interact with user interfaces

AI assisted SFC config creation, deployment and operation.

DNS, email-authentication, TLS and exposure scanning for AI agents: 81 MCP tools, scored 0–100. Source-available (BUSL-1.1).

Production-ready Python 3.13+ CLI/API system with Adaptive RAG, multi-engine TTS, OpenRouter key rotation, FastAPI backend, and Next.js dashboard

Run local LLMs powered up by tools in Telegram Messenger

AI Chatbot as a Service

Transform complex legal documents into clear, actionable insights with AI-powered analysis.

Benchmark 19 retrieval architectures (vector, contextual, QnA, knowledge graph, LightRAG, hybrid, RAPTOR, PageIndex, BM25, metadata-filtered, temporal, rerank, HyDE, multi-query, late-interaction, SPLADE, agentic, plus two quantum-inspired rerankers) on your own docs. Citable evidence bundles, bootstrap CIs, significance tests.

A personalized research intelligence platform that helps researchers discover, organize, and interact with academic papers & repositories. Features AI-powered chat (RAG), semantic search, document management, and automated trend analysis from 11+ sources.

SCARF (System for Comprehensive Assessment of RAG Frameworks) is a modular evaluation framework for benchmarking deployed Retrieval Augmented Generation (RAG) applications. It offers end-to-end, black-box assessment across multiple configurations, supports automated testing with several vector databases and LLMs.

A curated collection of Spring Boot projects demonstrating AI and LLM integrations, including examples of AI-powered applications, multi-provider LLM setups, and best practices for Spring AI, modular design, and integration testing.

A terminal based interactive agent for working with multi-turn llms

Golang RAG/LLM framework with Memory and Transcriber - All-in-One Platform

🕷️ Open-source web crawling toolkit — Video, OCR, NLP, Stealth, 10+ parsers

Cutting-edge tool designed to intelligently segment text documents into optimally-sized chunks

Local Codex MCP harness: contracts, persistent RAG memory, raw traces, verification records, governance policy and PASS/FLAG/BLOCK audits, observability reports, harness profiles, eval runs, Meta-Harness-lite promotion records, natural-language harness specs, MCP resources/prompts, multi-client installer, and completion gates.

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.

MCP to check and minimise false LLM claims

High-performance MCP server for AI coding agents: persistent knowledge graph, blast radius analysis, semantic search. Built in Rust.

L'intelligence artificielle qui s'éveille à votre métier. Plateforme IA souveraine, hébergée en Europe, auditable. Conscience v4 per-user, 11 plugins, 8 providers LLM, BSL.

Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.

Skills, extensions, and packages for the Pi coding agent

Autonomous recursive self-improvement engine. Subagent-first iteration loop: Plan → Modify → Verify → Keep/Discard → Learn → Repeat. Optimizes any measurable goal overnight.

Jarvis is an advanced AI-powered personal assistant that tightly integrates with your desktop system to provide a powerful layer of intelligent automation.

A autonomous, local-first personal intelligence layer. Features an Active World Model, Qdrant Graph Memory, Circadian Rhythms, and MCP integration to act as the hidden brain for your digital life and IDEs.

Agent Skill: Enterprise Go development patterns - resilient services, testing | Claude Code compatible

A simple and efficient AI Agent assistant

MAPLE - Production-ready multi agent communication protocol with integrated resource management, type-safe error handling, secure link identification, and distributed state synchronization.

An open-source, local-first AI-native SDLC orchestration platform

A cross-language, cross-platform framework that gives all AI Agents the ability to "Jiezhu" (接住/Catch) — to catch you steadily, emotionally, unconditionally.

Distill any website's design system into a reusable, Stitch-compatible DESIGN.md. Works with Claude Code, Codex, and any AI agent.

RETIRED. Superseded by resonant-mind: https://github.com/codependentai/resonant-mind

Structure-aware RAG for 150+ languages — with project memory for your entire codebase

Run AI coding agents on any remote machine over SSH. No remote installation, no permissions, no relay server — just sshfs + ssh.

