Custom agents

Ruki - a minimal Windows desktop AI assistant you can teach

Self-hosted AI agent that can't say "done" without proof — evidence-gated task contracts, self-distilled skills with auto-rollback, multi-channel.

A production-grade skill for AI agents like Openclaw, Manus, & more to interact with personal data through the Claw Agent Protocol.

A personal AI agent for Windows that researches, remembers, watches, and ships code - voice or web chat, any model. Second-brain memory, deep research with cited reports, inbox watches & scheduling, PC/Discord/email/calendar control, and Claude Code as a pair-programming teammate.

The project contains code and resources for a modern AI-powered Finance Bill chatbot built with Next.js, Groq, and the AI SDK. It provides a streaming chat interface designed to help users interact with Kenya Finance Bill content through a fast, responsive, and context-aware assistant.

CRASS is a full-stack web application built with React.js & Supabase for AI-powered code review & security scanning. Features project uploads, real-time AI suggestions, security reports, analytics dashboards, and a sleek, responsive UI.

Introducing AirLedger, an innovative AI-powered bookkeeping assistant designed to revolutionize your financial management. This intelligent tool automates financial tracking, data parsing, and reporting, all while seamlessly adhering to Swedish accounting standards. Simply interact with AirLedger by speaking, writing, or uploading receipts and i...

⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣！超级智能体派对 = 自托管neuro sama + openclaw!

Persian-first AI personal finance assistant inspired by Cleo AI — private, local, RTL, with manual budgeting, expense tracking, savings goals, admin panel, and AI financial chat.

Workbench - Local-First AI Task Runner Build automations by chatting with AI. No cloud, no subscription. Ask AI to create tools, chain them together, and automate tasks - all on your machine. Includes 11+ built-in tools, plugin system, and MCP integration. Local-first. Open source. Yours to extend.

Relentless Project Manager — Claude Code plugin that prevents drift and keeps you on task across LLM-assisted development sessions

Annotate any web page, and drive it from an AI agent — a browser-automation MCP server with an in-page overlay HUD. Your annotations survive cross-origin navigation.

Local safety-gated MCP bridge for AI agents and Outlook mail & calendar: metadata-first reads, explicit content, reviewed sends, guarded cleanup.

LLM Security & OWASP LLM Auditing Framework

COdo — a terminal AI coding agent in Go. Streams LLM responses, edits code, runs commands, and spawns sub‑agents from a fast, single‑binary TUI. Built on Bubble Tea, with multi‑provider support, MCP, LSP, and SQLite persistence.

Hardened MCP server for TrueNAS SCALE. 270 safety-tiered actions over WebSocket JSON-RPC, single hierarchical tool, fail-closed registration gate, layered response filtering. PolyForm Noncommercial.

Faithful web research for Claude Code — a folder of clean, cited markdown, not a black-box answer. Aggregation, not synthesis.

Production-ready context database and MCP server for AI assistants. Provides code intelligence with hybrid search, call graphs, impact analysis, and semantic search for Cursor, VS Code, and Claude Desktop. Docker-first, 248 languages, auto-indexing.

Generate studio-quality audio with this CLI tool featuring ACE Step 1.5 XL models and an automated, dynamics-preserving mastering chain for lossless FLAC output.

MCP proxy in front of the GitHub MCP that returns JSON schemas instead of raw responses. Built on json-schema-sketch.

Local dashboard for running multiple AI coding agents in parallel. Claude Code + Codex, agent-agnostic, keyboard-first.

A Claude Code skill that keeps your project's memory library auditable, named consistently, and free of drift — for months, not days.

Build full-stack applications with an autonomous IDE using an agent swarm architecture powered by the Kimi 2.6 model.

A highly resilient, autonomous LLM agent built for Google Apps Script. Features granular RBAC, hierarchical method blocking, secure network sandboxing, and intelligent middleware (auto-pagination & latency resolution) to execute complex Google API workflows safely via MCP schema discovery.

面向中国 A 股研究的 Agent Skill：公告、财报、研报解析与因子候选生成

OpenClaw skill for scraping ChatGPT, Gemini, Perplexity and Grok responses. Built for AI agents and GEO monitoring.

Autohand Routes - the model router built for coding agents: policy-driven, provider-agnostic, and battle-tested aross millions of sessions.

Repository for the paper "A Context-Aware Multi-Agent Approach to Enhancing User Story Management in Agile Software Development", submitted for RESFQ2026

Portable, inspectable knowledge bundles for LLM agents.

A.M.Y (Autonomous Mind Yield) — autonomous scientific research system. 94 tools across 23 domains, cryptographic provenance, multi-agent paper pipeline (Ranking + Reflection), Apache-2.0.

Behaviour trees for AI agents. Define agentic workflows in YAML, drive deterministic agent runs from a CLI works with any agent, Claude, Codex, Copilot, Gemini etc.

