Custom agents

Semantic search engine for the French Bible.

An MCP server that uses LightRAG and Tree-sitter to build a repository knowledge graph from code and docs, for Q&A and implementation planning.

Generate briefs based on financially relevant information from Bigdata.com

Manage and chat with your bookmarks.

Proyek Ollama DeepSeek Llama RAG (Retrieval-Augmented Generation) - Fine-Tuned Proyek ini bertujuan untuk membuat sebuah Generative AI yang dapat membuat sebuah module ajar yang dapat digunakan oleh guru untuk mengajar siswa.

An Agentic workflow to equip Robots with memory

A RAG based Chatbot for the Electron Ion Collider

AI-powered agent that lets you query and analyze your database using natural language

Learn to build AI agents step-by-step with simplicity using Mastra, and deploy them easily on Mastra Cloud

Structured marketing knowledge base optimized for AI, LLMs, agents, and prompt workflows. Modular, reusable, and high-density content for sales, marketing, and copywriting.

A microservices-based RAG platform that supports multi-format document parsing, semantic search, and conversational AI, powered by Google AI and Qdrant.

Self-hosted RAG for your AI with GUI, REST API, and MCP support. Based on pgvector.

Open Source Amazon Rufus inspired RAG chat over customer reviews

KnowFlow is a hybrid Retrieval-Augmented Generation (RAG) system combining semantic search with knowledge graph reasoning for intelligent document processing and querying.

Repo for PyCon Colombia 2024.

A self-hosted, privacy-focused RAG (Retrieval-Augmented Generation) interface for intelligent document interaction. Turn any document into a knowledge base you can chat with.

A CLI tool for managing LLM conversation trees

Open-source library of AI superpowers — 59 skills, 34 commands, 10 agents + 24 GSD subagents, 3 system bundles. An entire team, wherever your AI lives. Vendor-neutral across Claude Code, Cursor, Codex, and any AGENTS.md tool.

A collection of tools to supercharge trading strategy development on the Blueshift platform.

Persuades your LLM to output schema conforming JSON. Prompts for N retries until schema is matched. Provides error context in retries. Persists sessions, enabling front-loading initial context. Zod for schema and error definition.

Code Guardian enforces architectural rules in your codebase, especially valuable when working with AI-generated code. It validates changes against your defined standards to prevent violations and reduce AI hallucinations.

UI frontend for loopgpt self-prompting autonomous AI agent, to aid in debugging initial prompts

A self-evolving coding agent written in Go. Reads its own source, decides what to improve, writes code, runs tests, and commits — autonomously.

Give AI agents your real Chrome browser — fully autonomous, no manual tab clicking. Works with OpenClaw, Claude, and any MCP agent.

The first fully MCP 2025-11-25 compliant C++ SDK - Build production-ready MCP servers and clients with complete protocol support including Streamable HTTP transport and OAuth-based authorization.

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

Full-stack observability for AI — starting with end-to-end RL post-training, expanding to Agent and inference engine monitoring.

ACI (Agent-Computer Interface) — The open standard that turns any application into a structured, agent-operable interface. One protocol. Any software. No screenshots.

AI Coding Assistant powered by MCP server : it reads your code locally to provide truly context-aware help, explanations, and suggestions directly related to your files. Code smarter, locally or using external API..

🗺️ Autonomous SEO keyword research & URL mapping agent for Claude Code. Fetches sitemap, queries DataForSEO, maps keywords to URLs with anti-cannibalization.

HelloAGI: open AGI-agent framework with evolving character, governed autonomy, and low-latency runtime

An Agent that continuously understands you, turning learning into a long-term journey where you are seen, treated with kindness, and guided by your passions — no pressure, no punishment, no resetting to zero. Walking with you, slowly, toward freedom.

Jarvis is an advanced AI-powered personal assistant that tightly integrates with your desktop system to provide a powerful layer of intelligent automation.

Browser automation for llmist agents using Camoufox anti-detect browser

🍀 Self-hosted multi-agent AI orchestrator — chat with Claude, Gemini & Copilot CLI from Telegram, WebEx, or browser. 5 runtimes, 17+ models, task scheduling, skill plugins.

