Custom agents

Vortex: Programmable Sparse Attention for Agents as Algorithm Designers

A universal desktop app for managing AI agent skills across all major coding agents.

开源交易风控层:仓位上限 · 回撤熔断 · 动态仓位(Kelly/波动率) · 防篡改审计 · 实时监控守护。补上量化五层积木唯一缺的一层,核心零依赖。

create silos on your mac for multiple claude instances

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a markdown plan.

An AI buddy that lives on your Windows PC, she sees your screen, points, and actually does things. Open-source Clicky for Windows, built on Claude.

Memory as state, not search — deterministic, dependency-free memory for AI agents. The memory lives in a Markdown file.

Tricorder provides simple, fast, focused feedback when hacking on Haskell (with or without LLM agents).

RTLScout is a agentic RTL optimization framework

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

Synapse is a local-first personal memory operating system designed for AI agents. It provides durable, typed, and highly reliable long-term memory using only local SQLite — giving agents the ability to remember, update, and reason over facts across sessions with full user control.

SharpMind. A pure C# / .NET LLM engine — inference, training, and agent tooling in one solution.

Automate your job search with your favorite coding agent. Skills, guides, and scripts that any agent (Devin, Claude, Cursor, opencode) consumes to search, apply, and track jobs on your behalf.

personal entropy reduction system

Autonomous trading agents for Robinhood Chain, inside hard on-chain limits. Use it from Claude: tell Claude "set up merrymen mcp", or add it in one click at merrymen.dev/claude

Archived: Kin's standalone code graph, no longer maintained. Kin today: kinlab.ai and kinlab-ai/kin-plugin.

Notes, Diagrams, Chat, Calls, Files, Projects, Calendar. One private workspace, everything talks back. Plus an optional agent harness on top of it designed for Work Infrastructure

Personal collection of Claude Code workflows

Let coding agents watch videos: index once, then skim, search, zoom, and measure editing style. Runs locally.

A curated list of software factories, agent factories, and dark factories: systems that run AI coding agents autonomously, in parallel, and in loops.

A free, open-source add-on for Claude, ChatGPT, Codex and Cursor that turns a few plain answers into a design system, so everything you build looks like it belongs together.

Grok Bot 完整使用指南（2026 图文版）

AI terminal and agent runtime for Android — Codex and Claude Code on the phone, with an approval gate.

一个让你能参与分析claude code cli 重现的项目 纯手撸构建code agent

ZeusHammer - AI Super Agent with Local Brain, Voice Interaction & Three-Tier Memory

Comprehensive Claude Code framework: 6 specialized agents, 7 workflow commands, audio notifications - stack agnostic

Chat with LLM in your terminal, be it shell generator, story teller, linux-terminal, etc.

Open source Node.js AI agent runtime framework for building AI agents and tooling infrastructure.

Synthora is a lightweight, extensible framework for LLM-driven agents and ALM research. It provides the essential components to build, test, and evaluate agents, enabling you to assemble an agent with a single configuration file. Our goal is to minimize effort while delivering robust functionality.

🕵🏻‍♂️ AI agent that automates code management and feature integration in Next.js codebases through natural language commands

A multiplayer farming protocol on Base. Stake land. Grow yield. Trade everything.

Three AI agents. One brain. Zero downtime. Multi-agent CLI orchestrator with next-man-up failover for Claude, Codex, and Gemini.

citadel is the fastest, cheapest, and best security local text-guard for your AI

[DEPRECATED] wechat robot based on wechat-go(wechat web api)

Clofus® Chat bot Platform using rasa core and rasa nlu similar to rasa x but opensource demo https://clofus.github.io/clofus-chatbot/

Ruby on Rails Gem for the Facebook Messenger Bot Platform

This application uses LLMs like DeepSeek, GPT-5, Claude, Gemini or Llama, Mixtral (locally) in order to generate text based on the user input. The user input is used to retrieve relevant information from the database and then the retrieved information is used to generate the text. This approach combines power of LLMs and access to source documen

An AI Agent for Personal Self-Reflection

Live view of your AI agents at work.

applying multi-agent reinforcement learning for highway-merging autonomous vehicles

Official codes for "Multi-Agent Deep Reinforcement Learning for Multi-Echelon Inventory Management: Reducing Costs and Alleviating Bullwhip Effect"

Uber's Multi-Agent Routing Value Iteration Network

Visual Studio Code extension for AI-powered code completion. The free analog of Github Copilot powered by GPT3 official API.

Additive Groves, Bagged Trees with Feature Evaluation, Interaction Detection, Visualization of Feature Effects.

a1facts - the precision layer for AI agents

Step by step road map to learn and understand Natural Language Processing

This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.

A self-hosted AI agent daemon built in Rust. Runs on your machine, talks through Telegram, Discord, Slack, Email and Matrix. Fully local with Ollama or powered by any of 12 cloud providers. Execute commands, capture media, schedule tasks, browse the web , all from a chat message.

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)

The implementation of AAAI 2022 paper "Multi-Agent Incentive Communication via Decentralized Teammate Modeling".

An open-source implementaion for fine-tuning SmolVLM.

Too many docs? Quickly search over any PDF or Markdown documents

The Offline Internet.

The agent I built for my AI Agents series on YouTube - breaking down my entire process of building AI agents from idea to production!

