Custom agents

A curated list of voice AI agent frameworks, tools, resources, and best practices

A composable library of skills and rules for AI coding agents. Covers repo memory, long-horizon execution, multi-agent coordination, TDD, security review, and delivery automation.

Agentic AI Use Cases with pgvector, Aurora PostgreSQL and Amazon Bedrock

An open-source framework for reduction of overfitting of DRL agents in Finance

100 Days of Code | Daily Challenges | Beautifully Crafted Designs | Created for Full-stack/Frontend/Web Developers - Vibe Code with AI.

ZenModel is a framework for building LLM applications with agentic workflow

Virtual Assistant

🤖🔎 STREAM: Search with Top Result Extraction & Answer Model 📈📝 REASON Docs Writing Agent 🚜📜 Tractor the Text Extractor 🔤📊 SEEKTOPIC

This is just the submodule of browserOS agent; MAIN REPO: https://github.com/browseros-ai/BrowserOS

Working repository for common AI Card standard

Whiskey AI lets you create autonomous AI agents without code. Connect APIs, automate Solana actions, launch tokens, run workflows, scrape data, monitor markets, post on Twitter, and trigger actions instantly. Build complex automation with simple natural language—no coding needed.

AI 文献检索与综述 Agent：支持多源检索、代码仓库定位、开放 PDF 下载、证据链与中英双语报告。

Implementation of Single-Agent and Multi-Agent Reinforcement Learning Algorithms. MATLAB.

StarCraft II Multi Agent Challenge : QMIX, COMA, LIIR, QTRAN, Central V, ROMA, RODE, DOP, Graph MIX

Open-source DSR research workflow template, work with Claude or other AI agents.

A sophisticated biologically inspired memory system for AI agents. Provides organic, high quality, persistent memory with self-maintenance strategies.

A TavernUI Character extension for oobabooga's Text Generation WebUI

Production-grade API to give your AI agents long-term memory without the boilerplate.

My LLM agent learning

LLM-powered agent memory with 6-category classification and L0/L1/L2 tiered structure

Code for running the implementations proposed in: Westny, T., Oskarsson, J., Olofsson, B. and Frisk, E., "MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs", IEEE Transactions on Intelligent Vehicles

A highly flexible AI Agent-driven EVM smart contract vulnerability detection framework

Open-source Model Context Protocol (MCP) server for JazzCash — Pakistan's largest mobile-money platform. Hosted Checkout, Mobile Wallet charges, inquiries, and refunds for AI agents.

A library of rules for the Cursor IDE, providing organized instructions for the Agent Composer LLM backend.

The way AI coordinates and transacts. Routing and settlement layer for your agent economy.

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

Claude Code Agentic Harness

Code accompanying the paper "TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play" (AAMAS 2023) 足球游戏智能体

Workshop "Build a Retail Copilot Code-First on Azure AI": attendee and presenter resources.

Compass is a context engine that builds a knowledge graph of your organization's metadata, capturing entities, relationships, and lineage across systems and time, making it discoverable and queryable for both humans and AI agents.

Unified Claude Code workflow: Superpowers + Beads + Templates. 413+ specialist agents on-demand.

A web app for rapidly prototyping AI agents and the lightweight web UIs that wrap them—build flows, preview interactions, and share agent-driven experiences without lock-in.

基于三省六部架构的 AI 多 Agent 协作系统 · Windows 优化版

Clawdbot skills for agentic coding workflows - ACFS stack, cloud CLIs, and dev tools

基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。

The Autonomous AI Writing Agent — a secure, author-focused AI for fiction and nonfiction authors (Planning, Revision, Promotion, and more)

这是一个基于 PyTorch 实现的连续动作空间 PPO（Proximal Policy Optimization）算法，专门用于多智能体(无人机/无人车)强化学习环境（MPE - Multi-Agent Particle Environment）。

AI Agent Orchestration Kanban Board — Route tasks to Claude Code, Codex CLI, and Gemini CLI with role-based auto-assignment and real-time monitoring

A macOS desktop app to monitor your Claude Code, Codex, OpenCode AI coding agents in real-time with voice or bell notifications. Easily jump to a conversation in any editor or terminal! Shows RAM and CPU usage for every running session and lets you code Stale or Idle chats that are wasting memory with 1 click!