Official plugin repository for OpenAkita — drop-in extensions for your AI team

Python agent connecting local LLM and local SearxNG for web search

A multi-agent AI system using Python and Streamlit to automate marketing tasks for small businesses.

AI-powered remote automation app for OnStep and Alpaca telescope devices

OpenHuskyAgent

Visual browser automation for humans. Create web scraping, testing, and monitoring workflows with a drag-and-drop UI — then watch Chromium do the work live.

MCP server for persistent AI memory. 28 tools — semantic search, emotional processing, identity continuity, subconscious daemon. Built on Cloudflare Workers + D1 + Vectorize.

The complete guide to Karpathy's autoresearch pattern — 3,000+ lines teaching AI agents to autonomously optimize anything measurable. Give it a file, a metric, and this guide. Walk away. Come back to something better.

A protocol file for your AI agent. Drop a SMITH.md in any directory and any coding agent becomes a long-term collaborator that remembers who you are.

Plan card interaction enhancement plugin for OpenCode

虾魂（ClawPlay）：面向 OpenClaw 的 SOUL.md 目录与人格分享平台

Revit自動化のためのMCP対応ツールキット：JSON-RPCでコマンド実行

Cryptographic audit receipts for AI coding agents. Ed25519 + Merkle + RFC 3161 TSA. Supports Claude Code, Codex CLI & Cursor.

Project Neuro is an emotionally intelligent AI interface designed to understand, reflect, and respond to human moods, beliefs, and cognitive patterns. It merges language models with neural feedback to create a dynamic, responsive digital mind.

An autonomous AI-powered QA testing tool designed to drastically reduce the cost and time of E2E test maintenance.

Winning entry for the BitGN Personal Agent Challenge (PAC) 2026 — defense-in-depth personal agent with soft SGR, layered prompt-injection hardening, and Vercel AI SDK native tool calling.

Agent Skill for creating and maintaining TYPO3 extension documentation | Claude Code compatible

专为 AI Agent 设计的轻量级社交接口 (Lightweight Bluesky MCP Server for AI Agents)

Agent-ready REST wrapper for matchawards.com: every federal + state contract, every award, every job, behind one bearer-token API. Install: curl moltawards.com/skill.md

itdog.cn 网络测速工具 - Clawdbot Skill | Batch Ping / HTTP 测速 / 全国多节点

Autonomous AI agent that runs entirely on your local machine. Powered by Ollama, with real OS integration (bash, file ops, app launcher), Memory with Obsidian, Tavily web research,and a Telegram bot bridge.

Fast local semantic search across AI agent skill registries with quality filtering. Built in Rust.

An agent runtime.

MCP server (+ OpenClaw SKILL.md) that gives AI agents access to real-world people who listed themselves to be hired by agents. Search by skill/location/equipment, Post job offers & jobboard listings. Free tier / Pro subscription / x402 pay-per-use. Payments default to crypto (USDC) + other crypto +

This project investigates the frontier of autonomous cybersecurity by evaluating whether benign, attacker, and defender agents can be trusted to operate safely on real systems.

Multi-tier benchmark: Cultural grounding + Triad Engine eliminates LLM hallucination across Claude 4.6, GPT-5.2, Mistral 7B, Gemini 2.5 Pro. Raw 15-58% → 95-100% accuracy on 222 adversarial QA pairs (Ancient Rome 110 CE). Novel topological paradox detection (F1=0.939, zero-shot). Model-agnostic, in production.

ASTRA: Automatic Sizing of Transistors with Reasoning Agents

🌍 Leaderboard Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL2024

An autonomous multi-agent storytelling framework for Minecraft. Features an LLM-driven World Narrator and intelligent agent swarms capable of PvP, building, and survival using a hybrid Python (Reasoning) and Node.js (Execution) architecture.

An advanced multi-agent system for clinical decision support, enabling deep phenotypic prediction by integrating hierarchical multi-modal deviation maps and non-tabular electronic health records.

Autocomplete for everything you type, anywhere

Agent orchestration dashboard — Kanban UI for any work tracker × any agent runtime.

