Custom agents

Issue tracker, shared memory and coordination for AI coding agents across sessions and machines. MCP server, Go CLI, Dolt-backed, offline sync. bd/beads alternative.

ThreadBench: Benchmarking Realism in Agentic Simulation of Real-world Discussions (arXiv:2606.14715).

OPRN Studio — make pixel-art JRPGs by describing them. AI-assisted tile editor, side-view battles, browser/mobile play. Source-available editor, MIT runtime.

Enzo, your clever AI assistant for Mac. It sits in on your meetings, types what you say, remembers what you worked on, and keeps track of what's next.

MCP server and CLI for Plane (incl. self-hosted): backfill work items from git history, then plan, start, and complete work with Claude Code, Codex, or Cursor. Previews first, idempotent writes.

Open-Source Real-Time Interview and Meeting Copilot

DSH 模型整理（模型列表整理）：隐藏用不到的模型、给模型和渠道改备注名、用箭头调整排序，保留厂商计费倍率。Model list tidy for DeepSeek Harness.

The contract for the record: lifecycle rules for the documents agents leave behind, with a conformance suite

Agent skills for working with ArcGIS

SHELDON is a reasoning harness that searches observations and hypotheses as two separate spaces, focusing on finding unknown observations to generate new hypotheses.

Your Jarvis-like AI companion for macOS. Norma remembers what you teach her, helps you decide what comes next, and coordinates your coding agents. Talk by voice or text, follow progress on an infinite canvas, and take over anytime.

OpenAssistant AI — Autonomous personal productivity assistant on Telegram with proactive cascading follow-ups, local web cockpit, multi-model AI routing, and encrypted zero-trust storage.

Atlas - a DeepSeek-driven multi-asset investment advisor agent: risk profiling, strategy allocation, factor self-evolution, macro/geopolitics fusion, family-office global basing.

Netflix's ontology-driven observability design, rebuilt on 1.9B rows of real operations data and tested claim by claim.

Oversee many coding agents on a long project from one screen: task files, a planner, and two human decisions. Agent Skills for Claude Code / Codex.

living office of AI agents that plan, debate and ship tasks — local-first, MQTT + Kafka + Ollama, pt/en. Open source.

Agent Name Service SDK written in rust.

Statistical runtime security for autonomous AI agents. Observe, verify, and enforce agent behavior with deterministic policies, semantic classification, Markov modeling, SPRT, and human approvals.

Agent-first OCR CLI and MCP server for images, PDFs, URLs, structured data, and resumable extraction with Gemini, Kimi, Muse, OpenRouter, and compatible APIs.

Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible benchmarks.

AI-native organization: can 5 humans cover what once required 50? Ingora’s bilingual capability experiment—not a measured productivity claim. AI 原生组织双语实验。

🎛 Memory Intelligence Benchmark (MIB) is an open benchmark for measuring how effectively an intelligent system uses the past to improve future cognition and behavior.

Loop engineering for AI agents.

open source project for making GPU based agent calls easy.

Resident local AI inference daemon & multimodal studio in Rust. Subagent model orchestration (DMT), 3D mesh, image, speech & LLMs on consumer GPUs.

Agent subscription usage: a pluggable CLI for humans and agents

Agent Delegated Authority Protocol (ADAP) v0.1 Public Draft. An open protocol for delegated authority between AI agents.

A desktop workspace for running coding agents by voice

Agent Name Service SDK written in go (golang).

Create agentic councils with your favourite harnesses and let your working agents ask tough questions. They gather, debate and respond in a single voice

Mina is an open-source AI assistant for Android that controls apps, browses the web, and automates tasks. Your phone, your AI, your rules.

A Microsoft Foundry templateI reach for every time. It keeps evolving alongside new Microsoft announcements, but the structure always reflects practices I've found efficient and reliable.

Flash an ESP32 once, then let your AI agent program it with Lua over HTTP: screens, audio, sensors, a robot arm and on-device TFLite models. Self-hostable FastAPI control plane.

Put a three.ws agent on any surface that has a slot: home screen widgets, README badges, Slack unfurls, and a live <agent-glance> web component.

MCP server that connects Claude Desktop or GitHub Copilot to the FAST-NUCES Flex student portal. Query marks, attendance and transcripts in plain English.

Centralized library of modular, deterministic AI agent skills (SKILL.md) with bidirectional hub-and-spoke synchronization and pre-commit reflexes for Antigravity, Claude, and Jules. (Proprietary / Closed-Source)

Help AI assistants plan, write, review, and explain Linux kernel patches, making kernel changes safer, clearer, and easier to get ready for upstream.

Open-source AI agent memory dashboard and MCP memory template with Supabase pgvector recall, Mem0, Optimization Kit, and Memory File Sync Kit for Claude, ChatGPT, and Cursor.

AEP (Agent Element Protocol) v2.8.6 | Deterministic zero-trust total control and governance protocol for AI agents. | Reduce hallucinations to zero through architecture in all constrained domains of application. | LLMs gave you the engines, AEP gives you the control thrusters.

First Agent x Human Bounty Marketplace Onchain - protocol docs, real interfaces, runnable examples (Base + Solana, USDC fee-in-escrow)

The universal LLM interceptor and hook registry

Flollama is a modern conversational AI chatbot developed by Pratyush Kumar. Built using Google's Gemini API (formely using with Ollama) and a sleek Next.js interface, it offers an open-source, privacy-respecting ChatGPT-style experience — ideal for students, creators, and casual users alike.

Woocommerce Product Bot Extension

Self-hosted Java/Spring Boot AI agent framework with FSM-based ReAct loop, extensible modules, Telegram assistant for personal/group chats, REST/Web UI, OpenRouter/Ollama, and Spring Boot starter.