本项目是一个基于 LangGraph和大语言模型（LLM）实现的 Agentic RAG (检索增强生成)系统。它融合了动态查询分析和自我纠错机制，能够根据用户问题的复杂度智能地选择最优的策略（直接回答、向量库检索或网络搜索），并对生成的答案进行相关性评估，从而实现更高质量的问答效果。

WordPrerss Theme & Plugin Development Skills for AI Agents

A persistent, local-first AI development daemon built in Elixir/OTP. AST-level code intelligence, Property Graph, runtime BEAM introspection, and semantic search — all via a 80+ endpoint REST API.

EmbodiedAgents is a fully-loaded ROS2 based framework for creating interactive physical agents that can understand, remember, and act upon contextual information from their environment.

An agentic framework for autonomous protein design

SMART is an efficient soft-tool that bridge the gap between Multi-Agent Path Finding (MAPF) and real-world application. More details can be found in our paper: Advancing MAPF towards the Real World: A Scalable Multi-Agent Realistic Testbed (SMART) [1].

jarvis ai for Termux;)

Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval

AI-ML Companion: an interactive platform to learn AI & ML by watching it work - 28 tracks, 400+ modules, live visualizations - plus 20+ end-to-end real world projects from classical ML, DL, Computer Vision to production LLM & multi-agent systems.

An Agentic Skill System for Antigravity, transforming Spec-Driven Development into autonomous AI capabilities for the entire SDLC.

GGUF Loader with its Agentic Mode, and floating button, ai Models | Open Source & Offline. Mistral, Deepseek, llama, gemma, qwen

M.A.R.I.N.A GPT a powerful, evil brother of WormGPT.

AI-powered Zotero research assistant — MCP server + agent skill

Agents that do the work and show it.

Public docs, comparisons, and clone-ready kits for the AI-native workspace. Not the product source — issues welcome.

Android native AI inference library, bringing text, image, video, STT, TTS inference

Open-source AI marketing skills for coding agents like Claude Code, Cursor, and Codex. Do SEO, copywriting, competitor research, ad campaigns, marketing strategy, and more.

Product skills for AI agents — discovery, strategy, prioritization, and PRD writing

Visual Studio 2026 vide-coding extension: works with Claude, supports auto mode, bash/greb/glob, smart read/write/edit tools, sub agents, theming and more

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Bricks is the open-source, fully local alternative to Clay.com. It combines AI agents, advanced web scraping, and Puppeteer automation to turn raw CSV data into actionable business intelligence — without subscriptions, vendor lock-in, or sending your data to the cloud.

Use Codex and Claude Code with COMSOL via sim-cli: .mph inspection, live Desktop sessions, bounded execution, artifacts.

🧠 Multi-Agent AI System running 100% offline using Google Gemma-4 models. 5 specialized AI agents collaborate in infinite loops for brainstorming. Features: Dynamic VRAM swapping, 4-bit NF4 quantization, WhatsApp-style RTL UI, live token streaming, AI-powered agent customization. Built with PySide6 + PyTorch + Transformers.

Benchmarking LLM agents on real-world hardware bug repair tasks

10 AI agent skills for Claude Code — waterfall email enrichment, TAM building, signal discovery, job change detection, and outbound automation. Powered by Deepline CLI with 28+ GTM data providers.

Hello-AI是一个面向小白的 AI / LLM 学习入口平台：把 AI 基础、提示词、工具使用、RAG、Agent、部署、评测和安全常识串成一条能走通的路，并提供案例、练习和可复现项目让小白把这条路走通。

Claude Code on your laptop and remote dev boxes, in one web page. Sessions keep running when SSH drops (no tmux), each session's changes get their own diff, plus tasks, notes, and memory. Self-hosted.

It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.

Tired of paying for frontier AI models? Break free with this guide to 100% local, private LLM code generation on Apple Silicon. Optimized for 24GB+ Macs, it uses Ollama + Cline to build a disciplined, free agentic workflow. Learn to write system rules, configure custom Modelfiles, and run strict two-layer test suites.

