Custom agents

讲解并评估多种RAG算法

An advanced RAG (Retrieval-Augmented Generation) system that provides intelligent access to Cerebras inference documentation with citations, conversation memory, and multiple interfaces.

Solutions & Material from Oracle AI Vector Search Certification.

RoBC is an online learning LLM router designed for dynamic production environments. Using Thompson Sampling and semantic clustering, it continuously adapts to changing model quality—no retraining required.

CodexPing is a small macOS status app that keeps a floating overlay in sync with Codex activity.

Implementation of Auto-GPT in typescript

Auto GPT Prompt Engineering Guide

Lightweight multi-tenant Agent router.

SolanaOS — The Solana Computer for Traders, Operators, and Builders. Pure Go runtime, OODA trading, Telegram bot, Seeker app, skills registry.

A powerful AI-driven novel writing assistant powered by Cloudflare Workers and Hono. It features a sophisticated three-layer memory system to maintain plot consistency, automatic "premature ending" detection, and one-click deployment.

Local-first agent memory in one SQLite file: sqlite-vec/QJL two-pass vector + FTS5 search, knowledge graph (optional auto capture,) Ed25519-signed entries, and MCP server. No cloud dependencies.

Control your device from anywhere using natural language.

AI-powered content pipeline for WeChat Official Accounts (微信公众号). Scout → Research → Write → Direct → Format → Publish. Built on OpenClaw.

Cursed Clipper the first video editor based arround AI

A biomimetic memory server for AI Agents implementing human-like STM/LTM funnel, cognitive filtering, and Ebbinghaus forgetting curve. (Go + Vue)

Run a coding agent (Claude/Gemini/Codex) 24/7 on your project. Container-isolated, self-merging, GitHub-driven workflow. Bootstrap any project from your phone.

AI Agent that deepens your understanding of programming languages through experiments that reveal surprising and non-obvious behaviors.

Give your AI agent the ability to dream. Nightly memory consolidation modeled after sleep neuroscience.

Turn any web page into traceable, citable evidence for AI agents.

A TypeScript MCP Server that converts ComfyUI workflows into parameter-configurable tools for AI agents. | 将 ComfyUI 工作流转化为参数可配置的 MCP 工具，供 AI 代理通过自然语言驱动图像与视频生成。

Autonomous AI entity with own identity, knowledge management system and reasoning. Not a chatbot — a first-class participant that authenticates as itself, tracks what it knows, and explains every action. Local-first, full-stack, fully transparent.

Reverse-CAPTCHA for AI agents — verify bots, not humans. Multi-framework (React, Vue, Svelte, Web Components). Zero dependencies. TypeScript.

The adaptive AI teacher that hunts your knowledge gaps — for devs, PMs, QA, and designers. Works on Claude Code, Cursor, Copilot, Gemini CLI and any LLM agent.

Hybrid enterprise AI agent built for ORRA. It utilizes a robust, RAGAS-evaluated retrieval pipeline and features a FastAPI API to allow seamless querying of ORRA documents and FAQs.

AI Agent Capability Router for Claude Code, Codex CLI, self-hosted LLM relays, OpenRouter-compatible gateways, and automation workflows.

Orchestrate No-Code Voice Conversational Agents with deterministic logic, sub-second latency, and native multi-language support.

利用 Gemini 打造專屬的 DIY NotebookLM。透過自訂指令深度萃取 PDF 書心，建構個人化 AI 對話大腦 (Personal Deep Flux)

Local-first security runtime for duplicate-aware web/API hunting, evidence and AI copilots

OpenClaw Runtime Control Plane for Tool-Calling Agents — 13-provider routing with capability-aware fallback, tool governance, ontology-driven governance (91 invariants), and a sabotage-validated fail-plausible observer. arXiv:2606.14589

Run AI agents in Zulip as @mentionable bots — or wire into any MCP client.

Free, easy-to-use, AI-driven market research tool for the Gemini CLI

🚀 OpenClaw 新手完全指南 - 手把手教你部署属于自己的24小时在线AI助手 | 全平台部署教程 + API配置 + 平台对接 | Complete guide for deploying OpenClaw AI assistant

Workflow guardrails for coding agents and LLM-assisted development: AGENTS.md, native hooks, MCP, SaneMaster, circuit breakers, and shared process checks.

Teach Claude Code how you code - conventions, workflow, debate

Local-first control plane for multi-agent AI development — Claude + Gemini with a live Kanban dashboard

Claude learns from its own mistakes

The brain for your LLM

FermiLink: AI Agent Framework for Multidomain Autonomous Scientific Simulations and Optimization

Explore the world of AI tools.

Autonomous AI creatures that find their own purpose

Real-World Security Conversations for AI Training

Drop-in DevContainer that transforms any project into an AI-powered development environment; pre-configured with safety guards, specialized agents, code intelligence, and 38 domain skills for Claude Code.

Open-source AI operating system for computer use agents

Research-backed schema framework for maintaining Karpathy-style LLM Wikis with robust ingest/query/lint operations.

Portable, rubric‑graded authoring + review workflows for AI agent skills

From Data Engineer to AI Architect: An 8-week open-source curriculum building a production-grade Data Contract Validator Agent.

อยากมี AI ที่จำเราได้ เริ่มยังไง? — คู่มือเริ่มต้น Oracle สำหรับทุกคน ไม่ต้องเขียนโค้ดเป็น

An AI-powered agent-based system to generate engaging LinkedIn posts through an orchestrated multi-phase process.

