Framework
Custom agents
57,774 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,774 agents · ranked by popularity · refine in the directory →
Custom agents — page 523 of 578
The Google developer documentation style guide as an AI agent skill, with a checker. Routes between doc mode and voice mode so it improves your README without flattening your cover letter (which may be "tuned" by your own pre-AI voice samples).
Agentic AI GST copilot for Indian small businesses: invoice OCR, multi-agent pipeline, Groq chatbot, ITC finder and GST calculator.
Enterprise-grade Autonomous Agentic AI Platform with LangGraph multi-agent orchestration, Agentic RAG (reranking + semantic cache), CNN vision, secure sandboxed code execution, and full observability.
A terminal interface that connects IFC/BIM models to LLMs.
AgentConductor 是一个面向 CLI 的 Agent Contuctor 项目,旨在将《AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation》中描述的方法复现为一个可复用的软件系统。该代码仓库不应止步于一次性实验,而应朝着可维护的包、可调用的 API 接口以及持久的实现文档不断演进。
Local secret store for AI coding agents. Agents run commands with your secrets but never see them: a desktop window or your Android phone asks you to approve with a YubiKey touch, Touch ID, or passphrase, grants expire on a timer, and output is redacted. age-encrypted, no server. Linux, macOS, Windows, Android.
Pre-action evidence revalidation for AI agents. Detect stale reasoning before agents write, send, update, or delete.
Real-time 3D product customizer with agentic AI, RAG, CNN and Docker — built by NIKHIL CHARY SRIRAMOJU
Agentic looping AI — one prompt in, one of three specialists out. Built with React + Tailwind.
Spec-driven development harness for AI coding agents. Grill the decisions, write the RFC/PRD, check every spec claim against the real code, build against named proofs, then pass one adversarial audit. Specs stay up to date with what shipped. Claude Code & omp plugin, any language.
✨Local coding agent powered by Ollama.
Agentic OPAV speaker health & bio-acoustic suite: Digital Twin, thermal/excursion safety governor, Hyper Clean 60 Hz–20 kHz, CFD visualizer, signed health passport. Fully on-device.
Secure Host MCP server & native desktop studio with workspace isolation, capability gating, and 8 super-tools
See the wire of any AG-UI server. Records every request and SSE frame, validates them against the protocol, and drives runs like a client: interrupts, client tools and A2UI surfaces.
Agent skills that augment your customer data to hyper-personalize product ranking for your human and agent shoppers.
Full-Chain AI-Agentic Attack Framework
一个以集体智能与集群协作为核心的智能体系统。| An Ai Agent system centered on collective intelligence and swarm collaboration.
Multi-modal AI ecosystem architecture — CNN perception, agentic RAG, LLM orchestration, CI/CD pipeline, zero-trust security, and live status API. Built by NIKHIL CHARY SRIRAMOJU.
A simple web based tool that analyzes password strength in real time and gives instant feedback to help users create stronger more secure passwords
Non-custodial agentic wallet with onchain session key delegation. TypeScript SDK, MCP server, and x402 payments for AI agents on BNB Chain, Ethereum, and Base.
In-browser PDF text editor with AI redaction agent — click to edit, export clean PDFs
This the Portfolio of Muhammad Naveed , An Agentic AI Engineer.
Autonomous post-quantum-secured decentralized edge-AI mesh with agentic AI, RAG, and CNN vision
An agentic letter-writing application featuring a multi-agent system (Intent, Retrieve, Draft, Comply, Critic, Layout) to help you compose, review, and format letters.
A Kubernetes-native control plane for building and operating governed squads of autonomous AI agents.
Open curriculum on agentic intelligence, governance, and AI safety — organized in parts with Mermaid and Python-rendered figures, sourced from ODNI, CIA, NIST and NATO publications, built by a Python/uv pipeline into a PDF with claim-calibration and reference-integrity audits.
Hybrid semantic + keyword search RAG pipeline
NexaGuard — Autonomous infrastructure defense mesh with live Groq LLM multi-agent reasoning, real-time CNN vision (MobileNet), RAG-grounded triage, and a 3D digital twin. Built by NIKHIL CHARY SRIRAMOJU.....
A source-checked paper collection on multi-reference image generation, agentic image generation, and their intersection.
Find out whether a smaller model could handle some of your AI agent’s routine choices.
A minimalistic AI coding agent in 62 lines of bash, curl and jq. Step-by-step tutorial: LLM call → chat loop → tool-calling harness that writes and runs a Tetris game.
AI resume analyzer & builder: upload a resume, get an ATS score, and generate a one-page ATS-friendly DOCX/PDF. FastAPI + Groq agent, RAG, CNN-style layout scan, Docker. Designed & developed by NIKHIL CHARY SRIRAMOJU.
Windows AI PC manager powered by DeepSeek Harness — scoped read-only scanning, safe cleanup review, and privacy-first desktop controls.
