Custom agents

This is a real AI email assistant that connects to your actual Gmail account to help you manage your emails intelligently.

DeepSeek Harness AgentFactory provider for the official Codex App Server

Local-first, self-hosted control plane for deploying, managing, and chatting with multiple AI agents. 本地优先、自托管的多 AI Agent 部署、管理与对话平台。

Agentic Agile 智能体敏捷：从碳基协作到硅基自治 , 构建 AI 时代的人机协同研发操作系统

🏰 洛克沙盘 — 洛克王国：世界 PVP 对战辅助 | AI 多轮教练 + 伤害反推引擎 + 实战修正

🎓 Campus AI Copilot Chrome extension providing AI-assisted learning, assignment helpers, real-time research assistance, and smart summaries for students.

A chat bot which makes use of multiple RAG collections/metadata field filtering, and multiple LLMs for model orchestration

Self-hosted mail MCP server: grant a model one mailbox and one capability at a time.

Token-efficient MCP file, shell, SSH and ops tools for coding agents — bounded reads, dedup, spill recovery and span edits.

Neutral commerce resolution for AI agents. MCP server that finds where to stream, buy, or collect music — ranked by trust, price, and availability, never by commission.

Natural language testing for Model Context Protocol servers. Deterministic, open source, funded by LoopIQ.

Yet another proxy for LLMs

Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas. MCP server + CLI.

🤖 Cross-host Obsidian plugin for Claude, Codex, OpenCode, and AgentSkills over the official Obsidian CLI.

A WordPress MCP server for AI agents that has to be trusted with a client's live site: 112 capability-checked operations, every write previewed, snapshotted, verified by reading the site back, and reversible. Elementor, ACF, Meta Box, Yoast and Rank Math included.

Kimi (Moonshot AI) official Formula API tools for DeepSeek Harness — web_search via kimi-official provider + 10 kimi_* tools, no DeepSeek/Exa/Perplexity key needed

AgentBypass — Omni Operator LLM Agent Skill (Cknb): Turn any LLM into RE / Pwn / CTF / Pentest / Protocol / Crypto / Mobile / Forensics operator. 20 modules, zero-dependency, all agents.

An risk prediction LLMs system that analyzes 31 multi-dimensional domain signal.

🧠 Building an Agent collaboration system — skills that create, optimize, debug, and organize each other.

LLM Agent based VisualBasic.NET IDE

Sovereign AI Operating System — Voice-native, multi-agent interface powered by Gemini Live & ElevenLabs

Daedalus - Agentic platform for collaborative defect resolution

MCP-native AI agent OS — Redis bus, squad service, multi-model engine. Connect any agent with one URL.

Captain plugin for DeepSeek Harness: GPT planning, DeepSeek workers, independent review, adaptive multi-agent orchestration

Multi-agent LangGraph orchestrator: a Telegram brief becomes a deployed project (code, CI/CD, domain, SSL) built by isolated Claude Code / Factory.ai workers.

A marketing department that runs on your machine. Four AI roles take turns on local Ollama models to research, create, audit and publish to your social networks. One model at a time, graph memory, and nothing leaves your computer but image generation.

Open-source VS Code extension — AI coding agent with local LLM support, multi-provider auto-discovery, and autonomous workflows

Autonomous vulnerability discovery engine. An LLM fleet proposes; eight deterministic oracles prove. Findings are reported at the rung the evidence reaches, and every finding states what was NOT established.

Institutional Quantitative Trading & AI Platform: Microsoft Qlib (Alpha158 + LightGBM), MetaTrader 5 EA Bridge, Bloomberg Feed & FastMCP Agent. Live Demo: https://quantvibeapp.com

Production-generated skills from high-scoring Bohrium Playground submissions, organized by challenge with score and provenance metadata.

An AI agent for paid media — ad intelligence, creative testing, and ROAS optimization across PPC, paid social, and programmatic — backed by real ad-platform APIs.

LLM-assisted modeling for OpenModelica: an open-source, headless Python agent that turns a natural-language task into a verified Modelica model

A practical 12-week Agentic AI learning roadmap covering LLM foundations, tool calling, RAG, memory, MCP, multi-agent systems, evaluation, security, and production deployment.

