Custom agents

"简历匹配智能体"是一个AI驱动的平台，旨在逆向工程招聘算法，向您展示如何精准定制简历。获取那些能让你通过初步筛选、进入人工审阅阶段的关键词、格式和洞察。resume-matcher-agent意思就是模拟HR怎样筛选你的简历，提前给你展示筛选的结论，方便你尽快修改好你的简历，以增加通过的可能性。

AI-managed WordPress, out of the box. OpenClaw + WordPress + Data Machine + Agent Skills.

High performance (LLM-) agents execution environment with production in mind.

PolyGPT is an autonomous agent that can learn new capabilities on-demand.

PyTorch implementation of Foerster, Jakob N., et al. "Counterfactual multi-agent policy gradients."

An algorithm for exploiting Reinforcement Learning (RL) on Multi-agent Path Finding tasks.

PyBreeze features built-in modules tailored for every level of modern automation, allowing developers to tackle complex scenarios without leaving the IDE.

KGB-RAG是一个基于neo4j图数据库和其他图数据库的知识图谱检索系统，它可以根据用户的自然语句提问，从原数据库获取相关实体信息，并通过知识图谱检索技术以及结合大模型自身能力来增强回答用户的自然语言提问。

Experiment to create an agentic autonomous AGI with benevolent programming

An open-source command-line tool for developing Unity games with Claude Code

An example react-admin app simulating a help desk UI for support agents

Pragmatic framework to build LLM Copilots

MarketBot is a finance-customized version of openclaw, built as a dedicated AI agent for market intelligence, trading analysis, and decision support.

On premise enterprise-grade RAG-powered agentic workflow chatbot platform with multi-provider support

This project is a Streamlit-based chat application that interacts with the Gemini AI model, allowing users to engage in conversations with an artificial intelligence assistant. The application stores chat history, allowing users to revisit and continue previous conversations.

This is the coffee shop website developed using HTML, CSS, JS, PHP, & MySQL. This website has "Add to Cart" and Chatbot functionality. It also has a login and register form.

Brain-like memory + security for AI coding agents. Works with Claude Code, Cursor, VS Code, OpenClaw. Now ShieldCortex.

Code and data releases for the paper -- DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

A self-organizing network that combines cellular automata, coherence, and language models to explore emergent collective intelligence through cellular agents that think, plan, and evolve in a multi-dimensional space.

🇨🇳 SWCC — Democratic Centralism Multi-Agent Orchestration for Claude Code (民主集中制多智能体编排)

VOIP tool for calling over Tor

Official Repo for The Paper "Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems” (IEEE TAI)

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

Distributed Multi-Agent Messaging Framework

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

Open CLAW Knowledge Distiller · 龍蝦知識蒸餾器 — Turn YouTube/Bilibili videos into structured knowledge articles. Local Qwen3-ASR MLX + AI summarization. MCP server for Claude Code / Open CLAW agents.

An AI agent memory framework that converts an agent’s own interaction traces—both successes and failures—into reusable, high-level reasoning strategies. These strategies are retrieved to guide future decisions, and the loop repeats so the agent self-evolves.

run claude in a loop using docker.

Bioinformatics Retrieval Augmented Digital (BRAD) Assistant - A LLM powered agent for bioinformatics 🤖

LLMCompiler is an Agent Architecture designed to speed up the execution of agent tasks by executing them quickly in the DAG. It also saves the cost of redundant token use by reducing the number of calls to the LLM.

InfCode is an intelligent Code Agent System developed by Tokfinity's Code Research team & Beihang University, which uses LLMs to automatically analyze and fix Code Repo issues.

Thoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.

ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth before coding.

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval And Synthesis For SLMs

Self-Extensible Multi Agent Assistant 🐋

AI coding skills and prompts for Android lead engineers, works with Claude, GitHub Copilot, Gemini, and Cursor. Covers Jetpack Compose, shared element transitions, beautiful UI, architecture decisions, code reviews, and MCP integration.

