Custom agents

mcp implementation of an agentic framework

Starfish-FL is an essential component of the STARFISH project. It focuses on federated learning and analysis for the Analysis Mandate function of STARFISH.

A Programmatic Tool Calling MCP Server allowing AI agents to build and (re)use their own API interface stack tools.

Claude Code skill for creating and optimizing Claude Code skills. Includes optimization principles for LLM attention, router pattern, classification design, and prompt engineering.

Trust and Governance framework for AI coding agents. Local-first guardrails for spending, credentials, deployment, and cross-project isolation.

CLI for exporting Claude Code/Codex sessions to Hugging Face with privacy redaction, MCP memory, and share-ready dataset workflows.

VividnessMem is built on the idea that memory is not storage but changing salience over time. Vividness provides the core forgetting/reinforcement dynamic; associations enable lateral recall; higher layers like consolidation, dreaming, and regret build increasingly reflective and generative behaviour on top of that foundation.

AI engineering framework with quality gates, persistent memory, and multi-platform support. Works inside Claude Code, Cursor, Copilot, Codex, and Gemini.

LLM agent for Mini Micro

ToolRM: Towards Agentic Tool-Use Reward Modeling

An AI-driven character content generation system that implements a complete workflow from character creation, schedule planning, event planning, director output to video performance generation.

Agent-agnostic context, tracking, and cost analytics for AI-assisted development. Curated docs · Session tracking · Cost analytics · Team knowledge — all git-native

Spectrum: a deterministic semantic encoding enabling constant-time retrieval primitives

An AI-powered desktop coding workspace for planning, coding, debugging, review, and testing through multi-agent orchestration and shared blackboards.

OpioidRL is a cutting-edge reinforcement learning (RL) library that simulates drug addiction behaviors within RL agents. Inspired by the addictive properties of drugs like methamphetamine and crack cocaine, OpioidRL offers a unique environment where agents experience reward dependency, high-risk decision-making, and compulsive behaviors — pushing

TRAIL — Tracking Records Across Isolated Logs. An open protocol for cross-MCP content tracking and deduplication.

A sophisticated multi-agent system designed for real-time market analysis of HTX (formerly Huobi) exchange data. This swarm combines specialized AI agents to provide deep market microstructure insights and trading analytics.

🖌Generative UI in Golang, based on HTMX and Templ, is useful in Multi-Agent Systems.

RAG with web search, self correction, gap detection and query loops

Agentic Server for PostgreSQL

Clawd Phone is an Android app built around native tool calling

Capsule is an interactive inspector that turns session logs into a browsable and explorable timeline.

On-demand Services/Data marketplace for AI Agents.

Multi-agent framework for building large scale Agentic AI. Simple agents, powerful results

Agentic GitHub workflows with reminders, PR monitoring, and progress tracking. Includes a Discord bot for notifications. 🚀

MCP Server for GNU Make

Software Engineering Arena is an open-source initiative to transparently evaluate and track AI assistants across real-world software engineering tasks.

Track Al coding assistants by wikis

Track Al coding assistants by team management

🤖 FoodBot AI is an intelligent chatbot that automates the ordering process in restaurants. By replacing traditional waitstaff, it streamlines operations, reduces costs, and enhances the customer experience through a seamless chat interface.

A CLI tool and MCP (Model Context Protocol) server for querying and analyzing TensorBoard event files without requiring a running TensorBoard server.

ClippyAI is a multi-platform GUI application, which serves as an interface for Ollama.

Track Al coding assistants by releases

AI 日记助手 - 智能记录想法，自动生成洞察

SearxNG MCP Server provides privacy-focused web search for AI assistants using SearxNG and the Model Context Protocol.

