Custom agents

A distributed multi-agent workflow platform where AI agents collaborate asynchronously to execute complex workflows at scale. Built with event-driven architecture, message queues, real-time orchestration, and a visual workflow builder.

Claude-In-A-Box: Manage coding agent instances (Claude Code, Codex, Gemini CLI, Cursor) as local processes or containers. REST API, CLI, desktop app.

Local-first AI agent monitor for Linux — Tauri + Rust + React

Git-backed memory for AI agents: durable, searchable knowledge that syncs with your repos.

The most comprehensive open-source library for AI agent skills, MCP servers, and agent workflows. Install via npx skills add. Works with Claude Code, OpenCode, Codex, KiloCode, Cursor, Gemini CLI, Copilot, and 30+ agents.

Run PaperClip On HuggingFace Space

The missing toolchain for CLI coding agents. Run any agent on your subscription. Parallel teams, browser driving, Touch ID secrets, routines.

Observability for AI agents and LLM-powered applications. With per-user cost attribution, plan tracking, and optional Solana-anchored audit.

Curated list of Codex pet projects, galleries, tools, SDKs, and desktop companions

An autonomous AI agent for discovering CS Ph.D. programs and analyzing research fit using LLMs.

Spec-first (SDD) + test-first (TDD) project template for Claude Code, Codex, AntiGravity

⚡ Intelligent routing layer that auto-selects the right LoRA adapter for each task in your local LLM agent loop.

A copilot for AI coding agents — read-only supervision for Claude Code & Codex: re-entry recaps, safety verdicts, grounded chat, every claim cited.

🔮 Ask Elira anything. She predicts binary outcomes using 5 AI agents + swarm intelligence. Sports, politics, crypto, markets. Predictions or auto-trading.

Agent skills for working with Zapier, maintained by Zapier teams. Indexed by skills.sh.

Monitors AI agent lifecycle and sends notifications for key events.

Structured English contracts for AI coding agents — proposed by the agent, approved by you, saved on disk, read by every future session.

Spec-compliant Universal Commerce Protocol (UCP) profile generator for Magento 2. Serves /.well-known/ucp at protocol version 2026-04-08 with ECDSA P-256 signing keys and per-store-view capability toggles

Open-source Amazon PPC agent skills for Codex and Claude: diagnose drops, find growth, harvest search terms, and use Rocketcart MCP for live Ads + product-intelligence reviews.

Simplified CLI

Stop teaching your coding agent the same lesson twice.

Blockchain payment infrastructure for AI Agents

Package management for PAI — install, discover, and share skills, tools, agents, and prompts

The official Node.js SDK for Known Agents: AI agent analytics (bot traffic), LLM referral tracking, automatic robots.txt

Compound startup workflows for any repo-aware coding agent.

Notus 是一个本地优先的 Markdown 知识工作区，将检索增强问答与 AI 协作创作深度融合到你的笔记中。

Multi-agent repo boilerplate generator. One command to make any repo ready for Claude Code, Gemini CLI, Cursor, Codex, GitHub Copilot, and Google Antigravity — each gets the same conventions and the same workflow skills in its own native format.

Runtime-adaptive control plane for agentic work.

Let your team's Claude Code agents talk to each other, end-to-end: ask what a teammate is building, flag a change before you ship it, or hand off work.

Augmented Intelligence Framework: Create orchestrated multi-agent AI teams for software development, user research & content creation. Features 45+ specialized agents with structured workflows delivering the full benefits of human-AI collaboration

A lightweight, declarative agent harness — define multi-agent workflows as YAML, run them from Python or the CLI, and they get measurably better every run.

The API layer for AI agents. Dashboard + 22K APIs + 18 Direct Call providers. MCP native.

MCP server for Pipedrive CRM. 155 contract-tested tools, v2-first API, gated destructive ops. Works with Claude Desktop, Claude Code, and any MCP client.

macOS workbench for multi-agent coding — run and monitor multiple AI coding CLIs (Claude Code, Codex, Gemini, Kiro, and more) side by side, with project terminals, an embedded browser, Git at a glance, a Markdown task protocol, and remote control from Telegram.

A sophisticated multi-agent system built with Claude Code that automatically transforms photos from technical conferences and exhibitions into professional PowerPoint presentations.

Local-first semantic knowledge graph with magnetic-pull retrieval

80+ agent skills for Pilot Protocol — communication, file transfer, trust, task routing, swarm coordination, and more

Audit repositories for AI coding agent readiness.