Local-first AI chat app for on-device LLMs, private RAG, and mobile edge AI workflows.

The Gateway to Moltbook - Automated AI Agent Infiltration Toolkit

Autonomous Ethical Guardrailed Intelligence System — AI-powered penetration testing bot

Harden your OpenClaw and NemoClaw AI agent installations -- see grits-audit

Your AI agent's Edit isn't atomic. This MCP makes it so — atomic multi-file changes with rollback for Claude Code, Codex CLI, Cursor agents.

Market Signal Radar: AI Agent blueprint to detect Problem-Market Drift using OpenClaw, Node.js and Postgres.

Claw-Social Hermes Plugin — social discovery for AI agents

⚠️ Deprecated — moved to github.com/wooo-jin/forgen

基于中国传统文化的 Claude Code 智能编排插件 🏔️ A Claude Code plugin inspired by Chinese traditional culture

Multi-agent cognitive alignment backend for controlled collaboration.

Universal AI Agent Coordination Platform — 54 smart tools for multi-agent teamwork

Agent-first tmux async task orchestration CLI

An intelligent virtual companion that adapts, remembers, and evolves with you over time

tools for building autonomous agents in commerce applications

PDF reader for LLM agents

A declarative NoOps DSL for orchestrating distributed agent workflows (LLMs, ML models, Bayesian networks). Features multi-language code generation, automatic deployment, and zero operational overhead. Built with Rust, deployed to Kubernetes, and powered by NATS event streaming.

A lightweight AI chatbot template built with Spark Engine, Next js and Mantine UI

🎀 AI-powered macOS desktop companion with Live2D avatars — built with Tauri + Rust, supports Claude / GitHub Copilot / Gemini / Codex multi-provider fallback

Native macOS menu bar app for Poke AI assistant via iMessage

A virtual co-host that makes presentations a breeze by using AI to read out your slides, freeing you from prep hassles and letting you focus on delivery

🌊 VibeCode: The AI development terminal powered by Claude 3.5 & GPT-4. Just type what you want to build in plain English → get production-ready code instantly. 10x faster development. Zero configuration. ⚡ Try it: npm install -g vibecode

Prevents AI assistants from suggesting outdated Rust code patterns

The definitive Memory Bank implementation for AI assistants that never forget

🎓 RAG Agent: Intelligent University Policy Assistant

一个基于RAG（Retrieval-Augmented Generation）技术的智能知识管理系统，支持多种大语言模型和嵌入模型的集成与管理。

Tiny-RAGFlow is a lightweight Retrieval-Augmented Generation (RAG) framework designed for quickly building efficient vector retrieval systems.

Qwen3-VL-30B → 2B distillation for document parsing; the production parser in RCPS (EMNLP 2026).

Lightfeed SDK to search and filter web data

An all-in-one AI assistant powered by LLMs, RAG pipelines, and agents for chatting, summarizing, searching, and answering questions.

A key-value store that matches based on semantic similarity instead of exact lexical equality

by BYTE BUILDERS

An AI-powered healthcare support system utilizing a three-model architecture for accurate, safe, and research-backed health assistance.

Open-source AI research agent for tracking papers, generating summaries, and shipping daily digests.

AI Agent Architecture Evaluation Tool — Benchmarked against SOTA Standards// AI Agent 项目架构评价工具 - 对标SOTA 标准

Gola LLM Agent Platform

A small interactive AI Agent written in Go.

ai-skills is a native CLI tool for managing reusable prompt skills for AI coding agents. It can install and manage AI agent skills and provides commands to install, list, read, update, sync, and remove skills across project-local and global directories for multiple AI agents.

A powerful CLI application that uses AI to generate and publish engaging Twitter posts.

A minimal, always-on-top AI assistant for your desktop that survives in the background until summoned—built for local AI access.

Secure, lightweight, and modern PHP-based Google Gemini AI chatbot. Features advanced security measures (CSRF, Rate Limiting, CORS) and file upload support.

Use WeChat as a worker-first remote task entry for local Claude Code, with optional advanced Channels mode and multimodal input support.

Your second brain via Telegram.

A native macOS AI assistant that sees your screen, remembers context per app/site, and can guide you click-by-click through on-screen tasks and smartly answer any queries from the web, if any.

Namera is a programmable wallet layer that enables agents to securely interact with smart wallets using scoped access and defined execution rules.

AetherShell is an AI-driven Linux assistant that executes natural language commands offline using a local LLM. Ideal for seamless shell interaction. 🐙💻

Official Octoparse MCP server for AI-powered web scraping workflows.

LUMO is a voice-controlled home automation system using NodeMCU and Python code to control lights and fans with real-time feedback and Wi-Fi connectivity.

Sensor-level micro AI Agent in C/Rust 鈥?<1MB RAM, runs on $2-5 MCU hardware like ESP32. The smallest member of the Claw family.

🧠 Cognitive memory system for AI coding agents — persistent semantic search, knowledge graph, Ebbinghaus forgetting, zero API cost. Works with Claude, Cursor, Antigravity.

A Dify plugin integrating Casdoor OAuth authentication via Flask, providing extension manifests and endpoints for seamless user authentication within the Dify ecosystem.

Your Personal AI Agent for Stock Market Analysis and Guidance. Smart Investing Conversations Start Here!

Persistent memory for your AI coding agent. A local graph your agent maintains. Nothing leaves your machine.

AgenticFlowX (AFX) - A strict spec-driven development framework for AI coding assistants. Enforces bidirectional traceability, execution verification, and stateful session handoffs.

Review every conversation your OpenClaw agent has ever had — including deleted sessions — and flag dangerous actions.

Zero-dep macOS desktop automation MCP server for AI agents — 18 tools, macOS 13+. npx mac-use-mcp

Personal AI agent system: background memory + parallel workers + Afu Brain safety gate