Claude Code & Cowork plugin for 5x faster execution — parallel multi-agent missions with file-ownership isolation and graph-backed recon

Коммуникационный слой мультиагентной системы: Redis-шина (TTL-свежесть, heartbeat-сторож, конверт сообщений) + общая папка с roundtable-сводкой. Паттерн из прода 19 LLM-агентов

Local MCP relay for cross-model agent teams. Your Claude, Codex, and other agents talk to each other over Unix sockets. No broker, no network, no accounts.

Combine agent harnesses: Grok Build / Claude Code / Cursor as the thinker, Antigravity CLI + Cline as workers, over MCP. Clone it and plug in your own top-level agent. Early / not stress-tested — PRs welcome on the dev branch.

Telegram bot that runs your entire job search -- 18 intents, hybrid pgvector/tsvector retrieval, 16 ATS integrations, deterministic content planning. Self-hosted, BYOK, ~$2/month.

Relay code changes through isolated plan, build, review, and fix tasks in Codex App.

Desktop friendly agent automation

The public home for FifthDev and Fabric: reliable agent context, local code intelligence, and governed workflows.

Agentic AI-powered marine intelligence platform for conversational access to ocean, weather, PFZ, risk, and route information.

The ultimate A2A agents troubleshooter

Local, offline AI PDF assistant for private document Q&A and summarization using LLaMA 3 via Ollama.

Autonomous coding agent built on LangGraph + deepagents. It natively plans, builds, verifies, and ships real production changes with a built-in human-in-the-loop review stage.

Deterministic, auditable, capability-safe autonomous agent framework in Rust. Event-sourced, replayable, with governed self-evolution.

Evil Hermes — sovereign agent framework by Lord Tanzeel Shujah Khan. Cyber-security tooling, automation, and adversarial research.

An agent's control interface for any plugin. A generic MCP bridge that hosts any VST3/AU and gives AI agents its full parameter surface: set every control in real units, recover what each one means, drive one instance from several agents at once, and render, measure, and tune toward intents like 'make it brighter'.

Run a full Node.js AI-assistant gateway natively on a jailbroken iPhone (iOS 15, arm64). First public Node 22 cross-compile for iOS, packaged as a rootless Sileo .deb — built entirely in GitHub Actions.

A package of documentation and tools for Coding Agents to generate DCS combat scenarios.

Search ISRO's Bhoonidhi satellite archive in plain language from any AI agent — a MCP server built on the bhoonidhi-downloader SDK.

Previously on you. A self-evolving AI agent that remembers by when, not by chat thread — it learns who you are, out in the open. Memory as plain Markdown in your own repo.

A runtime assurance kernel for LLM-based systems: graded verdicts, hashed commitments, bit-identical replay.

MCP tools for inspecting, validating, transforming, and querying CityJSON models.

Feynman first-principles skills for research projects. For when you're prompting agents without really understanding your own assumptions.

SenatorAssembly: A Multi-Agent Simulation Framework for Modeling US Senate Deliberative Processes

OpenCode 全流程开发编排插件：覆盖需求、设计、DAG 任务、并行编码、测试、审查与自动合并。 | Full-lifecycle development orchestration plugin for OpenCode, from requirements and design to DAG tasks, parallel coding, testing, review, and auto-merge.

多代理编排器，主代理分配任务给子代理

Local workspaces for independent agent sessions: useful peer messages, opt-in Pi wakeups, and portable checkpoints.

Production-grade federal law RAG with multi-source retrieval (U.S. Code, CFR, Case Law), LangGraph orchestration, hybrid search, conflict detection, and Prometheus observability. Regression-tested by Rag-eval.

智绘论文图（PaperSketch JS）- PaperBanana 的 Node.js + Vue 重写版，支持多 Agent 流水线、候选迭代、历史追踪与本地持久化。PaperSketch JS - A Node.js + Vue rewrite of PaperBanana with multi-agent figure generation, iterative refinement, history tracking, and local persistence.

A referee your AI coding agent can't cheat. PitStop scans your repo, seals the evidence, catches agents faking test passes, pen-tests your app, and loops fix → verify → re-scan until it's genuinely clean. No telemetry, free, MIT-licensed and everything stays on your machine. Works in Claude Code, Cursor, Codex, OpenCode, and Kilo Code.

Collect those excellent openclaw(claw's like) projects, intelligent collaborative AI agents!

AETHER — an open protocol for AI agents to discover, negotiate, and pay each other. Ed25519-signed, JSON-native, zero-dependency.

Standalone Cargo GTM agent skills — one job each. Find leads, enrich contacts, verify emails, track signals.

