Custom agents

Tessmora — self-hosted multimodal RAG with an autonomous research agent. Search documents, images, audio, and video with traceable citations.

The Audited Context Generation (ACG) Protocol prevents AI hallucinations with a dual-layer system. The UGVP layer links every fact to a precise source for verification. The RSVP layer audits the AI's logical reasoning when combining facts. This creates a fully transparent, machine-auditable trail for both source and logical integrity.

Real-time AI Avatar interface powered by Google Gemini. Features a customizable VRM anime-style character with low-latency voice interaction, conceptually inspired by xAI's Ani

Open-source Glean for SaaS and the physical world. 87 connectors, hybrid search, autonomous agents, MCP server. Self-hosted, AGPL.

A clean, modular implementation of an Agentic RAG (Retrieval-Augmented Generation) system built with a production-ready architecture.

Local-first agent skill manager for VS Code / Cursor. Manage, browse, and import skills across Claude, Cursor, Codex and more.

A comprehensive advanced course for building production-ready AI agents using the Strands Agents SDK. This repository contains 6 progressive labs that teach advanced capabilities including tool integration, memory persistence, Model Context Protocol (MCP), and comprehensive observability.

Demo projects and examples for Apache Flink Agents

A real-time conversational AI platform built on AWS with Amazon Bedrock Nova Sonic for voice and Amazon Bedrock AgentCore Runtime for chat. While designed as a hotel guest services assistant, this platform is easily adaptable to any industry by simply changing system prompts and integrating industry-specific tools via MCP servers.

Chessmata: chess game for humans and AI agents

A lightweight Vue component and composable designed for AI chat applications to smoothly stick to the bottom of messages.

A standalone Rust memory engine for AI coding assistants. Single binary, zero runtime deps. Graph-vector hybrid with MCP tools.

OpenFused is a shared memory and messaging layer for AI agents, built on plain files. It gives agents persistent context, signed mail, and peer sync without locking them into a proprietary runtime.

AI agent skills by BESSER-PEARL, systematic paper review, and more. Works with Claude Code, Cursor, Copilot, Windsurf, and any skills.sh-compatible agent

Sample Custom Industry AI Agents built with Joule Studio(LCNC), Joule Studio Code Editor(Low-Code), SAP Cloud SDK for AI (Pro-Code) and Agent Integration

Auto-sync Git worktrees with remote branches. Includes an MCP server so Claude Code, Cursor & other AI agents can inspect and manage worktrees.

LiSSA: A Framework for Generic Traceability Link Recovery

AI image generation CLI. One command, one image, three seconds. Gemini-powered.

Claude Code harness for disciplined Java backend dev — risk-classified routing, 6-phase lifecycle (Explorer → Propose → Review → Implement → QA → Archive), 13 specialist agents, gate-enforced contracts. Prevents LLM slop via spec-first briefs, TDD, and WAL.

Trae AI Agent 增强框架 — 34 个技能 + 8 条规则 + 双轨记忆。稳定、专业、中文优先。

A collection of reusable AI agent skills and standalone CLI tools for Manus, Claude Code, Qodo, Cursor, and more.

Self-hosted multi-agent AI platform — isolated Docker containers, governance & compliance, DSGVO-ready. Built for teams.

A closed-loop security runtime preventing "The Great Exfiltration" and Indirect Prompt Injection in Autonomous AI Agents.

Common GitHub workflows, actions, and shared tooling used across the Strands Agents organization.

MCP-сервер: документация API платформы 1С, строгая типизация BSL, стандарты кода. Keyword, semantic и hybrid поиск для AI-ассистентов.

An autonomous orchestrator for the Copilot Go SDK in Neovim, delivering a native, agentic coding experience.

面向 AI Agent 的微信公众号文章阅读工具。提供 CLI、MCP server 和 Python API。

Autonomous robotics research with simulation feedback

A agent skill that leverages the Perplexity CLI for web research, deep reasoning, and independent validation.

taskers is an agent-first terminal workspace app scaffolded around a Linux-first Rust shell, a flexible terminal backend boundary, and a Niri-like tiling model for terminal workspaces.