TraceBrain is an open-source trace management platform for observing, governing, and improving LLM-based agent workflows.

Moved to EKKOLearnAI/hermes-web-ui; this repo is kept for historical releases.

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host runs your checks, a different model reviews, and every run ends with a CI exit code and a signed receipt.

A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard / core / full presets). 12 agents, 19 skills, 15 hooks, 6 rules, with reasoning behind every decision.

AI长篇小说工程化写作流水线 — SQLite记忆、21道Guard门禁、Agent陪审团、防幻觉检查、多小说独立数据库、人工味质量层

Team of specialized AI agents that collaborate through a spec-driven development process. Full Stack Developer parent orchestrates dynamically sized pools of specialists: Coding, DevOps, Review, and Solutions Architect agents.

Interactive documents from Markdown. Extends MD with forms, approvals, webhooks, and more — built for next gen apps

MCP and REST control plane for AI agents to operate creative software: shared Rust/Python runtime, multi-instance gateway, CLI, skill discovery, and studio workflow infrastructure for DCC-MCP.

Pilot coding agents (Claude Code, Codex) and monitor their telemetry from one cockpit.

Cognee Rust - fast and performant AI memory engine

Perseus Vault — durable, encrypted, time-aware memory for AI agents. One Rust binary, one file, local-first, MCP-native, MIT.

Fast, multi-modal context for agents

轻量全平台 SSH 客户端（Windows / macOS / Linux） — Go 原生并发 · 毫秒级终端 · 远程文件管理 · 系统探针 · 云端加密同步 · AI 对话 · MCP 智能体集成，无需服务端 Agent

The CUSTODY(TM) Framework for AI Agent Containment

【EMNLP 2026 Demo】A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

GTM agent skills for Claude Code, Codex, and GitHub Copilot: sales, marketing, SEO, RevOps, and customer research playbooks with templates.

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

Shared memory for your AI agents: a fact one agent writes on one machine is there for the next agent and the next machine, with no server in between. AGPL-3.0, alpha.

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline on Windows, macOS, or Linux. No installs, no internet, just plug and play.

Understand your agent's decisions

ACP agent in TypeScript that uses the Z.AI / Zhipu AI GLM Coding Plan models (GLM-5.3, GLM-5 Turbo, GLM-4.7) as the reasoning core

121 скил и 49 правил для Cursor IDE: агент собирает исходники 1С (метаданные, формы, расширения, роли, СКД, обработки) из компактного JSON и разбирает обратно. Базовые операции - без Конфигуратора.

DeepSeek Harness (DSH) 插件精选目录 — 14 类 280+ 个社区插件，覆盖 MCP / Skill / TUI / 多 Agent / 上下文记忆 / UI 皮肤，点链接直达仓库。Curated directory of dsh plugins for DeepSeek Harness.

The team harness for AI agents

[RESEARCH PREVIEW] The open & extensible cybersecurity harness - by the Swiss Applied AI & Cybersecurity Research Lab.

Juniper🌿 is an autonomous agent that watches pump.fun token volume, bonding-curve migrations, and surfacing statistically favorable windows to trade.

DeepSeek V4-Flash Vision Video RAG 让 AI 真正"看懂" 一段视频，然后你对它提问：它告诉你答案、答案发生在 第几分几秒，并切出那一段的可播放片段和关键帧给你核对。 基于 DeepSeek 视觉大模型 deepseek-v4-flash-vision-exp 的视频理解与问答 （video RAG）agent skill。先按时间轴抽帧阅读、建立索引（一次性），再对问题做 本地粗筛 → 视觉精排 → 深读回答；回答带 [MM:SS] 时间戳引用，自动生成 自包含 HTML 预览页（内嵌可播放片段 + 关键帧 + 答案），双击浏览器即看。

Behavioral testing for AI agents.

Circuit design assets, SPICE fixtures, and an auditable Agent workflow

Paper artifacts, figures, aggregate data, and share cards for the DXRG paper: What LLM Trading Agents Actually Do in Production (six months, two fleets, 231,638 recorded turns)

Self-host your Obsidian vaults: a web UI for you, MCP for your AI agents. No Obsidian, no plugins required.