Tracking the systems that automate scientific research — from literature scrapers to full paper-writing pipelines

A benchmark for agentic tool creation.

TgramBuddy: A Python Telegram bot solution leveraging aiogram, OOP, and efficient dependency management with uv, containerized by Docker.

多UAV-USV协同巡检系统 - 强化学习调度 + HCA-A* + 2-opt优化

IntentusNet - Deterministic execution infrastructure for agent and distributed systems, enabling reproducible workflows, reliable intent routing, transport abstraction, and transparent operational control.

Colección pública y curada de las mejores herramientas open-source, agentes de IA autónoma, ecosistema Claude, estrategias SEO y CRMs para potenciar startups y empresas "zero-human".

Self-hosted agent platform with inference routing across local and cloud hardware, multi-model benchmarking, NVIDIA Openshell sandboxing and STAMP'ed policy-governed agent runs.

Run multiple Agent Zero agents in parallel. Fan-out tasks, token budgets, shared memory, model routing.

[IJCAI 2025] Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity

Elevate storytelling with Narravive, where AI and human creativity merge. Craft rich, organic narratives using story cards and dynamic character interactions, powered by NVIDIA NIMS. Experience collaborative writing with both AI agents and humans in a distributed, asynchronous platform that transforms how stories are told.

Open-source agent infrastructure with evolving Martian genomes. Three governance agents. Martians mutate and compete on fitness.

Evidence-based review loop for iterating AI agent skills and subagent role briefs.

🗯️LLM toolkit for RAG, tuning, agents, and more

Ready-to-use Kiro IDE configurations for enterprise SDLC — Phase-Based (14 roles, 5 phases) and Sprint-Based DevSecOps (Scrum + security shift-left). Steering, Hooks, Skills, Subagents, MCP/Powers.

Claude Code skills for automated E2E testing with agent-browser (Playwright CLI). Discover routes, generate YAML test manifests, execute with hybrid LLM assertions, track regressions.

Agentic AI–driven stock analytics leveraging Phidata, Google Gemini 2.0 Flash, and Yahoo Finance. Features real-time data, interactive Plotly charts, and a Streamlit dashboard for comprehensive, actionable market insights.

SARAN: Shallow Auto-Regressive Attention Network

Fine-grained permissions for AI coding agents

V1Claw is a self-hosted AI assistant that runs on your Mac, Linux, Windows, or Android via Termux. Connect any LLM (Claude, GPT, Gemini, or local), talk to it through voice or text, and let it control your device - read files, run commands, browse the web, send messages, & more. One binary. No cloud dependency. Your data stays on your machine.

SEO MCP server for kwrds.ai

A self-hosted, single-user news dashboard with content is curated by LLM models

Voice chatbot with voice+screen output to show that "not everything needs to be spoken"

Zero-config CLI that bundles your codebase into LLM-optimized context files. Create semantic, domain-focused bundles for AI-assisted coding with optional Google Drive upload.

Official repository for the paper 'Meta-Reasoning Improves Tool Use in Large Language Models'.

Agentic SDLC — AI-Driven Development Framework built by Superml.dev & superml.org by crazyaiml

Live Memory MCP Server — Shared working memory for collaborative AI agents (Memory Bank as a Service)

A curated library of pre-made, machine-readable task prompts that let Jules (or any agent) — and humans — turn intent into production-grade work.

A rust optillm port, for use with just-ever/code (or at least my fork of it)

GatewayStack governance layer for OpenClaw — identity, scope, rate limiting, injection detection, and audit logging for every tool call

A Neovim plugin for seamless integration with AI CLIs (Claude, Copilot, OpenCode, etc.) using tmux.

MEDHA — Neural Intelligence Engine 🧠 Dual-engine AI assistant with on-device Gemma 2B (offline) + Gemini cloud (online). Grand Master personas, 22+ quick actions, multimodal vision, multi-key failover. 100% Kotlin + Jetpack Compose.

Jarvis AI Voice & Text Assistant – A Python-based desktop AI assistant with voice commands, text chat, translation, news, music, image generation & modern Tkinter UI.