VS Code AI Agent Interactive Programming. Tools for CoPIlot and other assistants. Can also be used as an MCP server.

Google《Introduction to Agents》中文翻译

Background sounds that play while Claude Code works and stop when it needs your attention — so the silence doesn't drive you to a “that's what she said” moment.

🔍 Awesome Agentic Search is a curated list of papers, tools, and resources on agentic search—where AI agents plan, search, and reason to answer complex questions. Explore the latest research, benchmarks, and industry solutions for next-gen search-enhanced AI! 🤖✨

Rules and instructions for agentic coding tools like Cursor, Claude CLI, Gemini CLI, Qodo, Cline and more

Copilot SDK for building Production-ready AI Copilots for any product. Connect any LLM, deploy on your infrastructure, own your data. Built for speed and control.

A Decoupled Architecture for Autonomous High-Energy Physics Phenomenology

Control Claude Code from your phone — a multi-machine agent hub via Discord. No API key needed, runs on your Claude Pro/Max subscription. Start new sessions from mobile, manage multiple machines from one place.

Nous Research 精心整理了一份适用于 Hermes Agent 的实用技能、工具、集成和资源列表。

A detail Implementation of handling long-term memory in Agentic AI

A Rust-based agent orchestrator enabling a swarm of Claude Code instances building software.

AI Agent plugin for Google NotebookLM (Claude, OpenClaw, etc) — generate slide decks, audio overviews, videos, mind maps, flashcards, quizzes, infographics, reports, and data tables from your notebooks

Open-source, customizable frontend for Venice AI. Chat, image gen, audio, video, embeddings + visual workflows — all in one UI. Your API key, your browser, no backend.

Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

Archived: Archcore moved to github.com/archcore-ai/archcore (CLI under cli/)

Yappuccino is a social blogging platform where you can share posts, comment, vote, and repost. Platform integrates n8n AI agent to automatically summarize posts.

🤖QueryMind is an agent framework for building LLM-powered agents specialized in Text2SQL📊 tasks with agentic retrieval capabilities🔄 and enterprise-grade security🔒.

MedAutoBench — Medical AutoResearch Benchmark for Autonomous AI Agents

MCP server for Denmark's Aula school platform — TypeScript MitID auth, no headless browser. Exposes profiles, calendar, messages, ugeplaner to AI agents (Claude/Cursor/etc) via Model Context Protocol.

Zooid is an open-source, self-hostable chat app for collaborating with AI agents alongside your team.

Claude Cortex

🚀 Level up your career with GenAI. 📄 Tailor your CV to any JD, 🔍 automate company research, and 🗓️ generate custom interview prep plans for your next role or internal promotion.

Open source AI agent for personal finance

EvE is an open-source framework for co-evolving ensembles of coding agents. Wrap Codex into an evolutionary loop that co-evolves solvers and agent guidance.

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.

Your coding agents forget. Graft doesn't. Persistent local memory that brings back fixes, decisions and project knowledge when they matter — across Claude Code, Codex, ChatGPT and more. Local-first. No SaaS. No API key.

An agent for automatically deploying models from monolithic DL models to complex LLM-RAG models

A code companion that lives in Slack

AgentWard – Built for all, hardened for OpenClaw.

Portable fresh-agent QA loop prompt for finding bugs without biased self-checks / 通用自动 QA 循环 SKILL

macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.

Uses Apple Reminders as a bridge between Claude on your phone and Claude Code on your Mac, dispatching agents from new reminders.

A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.

A Claude Code / agent skill for building genuinely designed, editable Feishu / Lark (飞书) whiteboards — deliberate composition, real hierarchy, a gated pipeline with pre-render fit-check and independent design critique.