一站式轻量化数据引擎：连接设备，交付价值；CRose是一个专为制造业与现代农业打造的集成化数据底座。它封装了从底层的协议采集（Modbus/MQTT）到上层的统计分析、UI展示的全链路能力。CRose is an integrated data platform designed for manufacturing and modern agriculture. It encapsulates the full stack capabilities from underlying protocol collection (Modbus/MQTT) to upper-level statistical analysis and UI visualizat

PolicyRAG : A RAG Based policy agent designed to guide through the process of finding the best policy that fits the requirement with no effort of reading

Expose local PDFs via MCP or the standalone pdf-reader CLI with deterministic chunking, sandboxed access, and semantic search.

🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.

PagePilot is a VS Code Chat participant that automatically loads external context (documentation, APIs, README files) to provide enhanced responses. Language is automatically detected from your VS Code settings.

EasyRAG: A Beginner-friendly and Interactive Framework for Retrieval-Augmented Generation, SIGIR 2026

The Driflyte MCP Server exposes tools that allow AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages.

A curated list of awesome papers and resources for Retrieval-Augmented Generation (RAG) in Large Language Models(LLM).

Ai Agent

Kikiola is a high-performance vector database written in Go.

LLM chat built for University of Helsinki staff and students, for education and research.

Claude Code skill for building ADK agents with Google A2UI declarative UI format

🦅 DestinyScout: 一款基于 Agent-Native LLM + Boss直聘的 L3 级自主个性化求职引擎。告别机械搬运，它能深度注入你的私人职场 DNA 并配合强力反穿透爬虫，让大模型在茫茫数据海中为你精准捕获那个“命中注定”的理想 Offer。

Orchestrate No-Code Voice Conversational Agents with deterministic logic, sub-second latency, and native multi-language support.

Voice calling plugin for OpenClaw — give your AI agent a phone number. Inbound/outbound calls, batch calling campaigns, SMS, post-call transcripts & notifications, ElevenLabs + Deepgram voice engines.

Open security architecture for autonomous AI agents - extending Zero Trust principles

Multi-model AI agent orchestrator. Run Claude, GPT, and Ollama agents in one workspace with group chat, smart routing, and per-agent model assignment.

Open-source AI Agent platform built on .NET — design, test, and deploy agent workflows

Local-first semantic cache for AI agents. A small C daemon + CLI that remembers what your agent learned across sessions. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop / ChatGPT via MCP. No LLM calls, no SaaS, no API key.

A FUSE semantic filesystem for LLM/AI AgentsAgentic FUSE filesystem for LLM agents. Structured file operations with JSON feedback, audit logging, undo support, and semantic search.

AI-powered learning analytics platform with A2A multi-agent pipeline — xAPI behavioral tracking, at-risk detection, and automated PDF/DOCX reports for instructional designers.

Various LLM resources and experiments

Multi-agent RISC-V verification and test-generation framework for AI-assisted RTL, ISS, compliance, coverage, and debug workflows.

Talk to your starred github repositories

End-to-end training methodology for agent recommendation system

Agentic GraphRAG system for loan compliance monitoring and financial crime investigation in Australian financial services. Built on Neo4j, Claude, and APRA prudential standards. Features a multi-agent pipeline, three-layer knowledge graph architecture, and full reasoning chains with cited regulatory evidence.

Ultrarunning training companion agent powered by Intervals.icu.

AICO – An open-source experiment to build a real AI companion: emotionally present, embodied, proactive, and fully local on your system and self-contained. More confidante than assistant. For builders who want technology to feel truly on your side, not just at your command.

Musclog - Lift, Log, Repeat

Check Your Password is Ever Cracked & Know About Strength of Your Password & Generate Passwords Using a Specialized AI Model (StrengthX-Dildo:V1) Dynamic Intelligent Lock & Defense Operator

Retrieval augmented generation for building datasets from scientific literature: Contains the notebooks used for creating datasets

Python-based MCP server for Unreal Engine 5 Blueprints. Enables LLM-powered editing of Blueprints, graphs, variables, functions, and components.

Genesis Mind Interface — desktop chat UI for Genesis agents

OpenClaw-oriented workspace template for AI-agent continuity: file-based memory, self-identity docs, and operating conventions.

