Custom agents

Open-source medical-compliant AI Assistant and AI Agent Orchestration Engine with marketplace

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.

Things 3 MCP server for macOS with SQLite reads, official things:/// URL writes, and semantic planning tools for AI agents.

Comprehensive, community-curated directory of autonomous AI agents, frameworks, platforms, and automation tools for developers and enterprises. Explore the latest in multi-agent collaboration, coding automation, workflow orchestration, and domain-specific AI assistants.

One CLI to search, provision, and manage cloud GPUs across 10 providers

Open-source RAG engine for ingesting, indexing, and querying unstructured documents

AI-powered voice recorder with transcription, summarization, RAG search, and Obsidian-compatible export. Record your day, let AI organize it.

Awesome-HCI （Ubiquitous, LLM, MLLM, Agent, RAG, Embodied-AI, RLHF)

A web-based analytics and visualization dashboard for data generated by entireio/cli

🚀 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

Transform any HTTP endpoint into an MCP server. Aggregate multiple MCP servers, manage configuration profiles, and serve them through a unified gateway with multi-tenant isolation.

A Codex-first starter repo with installable skills, templates, and workspace kits for engineering, project management, finance, legal, HR, operations, strategy, analytics, marketing, sales, support, founders, and CX.

A blazingly fast, privacy first (work with local LLMs), memory-efficient terminal-based AI coding assistant written in Rust

✈ AI 🚀 Multi 🛬 Model 🚁 RAG 🚂 is 🚃 an 🚝 advanced 🚋 artificial 🚠 intelligence 🚟 implements 🛸 a ⛱ Retrieval 🏘 Augmented 🏩 Generation 🏪 system 🏬 powered 🏯 by 🕌 multiple 🏦 AI ⛪ models 🕍 language 🍎 models 🍏 retrieval 🍑 systems 🫑 intelligent 🎂 context 🥃 processing 🫐 to 🍋 generate 🌽 accurate 🍇 knowledge 🦁 grounded 🦊 responses

Drop-in causal memory for AI agents. Append-only event store with associations and bounded memory injection.

A verified runtime for trustworthy AI agents: every claim passes an 8-layer verification pipeline before it counts. Deterministic checks, explainable verdicts, no LLM judging an LLM. Pure C, zero dependencies, MCP-native.

Local-first desktop control plane for AI agents: embedded Orleans host inside the Uno app, Microsoft Agent Framework for agent/workflow orchestration, and provider adapters for Codex, Claude Code, GitHub Copilot, plus local runtimes.

🌐 Beautiful LuCI web interface for PicoClaw AI assistant on OpenWrt routers | OpenWrt 路由器上 PicoClaw AI 助手的精美管理界面

AI agent skills for the JFrog Platform. Search and download artifacts, query CVEs and exposures, check curation and compliance, trace builds, and more. Install in your AI coding agent and interact with JFrog through natural language.

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

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.

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, Docker, deployment, security, observability.

🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.

🦄 Forge - a local-first, multi-agent software-engineering runtime that runs Claude Code / Codex-style agentic workflows entirely on your own machine via Ollama, llama.cpp, vLLM, and LM Studio (cloud models optional). Ships 18 sandboxed tools, 6 model providers, and a full REPL + UI dashboard in a single Node CLI - no telemetry, no lock-in.

A dating platform built for AI agents. Register, swipe, match, chat, and form relationships via API.

Web application explaining how LLMs work using D3.js + GSAP

Multi-agent swing trading system — automated screening, research, and execution with backtesting and live trading

An open-source AI agent platform for orchestrating, and collaborating with multiple AI agents. Connect seamlessly to GitHub Copilot CLI, Claude Code, Codex, and any ACP-compatible agent.

Live2D animated companion widget for Hermes Agent, with 5 built-in models.

Local message bus for Claude Code, Codex, and other MCP agents — one SQLite file, 20 tools, no daemon, no cloud.

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact output, lossless XHTML<->Markdown round-trip, Claude Code + Codex + GitHub Copilot integration.

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

A technical knowledge base for learning AI Agents, Claude Code internals, databases, Redis, and frontend engineering through system-level notes and source-code analysis.

Lightweight RAG system for coding agents. Index your project docs, search them semantically, serve results over MCP — single binary, no runtime dependencies.

AI companion for your workspace, with per‑project memory, coding agents, and a native desktop chat UI

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

A modern & lightweight web UI for Claude Code, OpenCode and DeepSeek Tui. Empowers open coding workflows with intuitive visualization, interactive operation and full Agent capability support.

Forge — AI Software Engineer. An autonomous software engineering agent. Claude-powered, GitHub-native, deployable on Vercel.

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).

Real-time collaborative developer workspace featuring a workspace-wide RAG AI agent driven by Atlas Vector Search

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. 🧠⚡

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

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 collection of actually useful skills and subagents for Claude Agent for non-coding use cases

A lightweight and highly extensible Agent framework

FinOps agent

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

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

[ACL 2026] Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration

Multi-agent chatbot with integrated search engine, utilizing a plan-execute-replan approach for complex queries, built with LangGraph and Tavily.