Offline voice agent framework for robots — agents, skills, workflows, sub-second voice pipeline, 2D/3D simulation (IR-SIM + MuJoCo), 16 languages, 56 voices, ROS2-native. Runs on CPU/CUDA/Metal, no cloud.

ProPR is an agentic code review system, that can help with unsolicited code reviews as well as join in on pull requests.

Menu-bar system monitor for Apple Silicon (optional local AI agent). Rust + Tauri. No cloud telemetry.

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.

PTY-backed claude -p-style executor for Claude Code, packaged as the claude-e npm CLI

A self-hosted MCP proxy and aggregation platform. Manage multiple MCP servers and expose them through a single endpoint.

SOUL.md governance framework for Hermes Agent — structured memory, skill management, and operational rules

🤖️ A collection of papers, blogs and projects of research agents.

an OpenCode MultiPlexer, to allow seamless switching between parallel running session, both existing and new

Your Local Email Agent

🔍 Connect Perplexity's powerful search capabilities easily to your AI applications with this versatile Python API package.

Open-source local-first AI mental health chatbot and CBT journal powered by Ollama, with RAG, session memory, mood and sleep tracking, self-assessments, and guided SOS exercises.

EnterpriseRAG-AI: The Linux-Native, eBPF-Powered Security & Governance Mesh for AI Agent Workloads

A desktop pet application based on Live2D and AI Agent

AI-native terminal IDE. You control what your AI sees.

Shannon's 5-phase pentest pipeline running natively in Claude Code — no Docker, no Temporal, just /pentest https://github.com/KeygraphHQ/shannon

An AI agent for playing XOShift with Python

Two-layer agentic Earth Observation on satellite-class compute. Fine-tuned LFM2.5-VL perception + tool-calling agent over Sentinel-2 imagery. Galamsey detection in Ghana as the worked example.

Intelligent FFMPEG agent node for ComfyUI - transforms natural language video editing prompts into automated video transformations

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.

Postman Agent Skills for AI coding agents. Sync collections, generate code, run tests, create mocks, publish docs, audit security, and analyze API readiness.

Code intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, smart context assembly - in single tool calls. 54 languages + PLC exports. 69.8% R@5 / 43.6% R@1 on dual-judge code-search eval. Daemon mode (3-19ms). MCP server, 30 read tools, full schemas. Local-first, GPU-accelerated.

Set up a Kiro IDE workspace with one command. Pick a preset and the agents, skills, commands, hooks and MCP config get written into .kiro/ for you.

Build your own local-first digital lifeform: an AI companion with memory, soul, multimodal perception, proactive dialogue, and auditable execution.

VS Code fork with the OpenCode AI coding agent embedded natively as a sidebar SPA via an Electron-main loopback proxy. Open source AI IDE — alternative to Cursor / Windsurf / Claude Code Desktop.

RadCrew.org website with LLM-powered chatbot

Skills that make your AI coding agent prove its work: PRD → TDD → implement → review → ship, where exit codes — not the AI saying "done" — decide every step. A Claude Code plugin, plus one-command install for Codex, GitHub Copilot, Cursor, Gemini CLI and other Agent Skills tools.

Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.

MCP server and agentic SQL/RAG engine for Oracle Fusion metadata and live queries

Hermes Agent 中文增强包：一条命令安装中文补丁，支持 v0.14.x、v0.13.x 和 legacy 老版本。

Skills, rules, slash commands and subagents for Claude Code, routed by intent and compiled into other coding agents — every claim machine-checked, including the artifact counts in these badges.

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool integrations.

An autonomous AI agent plugin for Acode that enables LLMs to directly read, create, and refactor files, while executing terminal commands through a secure agentic loop—bringing desktop-class AI automation to Android.

MCP server that wraps the Dagster GraphQL API — monitor and operate runs, assets, schedules, sensors, and backfills from any MCP client

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

An AI-powered in-game assistant for AzerothCore

Curated Agent Skills directory for course creators, educators, instructional designers, and L&D teams, featuring practical skills for course assets, research, role-play practice, training analysis, visuals, and delivery workflows.

Embedded code reviews directly directly within pi.

Production-grade MCP server for KiCad EDA: PCB design, DRC/ERC, BOM, DFM, simulation, manufacturing.

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, review. /change-manager for brownfield.