Real-time command center for Claude Code agents. Monitor all agents from one dashboard, send instructions, track costs, detect stuck/looping agents, 7-layer security radar. Works from your phone via QR code.

Give AI eyes and hands on your desktop. Open-source MCP server for desktop automation — screenshots, UI control, browser automation, OCR. Works with Claude, Cursor, and any MCP client. macOS + Windows.

Heterogeneous AI agents (Claude Code + Codex + Agy + Kimi) collaborating in Telegram groups over A2A-TG — a generation-counted envelope protocol. Self-hosted.

Web UI for opencode. Any device. Push notifications. Zero install.

Engineer user-research methodologies into AI prompts — professional-grade phone interviews at scale. 6 pluggable methodologies, 3 AI skills, 5+ tool compatibility.

AI-powered TikTok content factory — 6 autonomous agents, one command, one video

The open-source skills library for Agentic Customer Success Operations. Hardened, multi-protocol playbooks designed for human CSMs and autonomous AI agents. Codifying technical API logic, expansion blueprints, and predictive churn-stop plays to close the Value Realization Gap. Licensed for internal business use. Please contribute & collaborate.

Ship customer-facing AI with isolation, spend controls, and provenance.

AI coding agent orchestrator — run parallel Claude Code tasks in sandboxed Docker containers, monitor from a Kanban board or chat bot.

Build and host Coded MCP Servers within UiPath

Make the leaked Claude Code runnable with unified local model support.

Auditable MCP + cross-agent harness for autonomous and human-guided academic writing—from verified evidence to reviewed DOCX/PDF.

Source code of the wahl.chat platform. Our mission: Make politics more accessible.

GRASP — Code architecture visualizer + 150-tool MCP server. Dependency graphs, security scanning, multimodal knowledge graph, ORM tracking, git change impact, graph schema v3. Works with GitHub, GitLab & local dirs. 35 languages. Zero data collection.

Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.

Agent-Pilot · 飞书 AI 校园挑战赛 · 从 IM 对话到演示稿的一键智能闭环 | 6 Agent Multi-Agent Pipeline · MiniMax M2.7 Tool Calling · 飞书 Bot 全生态集成

暗恋一个人只有TA的小红书？粘贴链接，AI自动翻完所有笔记和收藏，用5套心理学理论画像，推断TA喜欢什么人，生成分阶段追求攻略。Claude Desktop Skill 🔮

Claude Code plugin: Control Apple Pages from Claude — create, edit, format & export documents via /pages slash command. 100+ templates, PDF/Word/EPUB export, tables, images, REPL mode.

AI-First SAP UI5 Test Automation for Playwright

SeekLink — hybrid semantic search for markdown vaults. Four-channel RRF fusion, MLX reranker, native CJK support. Fully local.

学习大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地. 立即上线你的agent 应用.

Claude Code + Codex 双平台 AI dotfiles：统一管理 skills/agents/hooks，并一键同步到 ~/.claude 与 ~/.codex。

🌐 An open, standardized four-layer enterprise ontology framework for knowledge graphs, semantic layers, master data management, and AI Agent knowledge bases.

Glossary of key concepts in Large Language Models (LLMs), Artificial Intelligence (AI), Natural Language Processing (NLP), and Machine Learning (ML). Clear definitions and resources for developers, researchers, and AI enthusiasts exploring generative language technologies.

6 hands-on demos to detect, prevent, and self-correct AI agent hallucinations using Graph-RAG, semantic tool selection, multi-agent validation, neurosymbolic guardrails, and agent steering. Deployed on Amazon Bedrock AgentCore.

Official WeRead Agent Skills collection | 微信读书官方 Agent Skills 集合，自动同步

基于AI agent 的 AI 长篇小说创作平台

🐜 AI-native modular coding workspace — 127 modules, 424 MCP tools, 21K+ zero-mock tests, multi-agent orchestration (Claude/Gemini/GPT), PAI integration

Turbocharge your AI Agents with TurboQuant

Lightweight, agent-optimized database CLI with one-shot schema introspection, column profiling, and ERD generation.