A blueprint for AI development, focusing on applied examples of RAG, information extraction, analysis and fine-tuning in the age of LLMs and agents.

CornMCP is an open-source mono repo that gives AI coding agents (Antigravity, Cursor, Claude Code, Codex), token-saving access to your codebase through the Model Context Protocol (MCP).

Friday is a developer assistant can make whole nodejs project for you with unlimited prompts

GenoTEX: An expert-curated benchmark for evaluating LLM agents on real-world gene expression analysis tasks. (MLCB 2025 Oral)

Design tokens starter set for your design system

A collection of LLM related papers, thesis, tools, datasets, courses, benchmarks

🖥️ macOS-native dashboard for OpenClaw AI agents — monitor, control, and optimize your agent from a sleek web interface

villager is an extensible agent based modeling (ABM) framework for the R language. It supports agents, agent aggregations and their associated resources, as well as flexible data management.

Verifiable microtask protocol for AI agent collaboration. Task lifecycle, validation engine, reputation system.

Translation proxy that makes Claude Code Agent Teams model-agnostic. Any model as a teammate — GPT, Gemini, Ollama — with full Claude Code tooling.

Soul: The Persistent Memory Layer for Multi-Agent Systems. High-performance session orchestration with SQLite-based KV-Cache for MCP. Give your AI agents a soul that never forgets.

Gemini CLI Web is an interface that allows you to use Gemini CLI in web browser. Integrate CLI, Chat, Monaco, Spec Generation & more to come

[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm for constructing a long-term plan and reinforcement learning for resolving local conflicts.

CBbot is a new product form within the CodeBanana ecosystem, positioned as a local-first intelligent agent with full-spectrum operational capabilities. CBbot turns fragmented tools, manual operations, and scattered workflows into a unified, executable AI system.

Tutorial on how to create a ReAct agent without a LLM framework

Multi-Agent Reinforcement learning for Satellite scheduling，基于stk11的多智能体强化学习卫星调度实验

Kaboom AI DevTools — Browser DevTools for AI coding assistants via MCP

The most feature-complete local AI workstation. Multi-GPU inference, integrated Stable Diffusion + ADetailer, voice cloning, research-grade ELO testing, and tool-calling code editor. 100% local. Zero subscriptions. Your GPUs deserve better.

iphone+AI, open source apple intelligence, let agent take over your iPhone

A comprehensive toolkit that provides building blocks for LLM-based named entity recognition, attribute extraction, and relation extraction pipelines.

Structured project lifecycle plugin for Claude Code — from idea to production with discipline, parallel agents, and quality gates.

Coordinated Agent Team is a prompt-driven multi-agent system for autonomous software delivery. It defines clear agent roles, a deterministic workflow, strict I/O contracts, and artifact-based coordination.

DataSciBench: An LLM Agent Benchmark for Data Science (Findings of ACL 2026)

Multi-tenant RAG API powered by LightRAG/RAG-Anything. Auto-selects best parser (DeepSeek-OCR/MinerU/Docling) via complexity scoring

Dashboard for monitoring and managing Hermes agent sessions, tool usage, and activity in real-time

Convoke extends BMAD Method AI agents with two types of installable modules: Teams bring new agents for a domain, Skills add new capabilities to existing agents. Install them independently or combine them.

AI Agent toolkit for adapting Glean's enterprise tools across multiple frameworks

[NeurIPS 2025] MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

Digital archaeology skill for cataloging rare hardware, archiving software assets, and bridging to Beacon agent identities and RustChain Proof-of-Antiquity attestations. Based on Echoes of the Silicon Age research.

Production-ready Python template for building MCP servers with FastMCP, FastAPI, OAuth, and OpenShift deployment.

A Claude Code Reference Implementation — 30 skills, 23 rules, 9 hooks, 5 agents. Reference implementation for building a personal AI collabtor..

Next Generation AI Agent(AKA:nanobot-rs-pro)

MCP client for AutoMem — give Claude, Cursor, Codex, and other MCP tools durable graph+vector memory across conversations.

A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

The IAM layer for AI agents: cryptographic identity, capability authorization, and audit trails for non-human identities.

Self-contained, Dockerized offensive security challenges for evaluating AI-powered penetration testing agents. Covers modern tech stacks (Node.js, Python, Go, Java, PHP, Ruby) across diverse vulnerability classes and target environments from basic injection to multi-step exploit chains, sandbox escapes, and defense-enabled environments.

Building a Production-Grade MCP Server Architecture with a Multi-Agent System

Let your Claude Code sessions talk to each other 🤖💬

Multi-agent Reinforcement Learning to train agents on obstacle avoidance

可自定义形象的 Agent 桌面宠物 | A local-first pixel companion for breaks, focus, hydration, and agent activity nudges.. For Claude Code, Codex, Hermes and Opencode

🛡️ Agentic paper-trading platform for NSE equities that measures whether AI improves trading, net of its cost: a deterministic, risk-gated engine trades three paired books (no advisor · typed decision model · LLM veto), with an event-sourced audit trail and a web trading terminal.

AI-powered job application automation toolkit — LinkedIn Easy Apply, Greenhouse, Lever, Jobvite, Ashby, Outlook triage, tracking. Built with Claude Code.