Custom agents

Open-source macOS SwiftUI Codex client with local Markdown chat history, reusable context, Skills + Mods, and explicit local safety controls.

A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Claude Code, Codex, Antigravity CLI, Copilot.

🗂 ToolFS: A FUSE virtual filesystem for AI Agents, integrating memory, RAG & local data access with flexible MCP/tool chaining and a scalable plugin system

Local-first autonomous coding agent that plans, executes, validates, and finishes software tasks end-to-end.

Single-file web UI for NVIDIA DGX Spark — pull Ollama models, browse and download from HuggingFace, manage LiteLLM routing, and control SGLang, vLLM, llama.cpp, LocalAI, and ComfyUI. All from one browser tab.

AI agent engineering meets system design: Claude Code dynamic workflows, loop engineering (bounded evaluator-optimizer gates) and runnable workflow scripts, plus real-world architecture case studies (Uber, Netflix, Stripe) and 15 engineering-blog deep dives, as Mermaid and draw.io diagrams.

CLI + SDK to automate, scrape, and extract from the web — for AI agents and humans. Cloud or local browser, one command.

A productive AI coworker that learns, self-improves, and ships work.

Academic paper downloader skill: Scopus search + Unpaywall primary + optional Sci-Hub fallback

Open-source multi-agent AI platform for Formula 1 race replay, strategy simulation, and explainable race strategy recommendations. (work in progress, MVP in legacy branch)

OpenCode plugin: Ralph outer loop + RLM inner loop — iterative AI development with file-first discipline and sub-agent support

Official implementation of "Think, Then Verify: A Hypothesis–Verification Multi-Agent Framework for Long Video Understanding(CVPR'2026)"

Albert Heijn MCP server for AI assistants

Autonomous AI decision engine for OpenClaw — give your AI a brain that decides for itself

Model Context Protocol server for CyberChef — exposes GCHQ's "Cyber Swiss Army Knife" as AI-agent tools: 504 operations across encryption, encoding, compression and forensics, on MCP protocol revision 2026-07-28

Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7

Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.

Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.

AI 驾驶的自愈式 A 股模拟盘交易赛车 · Self-healing paper-trading race car driven by AI agents

QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with deterministic guardrails, 100+ tools, a real browser, smart vision & shareable live artifacts. Open source, Apache-2.0.

Spec-driven agent harness for Claude Code and Codex — five-agent pipeline (scope, plan, build, verify, learn) with an auditable proof chain.

跑在 Claude Code / Codex 之上的本地多 Agent 协作脚手架:一个人下指令,主 Agent 拆解分派给专职角色,共用文件级记忆层。作者自用的主要方法是接到飞书bot，你只需要跟飞书bot聊天他就能帮你干活了

Official documentation for Taskade — build apps, deploy AI agents & automate workflows on the AI-native platform. REST & Action APIs, MCP server, Genesis. Source for docs.taskade.com — typos & gaps welcome via issues/PRs.

A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.

MultiTable is an open-source AI agent framework and meta-harness that gives you a common orchestration layer over LLM providers

面向企业内部授权场景的 AI 代码安全审计框架。支持 redteam/full 两种模式，支持靶场集成验证，全程自动编排。适配 Cursor、Claude Code 及其他支持 Agent 调度的 AI IDE。

Patch Codex's missing features with agent skills.

An xcresult parser CLI for CI and AI coding agents.

AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 lines of Python.

[ICLR 2026] Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

Raycast extension for real-time Claude Code session monitoring with hooks-based state tracking

Koda is your ideal development partner.

Claude Code skill that applies Naur's Programming as Theory Building to coding-agent workflows.

InferSports Agent Skill — live Asian-priced football & basketball odds + scores. Read-only, keyless. Claude Code / Codex / OpenClaw.

A secure agent harness runtime and framework

My private AI tools and scripts

Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com

AI Operating System cho Cong ty 1 Nguoi Viet Nam — solo founder + 12 phong ban AI agents hop ban debate, ra quyet dinh, sinh tai lieu chuan luat VN. Chay qua Claude Desktop subscription.

TriLane: autonomous AI pentester and multi-agent security auditor for authorized gray-box testing of web apps and APIs. Built with Rust and Tauri.

Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.

Deep Research skill for Claude Code — 3-cycle multi-agent adversarial ensemble methodology

Continuously Looping Engineering Machines. docker-compose for Claude Code agents - persistent teams, 24/7, on any Linux host.

This is a generic knowledge agent for creating a RAG pipeline from source docs, etc.

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isolated contexts, minimal permissions, adversarial verification built in. Ready to drop in.

Learn Claude Code — 基于源码的完整技术分析文档集，15章深度解析 Agent Loop、工具系统、权限系统等核心机制

Tool to improve compiling proficiency for AI coding agents (i.e. Claude Code)

Mixture-of-Agents-X - utilizing the MoA framework in agentic coding tools.

An Agent with Semantic Memory. This is an experiment for Neuro-Symbolic AI

Production-grade Kubernetes operator for nousresearch/hermes-agent: declarative spec, security defaults, S3 backups, OCI auto-update with rollback, SSA-based GitOps coexistence, OpenClaw migration.

Open-source A-share AI research workstation — multi-agent analysis, simulated trading loop, personal knowledge base; runs fully on your machine.

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.

一款专注于慢性病管理的AI平台，通过多Agent协作问答、干预效果仿真预测、认知评估与训练、亲情账号关怀等核心技术，为慢病患者提供专业、个性化的健康管理服务

An autonomous agent for open-source repository management — triages issues, reviews PRs across iterations, watches your sites, and escalates only the decisions that are yours

Codex skill for generating editable Excalidraw diagrams, previews, web links and iterative diagram workflows.