Starter repo for agentic software projects with guardrails built in: AGENTS.md, Claude Code hooks (kill switch, prod-guard, change freeze, audit log), plan-first specs, an agent offer letter, and 46 offline guardrail tests. Companion to the DevOpsDays Cairo 2026 talk Before You Put an AI Agent on Call.
Spatial Decision Support System for malaria elimination. Agent-based mosquito model, driven by satellite environmental data, with a neural surrogate for fast monthly risk maps. Ghana as first target region.
A TypeSafe-native (Jev) coding agent built on Recursive LLM Context Decomposition (RLCD), with a native macOS client
Autonomous multi-agent commerce intelligence platform for D2C brands — agentic pricing, inventory coordination, demand forecasting, and a trust/compliance auditor. Designed and developed by NIKHIL CHARY SRIRAMOJU.
Real-time fraud detection pipeline using Kafka, Airflow, dbt and Delta Lake, with a CNN scorer and an agentic RAG investigator (LangGraph + Qdrant), fully Dockerized. Designed and Developed by NIKHIL CHARY SRIRAMOJU
Give an AI agent the keys to a real Kubernetes platform and watch it burn, then turn on the CNCF and agent-specific guardrails that stop it. The BurritoBot demo platform, run at KubeCon NA 2026, DevOpsDays Portland 2026 and AI Engineer World's Fair 2026.
Rust SDK for ENSIP-25: Link verification between ENS names and ERC-8004 AI agent registries.
如果你开通了腾讯 WorkBuddy 或 CodeBuddy的会员/套餐积分,拥有大量的免费或高配模型额度(GLM-5.2/5.3、DeepSeek-V4、Kimi、混元等),但在日常编码中,你更习惯使用 Codex CLI、Claude Code、Claude Desktop 桌面端,或者 Cherry Studio / Chatbox 等外部工具
An open-source coding agent you can take apart: a terminal app (lmx), and the Elixir runtime underneath it (Lemieux). Works with any ReqLLM provider or a local Ollama model, and keeps every session as a transcript you can resume, fork and replay.
Agent Skill for building, testing and checking Embabel agents (Java or Kotlin, Maven or Gradle)
IRIS-X: Intelligent Robotics & Infrastructure Sentinel. A 3D digital twin with an agentic AI swarm, RAG, CNN vision and a Groq-powered personal assistant. Installable PWA with a FastAPI, Redis and Docker backend.
Read-only MCP server for Trino: six tools, writes refused on the SQL tree, one configured Trino identity, bounded rows and time. Any MCP host, any model.
Deep Rust reimplementation of DeepSeek Elastic Compute (DSec) — sandbox infrastructure for agentic RL training at scale, with a PufferLib core port
Distil - LLM-powered weekly digests from RSS feeds, arXiv, PubMed, YouTube etc.
Catch unsafe tool calls before you ship. Test prompt injection in tool-using agents with reproducible traces and benign controls.
Synthetic agentic-support service for the security bootcamp: fake data, local-only endpoints, v0-v3 tagged vulnerability states
Quantum-safe autonomous cognitive security fabric: Raft consensus, hybrid post-quantum crypto (ML-KEM/ML-DSA), agentic zero trust, GraphRAG and a CNN+Transformer traffic analyzer, with a live 3D simulator.
AI agents that draft cited answers to security questionnaires (SOC 2, SIG) from your own policies. Critic-checked, human-approved, XLSX in/out. Designed and developed by NIKHIL CHARY SRIRAMOJU........
AI that watches experts work, learns their workflows, asks the right questions, and turns tacit knowledge into reusable guidance.
An agentic AI skill that analyzes codebases to create, review, and incrementally maintain clear, structured project documentation
AGENTIC AI PLATFORM MEANT SPECIALLY FOR THOSE WHO CAN MAKE THIS WORD A SPECIAL PLACE TO LIVE IN
FastMcp 3.2 server plus webapp for human/agentic arxiv and doi paper search, rag and store
Source of docs.apowerb.com — the technical documentation for the apowerb open-core stack.
Zero-dependency CLI that bootstraps an agentic AI workflow system into any repo. Verbs over Personas.
AI-powered trip planner PWA: Gemini 2.0 itineraries, TF-IDF RAG chat, CNN scene classifier, DFS route optimizer, live 7-day forecast, Google Maps links, PDF/JSON/ICS export, voice input, offline-installable. Demo mode (no key).
Powerful AI-powered course generator that creates complete code learning courses with multi-agent workflows, interactive lessons, projects, progress tracking, and reusable design systems.
The lab house for industry hackathon tracks, datasets, and more.
An AI agent that runs on Windows XP and has exactly one tool.
My personal GNU/Linux dotfiles
Agentic AI routing lab — Dijkstra/BFS/A* with RAG + CNN topology intelligence, containerized with Docker
Multimodal support-ticket routing: QLoRA LLM + CNN + agentic hybrid RAG + confidence router with frontier fallback. Designed and developed by NIKHIL CHARY SRIRAMOJU.....