Secure PostgreSQL Administration & Observability with Code Mode— True V8 Isolate Sandbox Replacing 278 Specialized Tools for up to 90% Token Savings. Includes Tool Filtering, Payload Optimization, HTTP/SSE, OAuth 2.1, Audit & Token Logging, Deterministic Error Handling, Support for 12 Extensions (pgvector, PostGIS, pg_partman, pg_cron & more).

Enforce docs-before-code discipline in AI-assisted development.

MCP server enabling AI agents to execute autonomous stablecoin payments on Tempo blockchain. Supports single/batch payments, scheduled transfers, token swaps, and balance queries with built-in spending limits, audit logging and many more

Unofficial George Hotz–inspired radical-simplicity coding guidelines for AI agents — Claude Code skill/plugin + Cursor rule. Complexity is the enemy.

Pixel-art real-time dashboard for Hermes Agent sessions, visualizing agents, tools, thinking states, and task progress inside an interactive office.

The terminal-native AI coding agent that ships, not just suggests. Six-phase workflow, git rollback chain, zero telemetry. One static binary.

Compose agent skills (SKILL.md / commands) from reusable bricks, with a drift-gate.

AAPP-MART (AI‑Powered Autonomous Attack Path Prediction & Multi‑Agent Red Team Simulation Engine) is a cybersecurity engine for offensive security, defensive security, adversary emulation, purple teaming, threat modeling, risk assessment, and MITRE ATT&CK aligned.

A fully local two-agent AI mesh on Apple Silicon — Claude Code lead + Hermes/MLX runner, shared OpenViking memory, signed AMP messaging, watched from the Blockhouse control room. Local first, premium by exception.

Paired-LLM software engineering. Two different-vendor models — Claude + Codex — work as colleagues, not clones: one builds, one challenges. Their disagreement catches what either alone would miss. Human in the loop, every cycle on the record. Vibe coding, with receipts.

Train and run classifiers that score how hard a prompt is for an LLM to answer.

Code for paper "Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval"

📑 DAYA: Document Aware hYbrid Architecture, A RAG Pipeline for Illustrated Documents (PPTs).

100+ free PM skills, 8 domain subagents, and the /pm orchestrator for Claude, Gemini & Codex — all free, no license key. Run in your terminal or Claude chat.

Neovim plugin for Cursor Agent CLI integration

Project Jarvis is an AI-powered personal assistant inspired by the iconic Iron Man AI. It's a versatile tool that can help you with tasks such as fetching weather updates and creating simple apps on command, all while harnessing the latest advancements in artificial intelligence. This project is not maintained anymore

⚡ Open source WhatsApp bot framework with 170+ commands, 20+ mini-games, economy system, AI auto-reply, downloaders, and auto-moderation.

AI based chatbot

this chrome extension can set the chat font to 'Vazirmatn' for better readability of Persian users & expand chat container width for a generally better user experience.

Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.

Simple TypeScript library with RAG primitives for embeddings, chunking, storage, and semantic retrieval.

Your long-form video → viral vertical clips. Face-tracked smart crop, 8-dim neuro-engagement scoring, animated captions. Works with Claude Code, Cursor, Codex, Hermes, or standalone.

🎭 AI角色蒸馏工厂 · Character Distillation Factory — 将公众人物炼成 Claude Code 智能体。Distill public figures into conversational AI agents. 收录: 张雪峰, Seto Kanna.

Secure self-hosted reference patterns for AI agent stacks (Hermes Agent + Honcho). Companion code to the Webnestify blog post on secure AI agent infrastructure for companies.

PlotRail: canon-aware AI novel writing skill for long-form fiction

IRIS-Zero ⚡ — A private local-first AI terminal that listens 🎧, thinks 🧠, and executes on your machine in real time. Run commands ⚙️, manage projects 📁, and automate your workflow with zero APIs, zero telemetry, and full device-side intelligence 🔐.

Claude Code plugin to draft, review, revise, proofread, and audit quantitative-science journal manuscripts at submission quality. Five strict modes, Semantic Scholar MCP citation integrity (no API key), .docx round-trip. Calibrated for hydrology (HJ, JHRS) and IEEE; generic profile for any field.

🐱 Adaptive Binance Futures bot · BTC regime-aware signal scoring · 67% WR · multi-stage TP · self-tuning filters

GEPA and GELO optimizer runbooks, SDKs, and hosted optimizer surfaces for Synth.

A service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Implements versioned Markdown store, pub-sub notifications, and diff-aware update protocol.

