Custom agents

ZAST Express: Your Security Copilot in IDE.

Code of the ICCV 2023 paper "March in Chat: Interactive Prompting for Remote Embodied Referring Expression"

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Bridge local MCP clients to browser WebMCP tools through Playwright, using native WebMCP when available and injected adapters when not.

NebulaFlow is for visually designing and running developer workflows as node graphs (CLI, LLM, control‑flow, previews). Build and execute workflows inside VS Code, Electron and Browser with workspace persistence and agent-powered LLM nodes.

Compile documents into a living Obsidian wiki. Any AI agent. Based on Karpathy's LLM Wiki pattern.

Cursor10x is a comprehensive suite of tools that enhances the A.I. agent's capabilities within the Cursor IDE, providing persistent memory across sessions, standardized task management, and enforced best practices through cursor rules.

You install it. Claude drives the CLI tool. At first it might seem like too much. Eventually, nothing less will make sense.

A sleek AI-powered chat app with dynamic personalities, image generation, web search, and voice. Built with React Native & Expo. Web: https://eyux.com.et | Android: https://eyux.en.uptodown.com/android Desktop app: https://apps.microsoft.com/detail/9NX5DBW6NHW1?hl=en-us&gl=US&ocid=pdpshare

Create an IRC chat bot powered by AI, using llamafile, in minutes.

create a customizable chatbot easily and quickly with flutter

An AI-powered CLI tool to enhance your Markdown workflow, with auto-image downloading, translation, and more features coming soon!

AI coding agent in C. Single binary, zero runtime deps, every major LLM provider.

AI-Native Operating Environment — Linux-based OS with Rust kernel modules and Python AI/ML runtime. Local LLMs, multi-agent orchestration, and intent-driven computing, all on-device.

Embedded multi-session terminal panel for Agent Zero.

Simulation of a distributed control algorithm to drive a multi-agent system with a single leader (has knowledge about target locations) to the target positions with collision avoidance.

Oracle Framework - Complete Claude Code framework with commands, agents, and ψ/ structure

Telegram bridge for local claude, codex, neovate, and opencode — with per-session working directories and background service support

Claude Code skills for managing OpenClaw deployments — scaffold agents, configure channels, manage secrets, set up memory systems, and operate your gateway

SDD-AI (Specification-Driven Development with AI) packaged as a CLI. Installs skills and sub-agents for Claude Code, Cursor, Codex,OpenCode that guide the developer through a structured AI-assisted development workflow, using refacil-sdd/ as the specification store, plus a local bus so agents across different repos can communicate with each other.

A sophisticated real-time voice assistant that seamlessly integrates speech recognition, AI reasoning, and neural text-to-speech synthesis. It is designed for natural conversational interactions with advanced tool-calling capabilities.

An intelligent AI agent system that brings the world of Stardew Valley to life through conversational AI, RAG vector databases, and multimodal analysis.

Terraform framework for deploying [elizaos/eliza, swarms] ai agents

OSINT Agentic Framework

Cloudflare-native AI agent — 13 tools, codemode, 5-layer memory, self-learning, multimodal I/O. Telegram, Discord & WhatsApp bots. Web search, image gen, TTS, document RAG, calendar, task delegation. 100% serverless on Workers + Durable Objects.

An autonomous liquidity agent that watches Meteora DLMM pools, reasons over live on-chain data, and rebalances positions before they bleed.

AI-driven tool for automatically collecting, analyzing, and generating actionable insights from customer reviews across multiple platforms.

A multi-user Claude Code CLI based Coworker with Multi Agent Orchestrator, Multi model support including Ollama models, Advanced Functional skills, Channel integration for Chat and text messaging platform running completely in docker containers with an Admin module for complete visibility and observability

AI-powered code intelligence CLI with multi-agent analysis, impact graphs, and conversational coding.

An Interactive Infinite Story Generation Framework Based on Multi-Agent

Kagora - Multi-AI Terminal Platform

More than a writing assistant — BojuBot turns your Obsidian vault into a personal AI platform

Open-source CLI + editor plugin (Claude Code, Cursor, GitHub Copilot): one command installs 29 agents, 53 skills, 67 rules, 30 commands, 7 hooks & MCP integrations into any repo. Audited each release across 24 governance domains.