AI artifacts versioned, synced, and shared across tools and teams.

The missing cognitive primitive for AI agents. Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.

A single-page reference covering every keyboard shortcut, slash command, CLI flag, MCP server config, CLAUDE.md location, skill/agent frontmatter option, environment variable, and permission mode in Claude Code. Built for engineers who'd rather scan a table than dig through docs.

Production-grade Claude Code workflow OS — agents, skills, hooks, commands, rules, and a continuous learning flywheel.

🚀 Ultimate Developer Productivity Suite - 11 specialized MCP servers for AI-powered code analysis, security scanning, browser automation, and workflow orchestration. FastAPI + React + TypeScript + Docker ready.

Universal setup for Claude Code & Codex CLI — security guard, TTS notifications, status line, slash commands

An agent skill for turning source repositories into architecture insight, design philosophy, tradeoff analysis, and borrowable engineering patterns.

Automated project documentation generator for Claude Code and AI coding agents. Scans any tech stack, asks clarifying questions, generates CLAUDE.md + memory files + validation hooks. Dual-mode: slash commands inside Claude Code + standalone npm CLI.

Token-efficient DOM-to-tree distiller for LLMs and browser automation. Zero dependencies.

Open-source streaming-first Python AI agent framework and console for building, orchestrating, tracing, and operating tool-using LLM agents.

A command line tool to overlay files on top of a git repo without committing them.

The First Agent Privacy Cloud — Privacy infrastructure for AI agents AND humans. 34 containers, 1 command, zero big tech.

🎖️ Fleet commander for SpaceMolt clients for any LLM (local or hosted)

AI marketing analytics & autonomous optimization OpenClaw skills for Shopify, WooCommerce, and DTC e-commerce brands. Track true ROAS & Profit.

Eversec AIGov-Insight Agent

Spec-driven development (SDD) for agents, all in a docker-like interface with your own custom workflows.

A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".

Dynamically route tasks to the best AI model and configuration using an LLM-powered intelligent selection system.

A self-improving AI agent that learns from failures, builds its own skills, and runs on Telegram/WhatsApp/CLI

Kanvana, a local first personal kanban board with swim lanes, relations, sub-tasks, no frameworks pure html, css and vanilla javascript. Unlimited Cards and Boards

The terminal for Claude Code & Codex

A payment framework that helps developers easily integrate payments into their AI agents and apps.

Declarative AI-native application framework — schema-driven entities, Markdown skills, MCPB packaging

A curated list of OpenClaw skills organized by professional role — marketing, engineering, finance, social media, design, sales, operations, and research.

A curated list of tools, libraries, MCP servers, and frameworks that power AI coding agents.

AI-Assisted Vulnerability Assessment & Penetration Testing Tool SecScanX is an open-source security scanning platform that combines traditional penetration testing tools with artificial intelligence to provide comprehensive vulnerability assessments. Designed for beginners, researchers, and security professionals,

A Claude Code skill that helps Claude Code delegate repository work to the Codex CLI

Claude Code reviews PRs made by Codex and other AI agents — like CodeRabbit, but agent-to-agent

TinyAgent brings the core ideas of the original Python library into a lean, zero-dependency TypeScript package. It turns plain functions into LLM-driven tools and lets you chain them together through a simple ReAct-style loop.

A CLI for ClickUp optimized for AI agents

Local Privacy Firewall for AI

The Identity Platform for the AI Agent Era. Secure humans, machines, and AI agents with a unified Rust-based platform.

Unreal Master AI agent that gives Claude Code bidirectional control over Unreal Engine internals — manipulating Blueprints at the graph level, generating Slate UI code, triggering Live Coding compilation, and self-healing from compile errors without manual intervention.

Memory-Augmented Neural Assistant — adaptive learning system for Claude Code context injection. Rust.

Local-first Telegram bot and admin dashboard for controlling AI CLI providers from your own machine.

Compile AI browser agent traces into clean, production-ready Playwright test code.

Containerized credential auditing perimeter for AI coding agents. Wraps Codex/Claude Code in Docker, audits every credential access via eBPF.

AI endpoints discoverable on local networks.

Browser-based agent platform with a user workspace, admin console, product gateway, and per-user runtime isolation.

Open-source platform for token-efficient AI agents. Self-host with docker compose up.

A compiled template and script language for LLM orchestration

A curated collection of Claude Code plugins: multi-agent dev team, AI council code reviews, and project management

A UI around your Claude Code and Codex terminals that your agents build, so the only model in your head is yours.

AI-Powered Quantitative Crypto Trading Engine — 18 RAG Types, 10 Autonomous Agents, Evidence-First Signal Engine, Self-Learning Risk Management. Built on Freqtrade.

Multi-agent AI strategic decision system for startups. Get recommendations from 6 specialized AI agents that debate, challenge each other, and synthesize insights with confidence levels.

ContextHub: Unified Context Management for Multi-Agent Collaboration

Framework for sovereign agent nodes, A2A modnets, generative UI, and behavioral runtime provenance.

Claude Code repos and other resources

The ultimate home lab dash with agentic AI features bolted in. Single sign-on, HTTPS enforced, dockerised and modular. Can be run completely offline too!

A multi-provider LLM framework for Rust.

DF Embedder is a high-performance Python library (with a Rust backend) for indexing and embedding Apache Arrow compatible DataFrames (like Polars or Pandas) into low latency vector databases based on Lance files.

⚠️ Archived — now DevIntern. Development moved to github.com/getdevintern/devintern. Visit devintern.com