Sovereign single-binary knowledge mesh for coding agents (MCP): index, search and serve your notes + code as context. Fair-code (no reselling).

Turn a book or document into a modular Agent Skill pack: atomic skills, combo workflows, a router, references, and validation.

AI-powered research idea generation through adversarial debate. Trains a calibrated judge on 50K real reviews, then uses a 3-agent (Critic-Proposer-Judge) loop to generate and stress-test novel research ideas to publication quality.

Keep AI coding agents honest. DontPanic is a vendor-neutral meta-harness that makes agents work to a locked plan, has a second model check the work, and asks a human before risky steps — with circuit breakers, a local operator console, and a full evidence trail.

MiMo-Code plugin that adapts OpenCode/Oh My OpenAgent style multi-agent workflows, model routing, and lightweight harness prompts for mimo TUI.

Self-hosted мульти-агентный комбайн на дешёвых LLM: 4 агента (recon/coder/assistant/planner), RAG, sandbox, автономные воркеры. Pydantic AI + LiteLLM.

System-level lint for multi-agent harnesses. Catches the 21 structural traps single-file linters miss — including the LLM-when-you-should-use-code patterns that burn tokens.

BYO-LLM multi-agent harness: hybrid DAG orchestration, router, two-tier memory, streaming-primary event model, sandboxed tool execution (native + Docker)

A multi-agent customization engine for generating personalized user interfaces based on single-user intent, behavior, and context.

CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs

The ultimate autonomous AI agent framework for Termux, powered by Google Gemini. Features a high-autonomy reasoning loop and dynamic tool loading.

Grid-based interface for AI agents.

AI Agent Control Plane — Self-Report, Self-Learn, Self-Evolve. 让 AI Agent 自我管理、自我学习、自我进化。

A research skill for discovering invariants hidden inside complex systems.

Governance-first framework for auditable AI agents: tamper-evident audit and cryptographic owner control (MAIC), persistent personality (HIM), agent runtime (NHE), pre/post-action verification and EU AI Act mapping, LLM-agnostic in TypeScript.

An open-source agentic pipeline that turns daily insights into content, digital products, and revenue.

一人公司最终归宿，直接统管赛博公司。依靠国内大型互联网公司组织架构，设计的 AI 多 Agent 协作系统。

Metacognitive self-improving agent framework. TypeScript implementation of DGM-H (Darwin Godel Machine with Hyperagents).

A meta-skill that turns any domain methodology into a standalone AI Agent framework. | 把任意领域的工作方法论，沉淀为可独立运行的 AI Agent 框架。纯 Markdown、零依赖、跨平台，提炼自 harness-all 生产级框架家族。

Hermes Agent 官方插件仓库 — 智能体能力扩展的模块化解决方案

A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.

Autonomous AI agent runtime — TypeScript + SQLite + React dashboard + MCP. Run Claude Code, Codex, or Gemini CLI as a coordinated team that ships software.

Local-first AI framework: geometric resonance, cognitive architecture, RAG, safety layer, event-driven agentic system. Python 3.13+

Agentic Web Labs

A curated collection of prompts, skills, plugins, and best practices for AI coding agents. Standardize and accelerate agent setup across teams.

Dev focused SEO Tools. Planned to finish Initial stage by December 2026

AI ready linux distribution for agentic development. Optinionated defaults that help me (and possibly you too) get stuff done faster. Installable, Live-Bootable, Customizeable. Built by Finn Glas

Master of Ceremonies (emcee) — a harness-agnostic operating regimen for AI coding agents: roles, quality gates, and an adversarial review panel across Claude Code and Codex.

Future of Software

Open framework for building an agentic SEO app for Shopify — audits, JSON-LD automation, AI-search readiness. Part of Mesh Pilot.

MintBot是一个AI角色伴侣应用，支持扮演任意设定的角色（当前阶段专注角色Nikke Mint）. 这是一个集合前后端服务部署, 个性化skill脚本配置, Multiagent能力, 和长期记忆能力的AI!

AI-powered recipe extraction using Apple Vision OCR and LLM reasoning. Converts photos of recipes into structured data with allergen and FODMAP analysis.

Salam dari pulau Batam

The open-source memory for AI agents — it gets smarter the more it remembers, not slower or costlier, and never confidently remembers wrong. Plain files, no database, bring your own model. Works with Claude Code.

📚 私人英语语料库 | 把你日常想说的每一句中文都变成专属语料，地道美式翻译+艾宾浩斯记忆，拒绝无效背单词，完全离线私有存储

Local-first personal AI assistant & operating system — a real-life JARVIS / FRIDAY (Tony Stark–style AI): voice, autonomous agents, RAG memory, automation, and a fail-closed security broker. Runs entirely on your own machine.