Unofficial Facebook Chat API for Python

This web application is designed to facilitate seamless communication with the Gemini API, and it's available for free.

tmux + Python agent lifecycle manager (start/stop/monitor/assign) with cron-friendly scheduling; no server required

热门skills推荐,包括编程以及非编程等各种热门实用的skill

A single-file project management standard for agent-human collaboration. One markdown file captures everything about a project — from scoping through execution — so agents can pick up exactly where they left off.

分享高质量的AI项目

Cross-platform desktop app for multi-model AI chat, web search, knowledge bases, and document Q&A — install and use out of the box. 跨平台本地客户端，集成多模型聊天、网络检索、知识库与文档对话，开箱即用、稳定高效。

This project is the backend engine for a fully autonomous AI-powered call center. It integrates a large language model (LLM), speech recognition, and text-to-speech to manage real-time phone conversations via Asterisk.

The open-source, AI-powered Unified Namespace (UNS) Operations Center. Visualize MQTT topic trees, build dynamic SVG HMIs, transform data via ETL, and leverage an embedded Autonomous AI Agent for alerting and historical time-series analysis.

Agent workflow plugin for Claude Code and Codex that takes projects from idea to reviewed, tested implementation.

Browser-native agent · profiles · tools — by aratech | Zero installs, isolated, secured and self-evolving agent.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.

Knowledge-base-driven article generation, fact audit, and 7-platform publish packs for WeChat, Xiaohongshu, Zhihu, Juejin, CSDN, Toutiao, and Weibo, with Wechatsync draft-sync handoff.

飞书(Lark)AI 项目经理 Agent + 项目管理系统部署套件 · 共享引擎+多实例配置 · Claude Code 驱动 · markdown 为源 + 索引治理(四项校验)+ 多维表格镜像

Delegate complex tasks to Manus AI - web research, report generation, code building, data scraping. Task templates, monitoring, cost tracking. OpenClaw skill.

A GUI for Claude Code and Codex, built for multi-agent orchestration — with 'superthink' adversarial verification, agent memory, and Discord remote access

OpenClaw skill build of Web Search Plus — stable compatibility path synced to v3.3.0 / WSP v2.5–v2.9 features. Active engine development: hermes-web-search-plus + web-search-plus-mcp.

Biomimetic memory architectures for LLMs — surprisal gating, reconsolidation, affective routing, sleep consolidation, and spreading activation

A modal text editor built for the age of AI agents — Neovim-style editing, Emacs-style runtime flexibility, powered by Elixir/BEAM and Zig

Autonomous AI coding agent — 126 skills, 7 subagents, 5 platforms. Iterative optimization with automatic rollback, failure memory, and parallel multi-agent execution. Plugin for Claude Code, Cursor, Codex, Gemini CLI, OpenCode.

Product management OS for Claude Code: agents, skills, workflows, and memory across the full Agile loop.

🚀 Telegram MCP 多账号管理神器 | 123+ AI工具 | 一键群发 | 定时任务 | AI智能润色 | 扫码登录 | Web后台 | 批量营销引流拓客必备

Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code.

The first lifelong companion AI where the character you love grows old with you. Supports multiple LLMs and QQ integration.

AI agent security harness for adversarial testing: 603 executable tests across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Commit-pinned OWASP Agentic v1.1 T1-T17 coverage (13 direct, 4 partial, 0 not evidenced), AIUC-1 2026-Q1/Q2 crosswalk 19/20 testable, NIST AI 800-2 aligned. v4.15.0

🦞 ClawBox — Your private AI assistant on NVIDIA Jetson. Setup wizard, dashboard, and 580+ skills. Plug in, scan QR, done.

🧠 AI-native Android automation via MCP. Give Claude, GPT, Gemini or any AI agent full control over Android — tap, swipe, type, screenshot — with ~6ms latency. 100x faster than Appium. 43 tools. No root required.

A curated corpus of incidents, attack vectors, failure modes, and defensive tools for autonomous AI agents.

A high-visibility, general purpose programing language for humans and AI.

Agentic Theorem Prover for Rocq for Program Verification

Spettro is a terminal coding assistant built in Go. It automates planning, coding, and testing with multi-agent workflows, model selection, and an intuitive UI. Connects to local and remote AI providers, supports conversation history, and empowers developers to streamline their workflow from the terminal.