A powerful knowledge base management and work-study system. It supports a range of advanced AI features, including multi-role conversations, autonomous multi-turn KB search by Agents, browser automation, session compression, MCP, SKILLS, and bots. The project adopts a decoupled front-end and back-end architecture

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidence graphs for risk, forensics, and audit.

TripStar multi-agent travel planner powered by Spring Boot 4, Spring AI Alibaba, StateGraph, multimodal note understanding and AMap

Hands-on Microsoft Foundry hackathon labs to build, monitor, evaluate, and deploy agentic AI workflows.

An operating workspace for Claude Cowork: decisions, context, next actions and routines in Markdown, so AI work stays grounded and team-owned.

The governed client for Proxmox (PVE, PBS, PMG, PDM): plans, keeps the receipts, puts things back.

A curated list of awesome agentic commerce resources — protocols, MCP servers, tools, apps, APIs and services for AI agents that shop, sell and transact. For store owners, developers, agencies and marketers.

Secure, reproducible sandboxes for AI agent evaluation, training, and data synthesis.

Vibe first. Then FastAgent — turn a local agent directory into a live service: in your app, on GitHub, in Telegram, or any channel.

CLI toolkit for AI agents — turns search queries into structured web evidence (JSON). Provider-extensible architecture, designed to be called from Agent Skills (Claude Code, Codex, Cursor, etc.).

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)

AI diagram generator for software architecture - the open-source Eraser.io alternative. Describe your system in plain English, get editable system design, sequence, ERD & cloud diagrams on an Excalidraw canvas. Self-hostable, bring your own key. Vibe diagramming for engineers.

An autonomous multi-agent IDE for screenplays🎮 & novels📖. One-click to share web performances or drive Unity dialogue systems. Empowering vibe game dev with AI!

Self-evolving team memory

笨办法学 Agent · 亲手打造一个 harness——不用框架，32 个练习亲手写出一个 agent harness 的每一层。系列第一本，全书已完结，三本各自独立不分先后。

Synchronize and Orchestrate agents from CLI to GUI, across desktop to phone.

Enterprise Agent Operating System — AI employees that learn your business and deliver outcomes. Self-hosted, open core.

Cross-platform Computer Use plugin for DeepSeek Harness: observable desktop automation with an isolated virtual cursor, AX/UIA observation, screenshot vision, and 12 guarded tools.

The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

Self-hosted, non-custodial gateway between the API you already run and the protocols AI agents use to discover, call and pay for it

🐼 Steer your LLMs and agents at the token level: A web tool for token visualization & control, model inspection, installation-free harness, and LLM & agent trajectory annotation.

AI CAD 建模 Agent：一句话需求进来，调研、提问、出 BOM，逐件完成真实 CAD 建模并导出装配 STEP（参数化 BRep，不是图片或网格）；几何与碰撞检查不过关就不交付。Windows 封闭 Beta。An AI CAD modeling agent: real parametric geometry from a one-line brief, gated by geometry and interference checks.

Deterministic research reports for Chinese public mutual funds, as a DeepSeek Harness plugin: one fund code in, a versioned Markdown report out, with performance decomposition, holdings penetration, style attribution and explicit data-gap declarations. Metrics are computed in code, not by the model.

Collector/Correlator, Embedded log-based WAF, AI Patterns Classifier

把 DeepSeek Harness 打包成能直接装的安卓 APK：不用 Termux、不用 root、不用配电脑，读屏/点按/虚拟屏/定时任务和整套技能都随包；它还能在手机上自己编译、打包、签名、发布。 Android APK for DeepSeek Harness — no Termux, no root, no PC. Screen control, virtual display, scheduled tasks and bundled skills out of the box; it builds, signs and releases itself on the phone.

A local-first AI control plane for orchestrating agents, models, tools, and machines from one desktop app.

YouTube view bot: multi-threaded view inflation, proxy rotation, watch-time retention, and randomized user-agent/device fingerprinting per view.

Companion intelligence for autonomous agents with real-time supervision, escalation, and human approval loops.