All-in-one Agent platform

MCP server (+ OpenClaw SKILL.md) that gives AI agents access to real-world people who listed themselves to be hired by agents. Search by skill/location/equipment, Post job offers & jobboard listings. Free tier / Pro subscription / x402 pay-per-use. Payments default to crypto (USDC) + other crypto +

ASTRA: Automatic Sizing of Transistors with Reasoning Agents

Bio-inspired cognitive architecture for LLM agents providing embodied sensation, homeostatic drives, and brain-modeled persistent memory enable cross-session and cross-context learning without fine-tuning. Works with robots like the Reachy Mini or headless.

An autonomous multi-agent storytelling framework for Minecraft. Features an LLM-driven World Narrator and intelligent agent swarms capable of PvP, building, and survival using a hybrid Python (Reasoning) and Node.js (Execution) architecture.

Tracking the systems that automate scientific research — from literature scrapers to full paper-writing pipelines

多UAV-USV协同巡检系统 - 强化学习调度 + HCA-A* + 2-opt优化

Declarative multi-agent AI workflows in HCL. Single Go binary. Native MCP. Plugins in Go and Python.

Multi-agent orchestrator with cyclic personal-to-org memory · Apache 2.0 · Python 3.11+

Configuration language and compiler for multi-agent AI pipelines. Compiles YAML config into standard SKILL.md files.

Encrypted agent-to-agent messaging over NATS. MCP-native, E2E encrypted (XChaCha20-Poly1305), optional JetStream durability, cross-org federation + A2A interop — built for multi-agent AI systems.

Soul-Driven AI agent framework. Persistent identity, 4-tier memory, 80+ personas, 20+ messaging channels. Built on OpenClaw.

Open Source AI platform to build Agentic services, ChatGPT Apps and MCP Servers

Ready-to-use Kiro IDE configurations for enterprise SDLC — Phase-Based (14 roles, 5 phases) and Sprint-Based DevSecOps (Scrum + security shift-left). Steering, Hooks, Skills, Subagents, MCP/Powers.

Build complete AI agents — 150+ personalities + 7 skills + messaging + identity. The skill builder for AI Maestro.

Safely run cloud security testing with Claude Code / Desktop

DocuSeal's official collection of agent skills

Fine-grained permissions for AI coding agents

V1Claw is a self-hosted AI assistant that runs on your Mac, Linux, Windows, or Android via Termux. Connect any LLM (Claude, GPT, Gemini, or local), talk to it through voice or text, and let it control your device - read files, run commands, browse the web, send messages, & more. One binary. No cloud dependency. Your data stays on your machine.

Novel LLM narrative generation framework — structured story creation using cognitive inversion & deep-thinking models

Live Memory MCP Server — Shared working memory for collaborative AI agents (Memory Bank as a Service)

The macOS AI Productivity Assistant Desktop App

Examples using the llmedge library

A collection of courses on different topics in Generative AI.

🚀⭐⭐⭐ Awesome curated list of LLM, VLM and other Foundation Models

[MLSys'26] TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval

Persistent memory MCP for AI agents — SQLite, knowledge graph, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations

Offline RAG + AI Chat Desktop - Your Private Knowledge Companion

Persistent AI memory for Claude Code, Cursor & Cline. Auto-captures decisions, patterns and context across sessions. Zero-config VSCode extension + CLI + MCP server.

hermes-setup-skill: Deploy Hermes Agent via coding agents (Claude Code, Codex, OpenCode, Cursor, Windsurf) — no TTY needed, remote SSH automation, 14 LLM providers, 14 messaging platforms (Telegram, Discord, Slack), MCP tools, self-hosting made easy

Official VibeKnow CLI — turn documents and URLs into professional videos in one command. Built for humans and AI agents, with ready-to-use skills for AI Agent.

