Custom agents

My version of the Stanford experiment "Generative Agents: Interactive Simulacra of Human Behavior" in Python using a local LLM.

A tiny LLM Agent with minimal dependencies, focused on local inference.

AISecOps (AI Security Operations) framework for deterministic verification of AI systems. QWED verifies LLM outputs using math, logic, and symbolic execution — creating an auditable trust boundary for agentic AI systems. Not generation. Verification.

Multi-Agentic System Observability SDK

An ecologically inspired multi-agent system. Agents are designed with neural network based decision making, and complex resource requirements.

(Official) PyTorch implementation for Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning (EMU) (ICLR 2024, Oral)

Confidence-Weighted Multi-Agent Retrieval-Augmented Generation (CW-MARAG) — a contradiction-aware RAG system that uses multiple retrieval agents with confidence-based arbitration to generate grounded, non-hallucinated answers from PDFs.

Claude Code state management with session continuity and AI personas, subagents and agent discussion

An incredibly fast, atomic-first framework that gives software developers more control over agent construction

Give Copilot a memory! MemoriPilot provides seamless, persistent context management that makes Copilot aware of your project decisions, progress, and architectural patterns - dramatically improving the relevance and quality of AI assistance.

MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.

Open-source team collaboration where your conversations become your competitive edge. AI-powered, privacy-first, and you control every bit of it.

A modular AI orchestration system supporting local LLM (llama.cpp) and API models, featuring dynamic routing, multi-stage processing pipelines, and persistent conversational memory.

Web scraping framework built for AI applications. Extract clean, structured content from any website with dynamic content handling, markdown conversion, and intelligent crawling capabilities. Perfect for RAG applications and AI training data pipelines. Features async processing, browser management, and Prometheus monitoring.

Fully automated deployment of Azure SRE Agent, multi-pod AKS, and "break scenarios" with prompt guides to experiment with Azure SRE Agent.

To automate the SLR process and write paper quickly using multi agents of AI

Official Rust implementation of the UTCP

Lightweight, Rust-native AI Agent platform. Security sandbox from day one.

🤖 AI Dialer ☎️ – Autonomous Voice Agent for Appointment Scheduling 🗓️

This is the official repository of the paper "BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness"

12-layer memory architecture for OpenClaw agents — knowledge graph (3K+ facts), semantic search (multilingual, 7ms GPU), continuity + stability + graph-memory plugins, activation/decay system, domain RAG. Agents reconstruct themselves from files on every boot.

MCE: Clone Human Souls with LLM Native Agent Skills | 基于 LLM Agent Skills 的心智克隆工程 | Agent Skills | Mind Skills | Mind Clone

The first platform designed to empower organizations by automating and enhancing their employment processes through advanced autonomous agents.

🦞 A curated list of ResearchClaw ecosystem projects, AI research agents, autonomous paper-writing tools, and scientific workflow resources.

[AAAI 2026] Multimodal Deepresearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)

[ICCV 2025] V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction

Synode — A macOS & Windows desktop app where multiple AI models discuss questions as a council, with a master model delivering the final verdict. Follow up with any model via @mentions. Built with Tauri v2 + React + TypeScript.

RAG-powered AI agent that translates natural language into SQL for live database querying.

A toolkit for composing self-learning algorithmic trading agents

Code implementation for DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning.

ChatEDA: A Large Language Model Powered Autonomous Agent for EDA (TCAD'24, NAACL'25)

Convert workflows into Agent Teams (Split Pane/Swarm) for Claude Code

Lucia is your whole home assistant that you always wanted

Research, monitor, and action your brand's visibility in LLM search.

GitHub Copilot Agent Skill for Nightscout CGM blood glucose analysis

TokToken is a fast, single-binary C codebase indexer for AI coding agents. Powered by universal-ctags and SQLite FTS5, it provides precise symbol search, dependency tracking, and an MCP server. TokToken reduces LLM context token usage by 88-99% by retrieving exact code symbols instead of reading entire files. Zero runtime dependencies.

The open-source skill registry for AI coding agents. Create, manage, and distribute SKILL.md files across Openclaw, Claude Code, Cursor, Codex, OpenHands, Antigravity, and more.

a minimal, Rust-based coding agent focused at CI workflows and small codemods, similar to Claude Code

Private AI research agent — web search, document ingestion, RAG memory. Runs entirely in your browser.

Templates for developing your own listeners and agents for AdaptixC2.

Curated open-source skills for AI agents (Claude Code compatible)

为 AI coding agent（Claude Code / Codex CLI 等）打造的 Skill 分层路由树生成器。把臃肿的单体 Skill 拆分/聚合成 ROOT → ROUTER → SKILL 的树形结构，让 agent 根据用户意图按需加载子能力，避免一次性塞满上下文。支持单 Skill 拆树、多 Skill 聚合（含歧义消解）、增量扩展三种模式，兼容 .claude/skills 与 .agent/skills 双路径约定，纯 Markdown + Bash，零依赖。

ParaView-MCP integrates multimodal LLMs with ParaView via Model Context Protocol, enabling natural language control of scientific visualizations. The agent observes the viewport for visual feedback, making complex visualization tool accessible to all users while providing intelligent automation for experts.

Stata CLI for Agent; Stata CLI Is All Reg Monkeys Need

Open-source, customizable frontend for Venice AI. Chat, image gen, audio, video, embeddings + visual workflows — all in one UI. Your API key, your browser, no backend.

AI agent toolkit (skills+MCP server) for Lightning Network payments. Run nodes, pay for APIs (L402), host paid endpoints, and manage credentials.