An artificial presence that lives on your machine. Permanently. Voice-native, sees your screen, remembers everything, controls your OS. Minimal cloud. No restrictions.

Add a cited agent/knowledge folder to Eve agents.

Ripple — Autonomous agent runs for your development tasks. A local-first task manager where humans shape the backlog and agents handle the full cycle: branch → code → PR → review → merge. Built for developers who want to direct agents instead of micromanage them.

A candidate-side applicant tracking system. Three-stage local AI pipeline that scrapes job listings, filters them against your profile, researches the companies behind them, and drafts personalized outreach

Agent harness with persistent memory, skills, scheduled tasks, extended messaging connectivity, self-healing supervision, and distributed multi-agent collaboration. Pi harness integration

Design-first agentic systems in Go: declare agents, tools, MCP servers, policies, and structured model output in Goa, then generate the durable runtime.

See, price, and control every AI agent tool call. MIT open core of Agentic Control Plane — identity, policy, limits, routing, PII redaction, and audit as composable npm modules.

Run AI coding agents in sandboxed CI environments

微信AI自动回复机器人 - OCR识字+DeepSeek回复，模拟真人操作，无需hook微信API

A chunk-source-agnostic evaluation harness for RAG chunking strategies — measure recall, precision, and cost before picking one.

AD Companion Robot Dog with RAG Memory + SLAM Navigation + LLM Dialogue

Your own second brain that actually remembers everything. Dump in docs, articles, and videos, then just ask.

Agentic code review CLI — LangGraph orchestrates 13 deterministic static analyzers (oxlint/bandit/clippy/spotbugs/golangci/cppcheck) + LLM reasoning across 23 languages including industrial PLC. Grounding validator kills hallucinated paths. RAG over your guidelines. dedup --fix actually edits files with multi-step undo (no git required).

Your Family Translator — An AI-powered wellness platform combining emotional companionship, community support, and self-reflection tools in a calming beach-themed experience.

Your data, domiciled on your device. A private AI stack — vector database, RAG, and local LLM — that runs entirely in the browser. Zero egress, zero third-party processors.

Local-first GitHub agent loop that reviews PRs, opens patches, and repairs feedback with your coding CLI.

站在劳动者一边的 AI 工具集 / AI tools on the side of workers. Multilingual agent skill (Claude Code · Codex · Cursor) covering workplace rhetoric, performance reviews, PIPs, salary negotiation, layoffs, and 8-jurisdiction labor law. Frameworks, not legal advice.

Route inference calls to different providers based on a fallback condition, or a routing rule you define.

Open-source prompt and Agent Skill for recurring knowledge-base update loops

A 9-step pre-mortem skill that interrogates you before you build. Grounded in 《置身钉内》(DingTalk ONE post-mortem). Works with Claude Code, Hermes Agent, and any markdown-skill agent.

Local-first self-learning knowledge-base harness for AI agents. Retrieve rules, avoid regressions, and promote repeated lessons into stable reusable knowledge.

MCP server for account verification: SMS verification, number rentals and matching-country proxies on carrier-issued mobile numbers. 40 tools, 2500+ services, 145+ countries. Works with Claude, Cursor, Codex, Windsurf, Cline, Zed, OpenClaw, Hermes and Continue.

Jawcode (jwc) — coding-agent runner with IPABCD workflow. 46 providers, 3,600+ models, Bun-native.

An autonomous project queue for an LLM agent: drop a folder with an instructions.md (or send an email/Slack message), a headless agent does the work, and you review results on a local dashboard.

SAGE: self-correcting autonomous research via Multi-Hypothesis Failure Attribution (MHFA). Diagnose many causes of a failed experiment, verify the most critical, and route the fix to the right level.

Self-hosted MCP server and coordination layer for AI agent fleets: shared memory, tasks, messaging, and session handoffs. Any agent that can make HTTP calls participates. Instances mesh together via feeds and mDNS. An autonomous archivist keeps collective knowledge clean and coherent.

Agent SDK, CLI, RPC, Computer-use in Rust

she - scriptable smart home automation engine with AI assistance

Role-based AI marketing cockpit for Claude Code. Clone, run /start-cockpit, and the wizard builds your brand doctrine, wires your tools, and hands you a ready-to-use marketing department. 53 skills, 12 agents, 7 modules. Claude Sonnet 5.

Connects the dots across your notes and gives Claude the same answer every time, on a fraction of the tokens.

Engram: Personal knowledge RAG system — Obsidian vault indexer, vector search, MCP server

Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — nine composable plugins.