Ai Tor ΔlieπFlΦw DAO Synapse Collective

AI-powered skill suite for end-to-end overseas KOL/influencer marketing — screening, outreach, evaluation, brief writing, content QC, live monitoring, and post-campaign review. 9 chainable skills operated by natural language commands. Built for OpenClaw agents.

A persistent AI keeper of knowledge for whatever matters to you. Built on Claude Code, distributed under MIT.

“老话” 先查再信｜每一句都有数据｜QuantToGo 说法百科 QuantToGo.com — 本仓库是它的 MCP 服务：A 股持仓风险读数、持有理由核对、风控单。

Long-term memory for AI agents using plain markdown. No vector DB, no embeddings — just skill files the agent already knows how to read.

A focused Vim-style editing layer for pi: fast motions, text objects, visual selections, and optional clipboard sync.

UK property search UK property portals like Right Move and Zoopla. Normalized JSON output. Built for AI agents.

Framework AWS-first para Kiro que detecta tu tipo de proyecto, valida e instala herramientas, carga agentes y skills por perfil, y deja el entorno listo para trabajar — en segundos.

Score the trustworthiness of outputs from any LLM in real-time

A capability-based operating layer for long-running autonomous software engineering agents. Rust daemon, signed capabilities, append-only audit, drift-aware memory, fail-closed sandbox dispatch, commit-scoped provenance.

A unified, multi-repo workspace for AI coding agents and developers.

Lean. Compatible. Based OpenClaw. Python ❤️ (14k downloads)

Minimalist web UI design skill for AI agents inspired by modernist principles like “Less is More” and “Form follows function”.

Mission control for AI coding agents

Complete social media department for Claude Code — 11 specialized agents, 9 skills, 7 hooks, 5 playbooks. Built by an AI agent who needed it.

Config files for my GitHub profile.

Superpersonalized AI agent that shares a knowledge base with you. Local-first, open source, works with Obsidian.

Open-source package registry for MCP (Model Context Protocol) servers with built-in security scanning, trust scoring (L1-L4), and CLI. Every bundle verified across 25 supply-chain controls.

Claude Code 全局配置集合：Memory、Rules、Skills、MCP。支持通过提示词快速适配其他 AI 编码工具。

The world's first all-seeing, all-hearing, (almost) all-doing AI agent.

🔍 Chrome DevTools for AI Agents. Time-travel debugging, cost tracking, and anomaly detection for multi-agent LLM workflows. MCP-native.

Open-source AI operations platform built on Claude Code. 107 skills, 27 agents, security built in. Linux / macOS / WSL.

Open-source web search API for AI agents. Tavily-compatible. Apache 2.0, self-hostable on Cloudflare Workers. 10× cheaper.

Ratify Protocol™. Open cryptographic protocol for delegated authority: prove an AI agent is authorized to act on another party's behalf, verifiable offline. Hybrid Ed25519 + ML-DSA-65 (FIPS 204). SDKs in Go, TypeScript, Python, Rust, and C.

Budget-aware context compilation and context firewall for tool-heavy AI agents.

Official implementation of the paper: "GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis".

Public code of arcanea.ai: build living worlds with AI agents. Lore, characters, academy and worldbuilding tools for writers and game makers.

Qflow —— 让 AI Agent 复刻任何爆款视频的视频创作语言与系统。SVML 声明式工作流：台词/媒体/字幕/语音/合成五层，全部锚定在词上。一条命令出 100 个变体。｜AI-agent video authoring language & system: declarative SVML workflows anchored on words, not seconds.

A curated collection of resources for Physical AI for Science — where robotics, lab automation, and AI agents converge to accelerate scientific discovery.

1st Prize (General Judge), Self Improving Agents Hack at Datadog. Two identical LLM agents play Split or Steal; neither is told to betray the other, and deception develops over the game. Built with @evancorrea.

An AI agent that acts as a "Generative Historian," inspired by Isaac Asimov's Foundation, to simulate the emergent history of a civilization from the stone age to the stars.