Black-box web penetration testing automation framework for AI Agents

Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. No cloud, no API keys, no subscription, zero telemetry — your code and your ideas never leaves your Mac. Autovisor, an autonomous Supervisor, creates, runs, answers & reviews tasks on its own. Bash, computer use, vision, semantic search.

[ICML 2026] This is the official implementation for paper HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents

Enterprise-grade FastGPT workflow JSON generator - Works with Claude Code, OpenClaw, Costrict.ai, Trae and any skill-based AI platform

Terminal UI toolkit inspired by Claude Code — 25+ React components for building rich CLIs, AI agents, and dashboards

Fast-ASDLC: 5x TTM with AI-native Agentic SDLC. Local-LLM first, Human-in-the-loop, Spec-driven. Built on DDD, Hexagonal Architecture, C4 Model & MCP. Features Meta-agents for self-improvement, Memory Bank for context persistence, and automated 100% test coverage. Everything-as-Code & Mermaid.js centric to save context window and slash token costs.

Autonomous AI agent for Instagram — generates reels, carousels, memes, quote cards and posts them on autopilot. Free-tier LLM router, commercial-safe licences, 8-feature anti-detection layer, 671 tests. Single VPS deploy.

Hybrid RAG Worker on Cloudflare Edge — Vector + BM25 search, metadata filtering, multimodal vision, MCP server, and intelligent query routing. ~400ms p99.

Native Hermes Agent plugin for X/Twitter automation through Xquik. Not affiliated with X Corp.

A schema-enforced module framework where every interface is inherently perceivable by AI.

ISO 27001 (+42001 + NIS2) ISMS framework designed to be instantiated and maintained by LLM Agents

🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve them in a sandbox — every order through machine approval, the LLM never on the order path. Multi-market, audit-grade.

A simple agent co-researcher for coordinating GPT Pro, DeepThink, Codex, Gemini, and Aristotle on hard open problems. Emerged from work on Erdős #872.

Turn any English article or YouTube transcript into an offline deep-reading lesson page — Edge TTS, karaoke word highlight, per-lesson dictionary. For English learners who use local coding agents (Claude Code / Codex / OpenCode).

Configurable proactive nudge worker for chat apps

Unlimited context for Ai — give any LLM a billion-token memory. Open-source, local-first context + memory engine for agents. 🧠⚡

Dive is a secure, local-first desktop client for LllamaCCP, LmStudio, Ollama, Pi agentic AI and Cloud. Features an ultra-compact offline RAG engine for indexing massive book libraries, MCP tool integration, sandboxed custom skills, PDF extraction, and macOS daemon support.

A lightweight memory engine for AI agents using fuzzy graphs, Hebbian updates, and optional LLM gating.

IVAgent (Intelligent Vulnerability Agent) 是一个基于大语言模型(LLM)的智能漏洞挖掘 Agent，支持多种分析引擎和二进制/源码分析场景。

Autonomous Solidity Fuzzing via a Multi Agent Orchestration Framework

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached dispatch by default. GPL-3.0.

The First "Serverless" Swarm AI for GitHub Actions. Turn your repository into a self-healing, multi-agent AI workspace with zero infrastructure cost.

This repository considers the implementation of the paper "FoX: Formation-aware exploration in multi-agent reinforcement learning" which has been accepted to AAAI 2024

Visual Config Editor for Claude Code - Drag & Drop Hook Pipeline, Agent Workflow, Skill/Rule Editor

A lightweight and highly extensible Agent framework

FinOps agent

Open-source terminal AI coding agent with persistent local memory, automatic context recall, and searchable cross-session history.

A local-LLM privacy layer for anything you paste into a cloud model — detect, tokenize, restore. Zero deps, reversible, strong on Chinese.

Desktop + mobile cockpit for your local Hermes agent — chat, repos, fleet, kanban, terminal, editor, Obsidian — over your own Tailscale. Nothing leaves your machines.

Run Pi coding agent isolated in a Docker Sandbox microVM with a local llama-server as the inference backend

Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it fails the build when the code a doc describes changes. Deterministic, no LLM.

A curated database of China policy shocks for economics, finance, and policy evaluation research.

Tool for analyzing activity in chatbots (Telegram, Slack, Discord, Vk, WhatsApp, Viber and all other) created in Python.

local RAG extension for pi coding agent

Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge

The official source code for "RAG-Enhanced Collaborative LLM Agents for Drug Discovery"