AI health and fitness ecosystem: BMI/TDEE calculators, CNN + RAG food scan, multi-agent AI coach, memory chatbot, offline PWA. Live demo on GitHub Pages, plus a Docker full-stack version.
Skills for mobile development
Enterprise-grade Agentic AI customer support engine — LangGraph multi-agent orchestration, hybrid RAG, CNN visual defect inspection, MCP tool protocol, HITL governance, Dockerized.
Corona: self-healing 3D spatial digital twin with a human-approved agentic AI swarm, temporal Graph-RAG, federated vision (ViT+CNN), post-quantum crypto and a tamper-evident audit ledger. Live demo + full Docker/Helm stack.
Syngraphe keeps repository context versioned, current, and understandable by both humans and coding agents.
Meet Jack: The First Agent for Real Privacy and Security. By separating reasoning from system authority, Jack enforces strict local safety gates, sandboxed math solvers, and real-time streaming IRQs to turn untrusted LLMs into highly secure operational tools.
AI cyber defense platform with Agentic AI, RAG, CNN, LLM and Docker, plus a responsive 3D dashboard. Designed and developed by NIKHIL CHARY SRIRAMOJU....
Zero-knowledge personal vault — notes, passwords & files encrypted client-side (AES-256-GCM) before they ever touch the server. Next.js, Supabase, WebAuthn passkey unlock.
AI is not an isolated artificial intelligence. AI is an assemblage of human + LLM + language + “the entire Internet.”
Autonomous AI agents that batch analyze legal contracts for risk, missing provisions, and cross document inconsistencies. Built on AWS Bedrock + Strands Agents SDK. This app is NOT legal advice, just a really fast first pass.
Agentic AI summarizer that compresses source code and technical theory into meaningful summaries. Focus keywords, source tracing, flashcards, multi-format export. Runs in your browser. Designed and Developed by NIKHIL CHARY SRIRAMOJU.
Verification infrastructure for AI reasoning. Privacy by design, safety through cryptography.
LLM-assisted options swing trading: the model proposes trades, you approve each entry, risk rails + an exit manager keep the book bounded. Sanitized public release.
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
A TUI agent harness with multi-session support and Vim-style keybinds.
LongHarness evaluates how language-model harnesses access and reason over long contexts. Its four task suites contain 200 instances that require selective retrieval, verification, and multi-step reasoning.
CLI for image/video generation and editing, designed for scriptability and agentic use, with support for 150+ models.
macOS system monitor with a built-in agentic AI assistant: live CPU, memory, disk, network and battery dashboards, local-first via Ollama
Hermes Desktop plugin: AI-suggested next prompt as a pill under the composer
Always-on personal AI agents (OpenClaw, Hermes Agent, Letta, and more), memory layers, runtimes, and messaging bridges.
Servidor MCP oficial da Assinafy: conecte assistentes de IA para enviar documentos, acompanhar assinaturas e baixar PDFs assinados. Official MCP server for Brazilian e-signature with workspace authorization.
A source-first workspace for documents, data, and presentations with reviewable AI changes.
Custom websites, software and AI assistants for individuals and businesses. Remote projects in English and Portuguese. Explore JE4NDEV products and Nora in production.
Penpal MCP: a local-first memory layer for AI agents on macOS. Gives Claude Code, Codex and Cursor searchable, cited memory of your browsing, clipboard, windows and past AI sessions, with per-agent grants and redaction. No cloud, no built-in LLM.
Edico — AI-assisted LaTeX editor for scientific papers. Chat with Dico to refine style, structure and citations, review every edit as a diff, then compile to PDF. FastAPI · LangGraph · React 19 · PostgreSQL.
SmartBudget is an AI-driven personal & family finance manager built using Flutter and Firebase. Track income, expenses, categories, and investments with smart insights, charts, and secure login. Includes AI assistant for financial planning & real-time budgeting guidance.
A free, open-source personal AI for Mac and Windows. Runs on your computer, with your own models. Built on OpenClaw.
在 DeepSeek Harness (dsh) 桌面端内嵌 chat.deepseek.com:双入口聊天面板(中央主面板 + 右侧栏标签页)、多桌面宿主自适应驱动、持久登录会话,零运行时依赖。
Local AI workbench for Ubuntu/Debian: chat with text, images & voice, a coding agent (Box Code), image generation/inpaint/upscale, document Q&A + RAG, web/file tools, log auditing and agent mode — running LiteRT & GGUF models. All in a pretty GUI.
TelnyxHotel: a multilingual AI voice receptionist demo built on Telnyx AI Assistants, Voice, Messaging, Email and Edge Compute
The Student Tracking System is an AI-powered platform designed for educational institutions, providing features such as personalized dashboards, attendance tracking, class management, and real-time updates. It enhances both student and teacher experiences with smart recommendations and an AI chatbot assistant.
Clanker
✨ XingLing (星灵): A lightweight 0.68B Chinese Chat LLM built from scratch (Pretraining + SFT)
Terminal AI roleplay engine with multi-provider support and automatic memory consolidation.