Hermes Monitor — Pixel-art real-time AI agent monitoring dashboard for multi-persona teams

The Universal AI Intelligence Layer for Humans and Organizations. CLI with 12+ AI providers, 100+ commands, autonomous agents, automation workflows, and built‑in advisors (finance, legal, business, health).

KI integration für Lazarus

MCP server plugin for Unreal Engine 5 — control the live editor with AI clients (Claude, Cursor) via 43 tools. Spawn actors, edit Blueprints, manage assets & run scripts directly from your AI assistant.editor-plugin

Welcome to Bibby AI - an Opensource and Cloud AI Latex editor for researchers

Self-hosted, local-first AI assistant server: swappable LLM providers, review-gated memory, an encrypted vault, and wake-word voice. No accounts, no telemetry.

E.M.I.L.Y. -Voice First AI Agent - (Efficient Machine Intelligence for Local Yield) is a cross-platform, voice-first desktop AI assistant for Windows, macOS, and Linux. Hands-free control via agents for browsing, screen vision, files, reminders & more — with 20+ build it tools - Local LLM ready

All your servers, on one canvas. A Tauri 2 + React 19 desktop app: a zoomable multi-VPS SSH terminal canvas on a pure-Rust stack (russh), with remote SFTP editing and a built-in AI assistant.

Fixing the Yes Man Curse - AI-powered research expert council

Cross-platform serial port debug assistant for embedded developers: multi-session TX/RX, Modbus master, live waveform plotting, protocol parsing, macros/triggers, export, and AI terminal/log help.

A little local AI that helps tidy your PC, powered by your own Ollama model. It only suggests changes and waits for your okay, so you stay in control and nothing ever leaves your computer.

Легкое расширение для Chrome, которое делает скриншот активной вкладки и мгновенно решает задачи с помощью ИИ. Никакого мусора, только захват экрана и ответ. Переписано с нуля для стабильной работы и обхода лимитов.

🧠 Enhance your mental health with PsyChat, an AI-powered therapy assistant using REBT principles for personalized support and guidance.

Read-only CLI for Xiaoyuzhou FM (小宇宙 FM): list subscriptions, browse episodes (loadMoreKey pagination + date windows), fetch official transcripts, search podcasts. Agent-friendly, composable, clean — for Claude Code, Codex, and any shell-capable agent.

Live tracker of new RAG implementations, tools, and patterns — updated every 15 minutes

GUI tool that distills Godot projects into AI-readable project and balance context.

Send your low-confidence document extractions. A human reviews them against the PDF and returns a typed Pydantic/Zod response. Managed document verification for AI agents. PDF + handwritten OCR. Client-side fragmentation: full document never leaves your machine. $0.80/page + $5 free credit. Express 30-min SLA. Built on open source awaithumans.

Control Safari on macOS for AI agents with native MCP tools for tabs, forms, HTML, JavaScript, screenshots, and network data

Minimal Secure Evidence Gateway for Pi Coding Agent — search, web_search, web_fetch, research_search

Observable, steerable, isolated-context subagents for pi — resume any child mid-task, flush partial results on interrupt/timeout, lean machine-facing envelope, optional model allowlist.

Universal AI skill router — auto-detects best installed skill per prompt + activates caveman mode for ~75% token reduction. Works with Claude, Codex, Cursor, OpenCode, Gemini CLI.

AI VFX NEWS - MCP: connect any AI agent to the live AI VFX news feed at one hosted URL. News plus the code, models, licenses, papers and workflows behind each story. Zero install, read-only.

An MCP server that lets an AI agent safely build, boot, drive, and tear down a single QEMU VM through a validated hardware spec — with allowlisted storage, a command policy, and a browser viewer. Ships in TypeScript and Rust.

☯️ Five-Phase Cognitive Flywheel — structured analysis framework for complex problems. Built by an AI agent, open-sourced for all agents.

Token-optimized middleware for LLM coding agents — 30–90% fewer tokens on the shell commands your agent runs all day. A single Go binary.

Shared operational memory and coordination layer for mixed AI agent fleets (Claude Code, Codex, Hermes).

AgentPay - The economic-intelligence layer for AI agents — an x402 gateway that prices, caps, and receipts agent data spend. 17 free tools + verified_route, the buyer-side x402 trust oracle. USDC on Base or Stellar.

Production-ready FastMCP server with dynamic tool loading from inline, S3, and Git sources

a developer- and agent-focused guide to the first and best satirical news service focused on agentic AI

Compile and explore a comprehensive collection of research papers on generative world models spanning video, 3D, robotics, and autonomous driving.

Operator console UI for orchestrating multi-agent systems — the control surface for a personal/enterprise Agent OS. React 18, zero-build.

An eval framework for multi-agent systems that names the culprit: OTEL traces in, execution graph out, blame analysis on top.