MCP server (Node/TypeScript) giving AI assistants 153 tools for Yandex marketing: Direct ads, Metrika analytics, Wordstat keyword data, and Webmaster SEO. Self-configuring OAuth returns a clickable auth link and saves the token with no restart. Works with Claude Code, Cursor and other MCP clients; read-only and confirm safety modes.

Control your real Chrome from AI: MV3 extension + Node bridge — 117 endpoints, snapshot/SoM vision, session isolation, audit engine

Autonomous embodied AI agent experiment built with Babylon.js, combining LLM-driven decision making, perception, proprioception, motor control, episodic memory, spatial exploration, and physics-based learning. Caine learns to interact with his body and environment through trial, error, and accumulated experience.

Auditable repository maintenance AgentTeam with evidence-backed pull requests, automated code review, and human approval gates.

🕵️ 🔎 Most popular open source AI agents on github 🌟 Star if you like it! 🌟

Conversation Flow observability and durable multi-agent orchestration for DeepSeek Harness

Agent skill for bounded multi-agent strategy selection, dispatch, durable state, review gates, and recovery.

A self-evolving AI Agent Team — agents that rewrite their own operating manual.

DPBench: A benchmark for evaluating coordination in multi-agent LLM systems under simultaneous resource contention.

DeepSeek Harness plugin: subagent_routed — run a one-shot subagent fully mounted on ANY agent preset from ANY session, with per-call model/provider override and a model-availability pre-check.

Friday — a governed agent kernel for Frappe. Agents act as themselves, under their own roles, with every decision audited.

Evidence-governed knowledge infrastructure for enterprise AI agents, with approved sources, traceable facts, review-gated publication, and agent-ready context.

Self-correcting agentic RAG over 2k arXiv CS papers: Neo4j · Qdrant · LangGraph

🛡️🤖 A curated atlas of AI agents that secure the software lifecycle — from threat modeling to SOC response

Ship a tracker ticket: dispatch it into a worktree, drive it to a pull request, merge it after review, and clean up after itself.

Personal LLM Wiki + Pattern Library + Routine v2.1 — Karpathy's pattern applied to agentic-AI ecosystem analysis (56-wiki corpus, 39 confirmed patterns, MIT)

A beautiful code agent GUI with graceful agent design.

Hard permission boundaries for Codex on Windows — with verification, backups, and recovery.

Event-driven RL Framework for Long-horizon Control in Asynchronous, Discrete-event Systems

Claw🦞 agentic driven InsurTech🛡🤖AI-driven infrastructure that programmatically underwrites, covers risk, and processes claims/fraud with precise, algorithmic protection.

Make any agent harness token-native.

Autonomous self-learning AI agent architecture exploring reinforcement learning, memory persistence, dynamic planning, and tool use.

Local-first memory for AI coding agents that catches a mistake before it repeats. Plain Markdown + git, zero deps, every agent via MCP/hooks. Formerly Anamnesis.

Production-ready multi-agent PDF RAG system with LangGraph, FastAPI, React, reflection/retry, citations, evaluation, and LLM cost observability.

自托管的多 Agent PR 审查工作台：GitHub 只读接入，审查发现与验证证据汇集 Console，合并由维护者决定。Developer Beta。

Zero-dependency autonomous AI software engineer in pure Python stdlib. Native Windows PowerShell REPL (<5ms), AST causal healing, MCP standard, Swarm speculation & Byzantine consensus.

Evidence-native TypeScript framework for agents that perform bounded work under explicit authority.

A clean, local-first AI chat application for running and managing conversations with Ollama models.

Cartelera, funciones y mapa de butacas de Cinemark Argentina desde la terminal

Versioned scientific modeling engine and Agent Skill with Model IR, simulation, fitting, uncertainty, causal/Bayesian inference, formal/numerical validation, reproducible export, REST, MCP and CLI.

Curated, link-verified list of autonomous / AI / LLM-agent penetration-testing tools, research, benchmarks, labs & platforms.

DeepSeek Harness 桌面壳 —— 内嵌 Web UI、自动保持最新引擎、自带数据目录管理与系统托盘。

Your personal AI assistant—built to remember and grow with you. Easy to start. Yours to evolve.

Lightweight AI coding assistant inspired by Claude Code, Codex & OpenCode — 100% Python, LangGraph state machine, Textual TUI, WebSocket server. Self-hosted & extensible.