🔮 A smol coding agent in Elixir

A local-first Chrome extension that passively captures ChatGPT, Gemini, Claude, Grok, Perplexity conversations into a private memory graph. Features in-browser Hybrid RAG (Vector + BM25), semantic search, and 100% privacy via WebAssembly and IndexedDB. No servers, no API keys.

🤖 Cortex AI: #1 智能量化交易系统 — 全自动加密货币套利引擎 v3.4。支持 Solana、TON、Binance (币安) 和 Bybit。2026年最佳高频量化交易机器人。

Route your coding agent to the fastest free LLM in real time.

Obsidian vault intelligence

MCP server that lets any llm (i.e. Claude Desktop) delegate tasks to a local Hermes Agent — cron jobs, web search, email, documents, and more.

1-Click LLM Server on Your Phone — no Termux needed! 无需Termux，一键让你的手机变成LLM服务器！

面面-AI求职助手是一个利用大语言模型（LLM）和 LangGraph 状态机技术构建的综合求职辅助系统。它不仅能进行全真模拟面试，还能像专业的职业咨询师一样，通过多智能体协作（Multi-Agent）对简历进行深度诊断和定向优化，帮助求职者全方位提升竞争力。

Universal MCP to LSP bridge - expose Language Server Protocol capabilities as MCP tools for AI agents

Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.

Embodied AI companion for Minecraft — persistent memory, vision, learning, multi-agent. Built on Hermes Agent.

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop onboarding your coding agents like rookies every session.

MedAutoBench — Medical AutoResearch Benchmark for Autonomous AI Agents

Roblox Studio MCP server & plugin for Claude Code, Cursor, Codex, and Gemini. AI-powered scripts, terrain, assets, lighting, and bidirectional project sync.

Helix-AGI is an Agentic AI System that uses a spatial-graph memory retrieval system. Agents receive a rolling adaptive system prompt of memories and skills that afford the agent a highly dynamic center of conceptual gravity. By avoiding long identity files and subagent-heavy workflows, Agents can develop continuously without spiraling costs.

Curated OSS stack for solo founders to build, launch, sell, support, and grow polished products

Connect Claude and ChatGPT to KDAN PDF — upload, edit, compress, protect, redact, and compare PDFs in chat.

A context-aware and efficient CLI-based coding agent written in Go

A team that debates > a model that answers. MeetMind turns one requirement into a live discussion among five role-playing agents — architect, backend, frontend, test, and PM — each with its own private RAG knowledge base to search, cite, and reason from. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

An AI-powered assistant for your terminal and editor

Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks.

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

End-to-end AI literature review automation: crawl, screen, download, multi-agent review, and report generation

Rewrite frontier research using allegorical structural mapping.

A curated list of awesome open source projects for creating agentic operating systems, AI agents, and tools for the future of autonomous computing.

Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.

NSE BSE Indian Stock Market Data MCP server — search, screen & analyze all 8,200+ NSE/BSE stocks with 34 tools: live quotes, financials, technicals, 326-ratio screener, FII/DII flows, IPOs & portfolio tracking. Works with Claude, ChatGPT, Cursor & any MCP client | tapetide.com

ChatGPT Team Bug号自动注册；包含自动注册SKILL和自动注册脚本。慢一点儿，但是交给Agent，他自己能完成全部流程。推荐使用Codex

一个面向企业场景的 AIOps 智能体系统，基于大模型（LLM）构建，融合 RAG（Milvus）与 MCP 工具调用，实现知识问答、信息检索与智能运维能力

A pixel art virtual office that visualizes your AI agents working in real-time. Claude Code hooks, WebSocket events, and isometric pixel art.

Find and redact secrets in AI coding agent histories (Claude Code, and more).

Bring local AI intelligence to your device. No rate limits & local first.

StewardOS - agentic autonomous OSS system

Use your OpenCode Go subscription in the Codex app. Local Responses-to-Chat-Completions bridge for all 13 OpenCode Go models.

See what's on your ports, then act on it. Diagnostic-first port viewer for Linux, MacOS and Windows.

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary, no dependencies.

A curated collection of custom agents, skills, rules, and prompts for GitHub Copilot, Google Antigravity, OpenCode, ChatGPT Codex, and Oh My Pi. Tailored for Indonesian and International developers to streamline SDLC workflows with AI.

🔧 One layer above your AI tools. Your AI coding tools are brilliant. Managing them is a mess. :electron: Cradle is the command center that coordinates all of them.

An independent .NET implementation of a Neo4j-backed memory provider for AI agents. Persistent graph-native memory for Microsoft Agent Framework, with GraphRAG interoperability for Neo4j.

Open-source, agent-agnostic framework for multi-agent coding workflows. Run a fleet of coding agents in parallel, with deterministic validation, verifiable proof, and full observability.

Skills, agents, hooks. Cross-harness. With a side of Pi.

🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.

MoeGoe Android Application by calling Azure function API

This repository contains code snippets, steps and other artifacts used in the youtube videos in the demo. You can use this to get access to the code or artifacts.

An AI teaching assistant that allows students to interact with the teacher's course materials

A high-level Python wrapper for the WhatsApp API, providing easy abstraction.

OOP interface for composing Slack Block Kit messages and modals in PHP

NLGen: a library for creating recursive-descent natural language generators

Template for creating Telegram bots on Python Aiogram

Dialogflow Workshop Material. This can be used to create a Conversational Agent for a simple Linear Conversation using Dialogflow