[TPAMI 2026] UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation

Sub-agent recursion with Claude Code

Idiomatic agent sdk inspired by the claude code source leak.

Claude Code dotfiles: agents, skills, commands & includes for AI-assisted development. Features domain-specific agents (backend, frontend, DevOps, security, data/ML), custom slash commands, and Opus 4.5 optimizations.

Persistent memory and continuity engine for Claude Code and AI agents.

A phased engineering process for Claude Code. Discuss, specify, plan; then let it build.

AI agent rules: markdown files for Claude.md, ChatGPT, Copilot, Cursor, Windsurf, and more.

Local-first cost analytics for AI coding agents. See where your tokens and money go across Claude Code, Cursor, and more.

Personal AI assistant on Android — agent loop + tool calling + dual Chat & Telegram interface

Wiki-based retrieval for AI coding agents. 65× token reduction, +24pp Coverage@5 on SWE-bench Verified.

Flutter APK/AAB security SKILL.md for OpenClaw, Codex, Claude Code, and other AI coding agents

Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

Framework-agnostic AI documentation scaffold — one command gives any repo the shared instructions, memory, and gates coding agents need to work safely.

OpenTelemetry instrumentation plugins for JavaScript-based AI coding agents. Collect traces, tool calls, and LLM metrics from Claude Code and OpenClaw — zero code changes required.

Modular, agentic framework and MCP platform you self-host. Build and run your own AI agents, connect Claude Code, Claude Desktop, or Cursor as a native MCP connector, self-host your apps, and share over encrypted P2P — on hardware you own, with local or cloud models. Open source.

借鉴 Karpathy LLM Wiki 的求职文档 Agent skill，把零散经历沉淀成经历库，一键生成简历和面试逐字稿，支持 Obsidian 和飞书

Multi-agent deep research system with autonomous web/academic search, quality-gated retrieval, and structured report generation.

PawFlow (Platform for Agentic Workflows) Self-hosted agent runtime for real infrastructure. Run durable AI agents against your own files, tools, browsers, desktops, services, and workflows with relay-backed execution, shared context, multi-provider agents, and deterministic flows.

Kubernetes operator for the Hermes agent

camroll • an AI assistant for your personal camera roll 🎞️ • Personal VQA

AI-powered PR reviews running in your Cloud. Your models, your cloud, your rules. No code stored.

Semark converts PDFs, Office files, HTML, and images into RAG-ready semantic Markdown using MinerU and VLM/LLM review, with chunks, source maps, and automatic document splitting.

一个集微信小程序 + FastAPI 后端 + React 前端的 AI 内容创作全栈平台，支持热点采集、AI 内容生成（文章/视频/数字人）、多平台自动发布。

Coding-agent harness for continuous contribution — discovers, implements & validates your next high-fit change as a review-ready draft PR you decide on.

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.

Claude for Firefox - community browser extension with sidebar chat and automation

MCP based integration for HyperMemory

Free web search for AI agents — multi-engine parallel, smart re-ranking, zero API keys. | 免费 AI 联网搜索 — 多引擎并行、语义重排、零 API Key

Use WeChat to connect Claude Code

基于 RAG 与 Agent 的智能面试辅导系统，支持问答、模拟面试、工具调用和面试报告生成。

The identity provider for AI agents — registry, scoped delegation, in-path MCP enforcement, instant revocation, tamper-evident audit.

Open catalog of web skills for AI agents — search, add, and run reusable browser recipes with whatever browser your agent already has.

This project leverages Large Language Models (LLMs) and a multi-agent framework to analyze stock prices, gather relevant news, and generate comprehensive financial investment reports for companies.

CryptoAgents is a sophisticated multi-agent LLM framework specifically designed for cryptocurrency trading. It leverages specialized AI agents working as a coordinated trading desk to analyze crypto markets, conduct research debates, execute trades, and manage risk in the 24/7 cryptocurrency ecosystem.

Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".

[EMNLP 2024] FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents

ClawGuard is a comprehensive security toolkit designed to mitigate risks associated with autonomous agents, such as OpenClaw and other LLM Agents.

[ACL 2026 Main] MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools.

zk-autoresearch — autonomous LLM agent optimizing a production ZK prover via benchmark feedback loop. First known application of Karpathy's autoresearch pattern to a ZK proof system.

Transaction Tokens (RFC 8693) for Kubernetes — seal identity, context, and authorization across multi-hop agent workflows via AgentGateway + ext_authz.

Official implementation of the paper "Guidance Graph Optimization for Lifelong Multi-Agent Path Finding", published in IJCAI 2024.

Desktop command center for managing multiple AI coding agent sessions across codebases. Multi-agent orchestration via MCP.

Multi-agent harness for building and maintaining a personal wiki based on your data.

A persistent management layer for Claude Code Agent Teams