AI agent skills for ONES.com: spec-backed ONES App development, Open Platform capability mapping, and .opkx delivery.

Minimalistic, project-agnostic skills and rules for AI coding agents

Open verifier for heso ActionReceipts — verify signed AI-agent action receipts offline, with heso removed from the loop — plus the heso agent-web runtime. One Rust core. No Chromium, no Node.

🦛 Chonkie's recipes for Agents, Context Engineering, and more! 🧑‍🍳 Chonkie knows how to cook (and it cooks well!)

CLI advisor for ClickHouse query optimization. Formally verified rewrite rules + RAG + MCP server.

Claude Code plugin marketplace & agent skills for RudderStack — instrument events, design tracking plans & data graphs, write transformations, build Profiles, and drive the CLI, MCP server, and Terraform provider from Claude Code, Cursor, and 40+ AI agents.

The open standard for agentic software verification: query business rules, assess release risk, and execute autonomous testing workflows.

A batteries-included CLI to bootstrap and manage your autonomous team of coding agents - Claude Code, Gemini CLI, Codex, and more.

A helper tool to sync a tree of Jira tasks into beads tasks, and sync beads state back to Jira

Delegate hard problems to a more capable advisor model while working with a cheaper, faster model day-to-day

Self-hosted AI assistant with WhatsApp, Telegram, Ollama, memory, tools, SQLite, and FastAPI. Built by Naboraj (Nishant)

Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your machine.

ChronosTrade is an enterprise-grade quantitative trading and analytics platform. Engineered for high performance, it delivers a unified pipeline for market data ingestion, dynamic technical indicator computation, high-concurrency backtesting (parameter optimization), real-time signal dispatching

A more autonomous, more persistent, and easier alternative to OpenClaw/Hermes. Give it a task and it will carry it out, even if it takes hours or runs into problems. Memory, skills, self-improvement, scheduled tasks, web browsing, and GUI app usage work out of the box with no extra setup.

a methodology for building AI agents that develop memory, voice, and personality over time. CLI-first. zero API keys. built for Claude Code.

Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

Remind Karo - AI assistant and deadline reminder, management app.

The best CLI for pentest — AI coding agent with exploit, AD, and chain commands

HexaFinance is a production-grade financial simulation platform built with Clean/Hexagonal Architecture in Go and a Python (FastAPI + LangGraph) multi-agent AI research service. It offers portfolio management, buy/sell transactions, expense tracking, live market data, and LLM-powered stock research with deterministic fallback.

Scribo — free, AI-native EN 16931-compliant e-invoicing. ZUGFeRD/XRechnung (Germany) and US plain PDF live; Factur-X, Facturae, Peppol BIS UBL coming soon. Available as MCP server, Claude/Codex skill, CLI, HTTP API, and web app.

Offers 転職プラットフォームと AI エージェントを接続する Skill セット（Claude Code / Codex CLI 対応）

A multi-agent Claude Code framework for running role-based agents across GTM, product, design, and ops — with plans, project substrate, and a reinforcement loop that compounds learning.

Open-source AI Agent OS: a folder of plain-text files that gives your AI coding assistant a lasting memory, house rules, sealed per-client work and a receipt for every run (v8 kernel). Not a chatbot, no people inside. MIT.

Community Platform Developed 100% with AI Agents, Agentic and AI SDLC

A calm command centre for a founder who works with more than one AI tool. Eleven rooms, agents as colleagues, honest data. Point your agent at this repo and build your own.

OASiS — an open-source agentic framework for verified multi-physics, multi-code simulation. MCP server letting any AI model drive eight FEM/multiphysics codes (FEniCSx, deal.II, 4C, NGSolve, scikit-fem, Kratos, DUNE-fem, FEBio) plus the SPARTA DSMC particle code, with curated knowledge, verified execution, and cross-code coupling.

A production-grade Multi-Vendor Food Delivery Platform with AI Chatbot (Groq LLM), Real-Time GPS Tracking (Socket.io), Biometric Auth (WebAuthn), Razorpay Payments, 4-Role Dashboards, and Gamification. MERN Stack + Redis + PWA.

最系统的AI全栈学习实战手册

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents on your machine.

Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.