Open-source community study guide for Microsoft DP-800: Developing AI-Enabled Database Solutions. Aligned to the March 2026 official blueprint. Covers SQL Server 2025, Azure SQL, Microsoft Fabric, vector search, RAG, MCP, and more.

🔥 CogitoAgent — An autonomous AI agent, cloud-driven but locally executed. It continuously thinks, automatically analyzes, and integrates practical tools like file management, code execution, web search, and database operations — secure and efficient.

The local-first second brain for your AI agents - measured, self-improving, and gated so it can't leak what you keep private. 13 Claude Code plugins, 21 skills, Ollama, Neo4j, Qdrant.

Revenue-first website analytics installed and verified by AI agents through MCP

A governance framework that establishes memory as a first-class system component with explicit policies, tiered credential management, lifecycle controls, and full observability

NFT pet game on Ethereum & Solana - mint, breed, train, and battle pets with Chainlink VRF-powered combat and on-chain progression.

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage (ACL 2026)

Digital Life · Life Engineering — A runtime framework for persistent, autonomous LLM agents

PoC for GhostCommit Attack: Steal secrets via a pull request pointing to an image

Mission control for every Claude Code session on your machine.

Open-source AI browser agent for web reverse engineering. Turn websites into browser-free API clients and crawlers with CDP, network tracing, and JavaScript analysis. | 开源 AI 浏览器 Agent（智能体）：自动完成网页逆向，生成脱离浏览器运行的 API 客户端和爬虫。

Excalidraw MCP server with real vendor-icon search & insertion (AWS/Azure/GCP/OCI/Kubernetes) for AI-built architecture diagrams — live canvas, 31 tools

Literature-fetching & citation-auditing skill for LLM agents (Claude/Codex) — 讓 AI 引用經得起追問:找文獻、查核引用真偽與支持度、文獻支撐寫作,防幻覺引用。

Example realtime voice agent built with Google ADK and deepagents

AI news tracking skill for Agents like Claude Code, Openclaw, and more. Tracks AI entities across 9 sources and generates daily structured reports.

Claude Code skill that prepares Indian Income Tax Returns (ITR-1/2/3/4): parses Form 16/AIS/26AS/broker statements, reconciles every rupee, compares regimes, computes tax + interest, and emits a portal-ready data-pack JSON for a browser agent to file.

Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with generated invariants in a Docker sandbox, and returns PROVEN / REFUTED / UNVERIFIED with a JSON certificate. Part of a verifier-gated, multi-model agent runtime.

Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.

Run the Pi coding agent in a persistent session with a mobile PWA secured by Cloudflare Tunnel and Access.

Fund Analysis Multi-Agent System (FAMAS) - 基于多Agent协作的基金深度分析、筛选与持续监控决策支持系统

通用个人知识库 vault，配合 cognition-hub Obsidian 插件与 Claude Code Agent 工作流，构成完整的认知生产管线。

Claude Code scaffolding and first steps for complex brownfield projects

从零手搓的 Coding Agent（ReAct + 工具 + 记忆 + 权限 + 上下文压缩 + 子agent + MCP），纯 Python/asyncio

A self-improving retrospective skill for Claude Code. One command makes your AI agents get better after every conversation.

AI Agent engineering and quantitative finance knowledge base: source-level architecture analysis, Agent-to-Agent protocol research, runnable code experiments, industry insights. Obsidian vault, ready to clone.

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

One-handed agentic remote for Flipper Zero. Includes custom macros, voice dictation, an offline claude code manual & more.

Open-source, local-first desktop for AI coding agents and document work. Run Claude Code, Codex CLI, opencode, and Grok CLI in isolated Git worktrees.

A graph-native simulation engine for building composable engineering simulations and digital twins.

System design from evidence, not vibes — reads your repo as the current architecture, runs the capacity math, compares structurally distinct candidates, and ships an interactive report. For Claude Code, Codex, Cursor, and other coding agents.

CPU-oriented Python library for discrete Active Inference experiments in radCAD and cadCAD: deterministic grid worlds, multi-agent transitions, generative-model helpers, and fail-closed validation.

A real-world agentic AI system that combines supplier, procurement, delivery, and cost datasets to generate end-to-end supply chain insights, risk analysis, and automated decision support using RAG + multi-agent orchestration.

An agentic workflow for autonomous engineering loops

Agently AI application development framework's official collection of agent skills

Native OpenCoven workspace for familiars, agent sessions, memory, tools, workflows, and local-first development.

Coordination and context layer for AI coding agents. Shared file locks, live patch sync, and portable project memory across Claude Code, Cursor, Copilot, Codex and Antigravity with rooms for team-wide collaboration. Conflicts prevented at the edit, not discovered at the merge.

SaaS template for Claude Code agents — SvelteKit + Postgres + Drizzle skeleton with auth, multi-tenancy, and production deploy. Bundles the agent workflow (CLAUDE.md, DNA, slash commands) that drives end-to-end feature development.

Local-first Electron cockpit for the Codex SDK, OpenRouter, multi-agent crews, and bounded computer access.

A multi-agent AI framework formalizing the Yang-Mills Mass Gap finite-lattice theory in Lean 4 without axioms or sorry.

A set of constraints for a self-evolving agentic system that will work on any LLM.

Autonomous agent loops for Hermes Agent: the autoresearch harness and the health/improvement maintenance loops.