Custom agents

Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine — zero data sent to external services.

A Tomb Raider Custom Level management application

This repository contains code for the RAGonite project, a flexible RAG pipeline developed by the NLP team at Fraunhofer IIS, Erlangen, Germany. RAGONITE supports conversational question answering over heterogeneous data, iterative retrieval over structured and unstructured sources, automated database induction from knowledge graphs, and much more.

A Module for Large Language Models that seek to integrate a vector-based memory system into the inference process, leveraging embeddings to capture deeper semantic meaning.

A century-old style manual, converted into a taxonomy of agentic writing skills.

LLM驱动的情景解谜游戏 | AI海龟汤

Implementation of autonomous AI agent(s) in JS using Webworkers

An AI-native, lightweight web kanban board for tmux sessions and terminal agents.

Analyze Stocks using Deepseek-R1 and Ollama

Multi-mode, multi-agent idea ➡️ reality creation app.

Steuermann is designed as a domain-agnostic, on-premise AI runtime. It can be extended with profiles to adapt to specific use cases.

AiTaxs 综合财税 AI 助手skill

No longer maintained.

The community version of the Web Speed mapping tool

Installable Codex skill for long-running autonomous coding refinement loops with validation and resumable state

Nix flake framework for distributing, propagating, and sharing agent skills

📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .

AI-native agent framework for Go.

AI-powered job application automation with GPT-4o, LinkedIn auto-connect, resume optimization, and cold email campaigns. Features AI agents for contact ranking, scam detection, and memory layer for learning from successful outreach.

A 7-agent pre-release audit pipeline for software products. Generic, reusable, AI-native. Inspired by Garry Tan's gstack.

Python SDK for the Carbonyl terminal browser. Persistent named sessions, daemon mode, realistic browser fingerprinting, screen-text inspection, and host-browser cookie import. Lightweight Selenium/Playwright alternative purpose-built for LLM agents and scraping that needs a real browser but not a real display.

Agent-interpretable data-science tools, evolved via autoresearch.

OpenClaw Execution Firewall - Seccomp-locked AI agent sandbox with policy-enforced command governance, WhatsApp/Telegram integration, and Python isolation. Deploy on Oracle Cloud Free Tier.

Your local long-term memory for AI agent interactions. Parse, classify, search, and visualize every interaction with Claude Code, Codex CLI, Claude Desktop, and ChatGPT.

Turn MetaTrader 5 into a REST API server for algorithmic trading - supports historical candles, account data, and trade execution via HTTP.

PhantomEar is a privacy-first, local-only AI meeting assistant that runs invisibly on your machine. No bots, No cloud recording, No admin permissions.

EdgeTales - A Narrative Solo RPG Engine

Deterministic, scriptable CLI and live TUI for Planka kanban — built for shell scripts, CI/CD, and AI agents.

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.

Declare boundaries for coding agents with .human files.

Stop Claude Code from doing irreversible damage. Policy-gated execution + receipts so you can ship agents without sweating production.

Skills IA pour la bureaucratie luxembourgeoise (comptabilité, TVA, RCS/LBR, eCDF, FAIA, notariat, copropriété) — disponibles sur AgentSkill.sh/@gregherbe76

| Maintenance Mode | OAK automatically captures the plans, decisions, and trade-offs that usually vanish. Intelligence powered memories, context injection, autonomous agents, and more.

A daemon for discord bot with multiple agent.

Unit tests for AI agents

AI Company Orchestration Platform — Deploy governed teams of autonomous AI agents with Runtime Agentic IAM, credential vaults, heartbeat orchestration, and enterprise security. Built on Paperclip.

⚡ SOTA agent skills for OpenClaw — observability, security, code quality, incident response, and more. Built by Anvil AI.

🕸️ Code knowledge graph for Claude Code & AI coding agents — index TypeScript, NestJS, React into Neo4j and query architecture in Cypher

Agent Session Manager - A comprehensive Elixir library for managing AI agent sessions, state persistence, conversation context, and multi-agent orchestration workflows

Terminal-native LifeOS with an optional local Web UI for tasks, notes, habits, schedules, timelogs, relationships, and human-agent collaboration.

MindForge is a Python library designed to provide sophisticated memory management capabilities for AI agents and models. It combines vector-based similarity search, concept graphs, and multi-level memory structures (short-term, long-term, user-specific, session-specific, and agent-specific) to enable more context-aware and adaptive AI responses.

The open source repository for Ripley Terminal, a noncustodial, first AI-Enabled Monero Desktop Wallet.

A CLI for Trello built for AI agents and Claude Code — includes a ready-to-use Claude Code skill for autonomous Trello management

Autonomous agent orchestrator — polls Linear issues, creates workspaces, runs Codex sessions.

Persistent memory for AI coding agents with outcome-based learning

Research guides and RAG indexes for AI agent development

[PETS'26] AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents

Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. 3696 tests, zero deps.

A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten

Canvas Notebook — Your AI workspace with file management, agent support, and bring-your-own-model flexibility.

Multi-agent system for drafting and managing GitHub issues. Built with BeeAI Framework, integrated via GitHub MCP, and consumable through Agent Stack CLI & UI via A2A.

⚕️ Multi-agent SLM system for medical question answering — domain-aware, private-by-design, cloud-free

The best blockchain harness for agentic AI - on-chain execution with runtime, skills, and component library.

A tool for managing Claude Code Tasks across all your projects

Public skill pack for AI coding/automation/penetration-testing agents.

Strands Agents in Rust

Semantic grep for codebases — tree-sitter chunking, vector search, shared via Git orphan branch

AWS Bedrock Agentcore sample illustrating multi tenancy

https://nellaivijay.github.io/awesome-agi-aci-asi/ - The most comprehensive curated collection of AGI and ASI resources -- frameworks, agents, physical AI, robotics, research papers, safety & alignment, books, benchmarks, and conferences for builders and researchers shaping the future of intelligence.

One source of truth for AI agents, skills, rules, and hooks. Transpile to every AI CLI you use.

Your AI buddy is ready to help you achieve your goals in IETLS Writing

AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis

🖥️ Mistral_Desktop is a desktop application designed to provide an optimized Mistral experience.

RAG based LLM using Pathway and Dify for practicing consulting case studies

AI companions including generative AI such as chatbots, image generation, text generation, and audio generation.

Collection of various Android applications developed using Flutter. Serves as a collection of Android applications built for different purposes, including utilities, productivity, and experimental projects. Each application has its own folder containing Read me, source code, assets, and other required documents.

AI-powered study assistant for personalized learning, exam revision, and concept mastery. Streamlit web app integrating Gemini 2.5 Flash API for instant explanations, PDF summarization, smart quiz generation, and automated answer evaluation—built for students and educators.

ESG knowledge graph + RAG agent. Turn long-form sustainability disclosures into cited answers, extracted entities, and a reviewable graph of evidence.

工业知识智能问答系统

CLI converter from 1C .hbk help archives to Markdown vault with indexes and breadcrumbs

⚡ Vectro: Lightning-fast embedding quantization. Hit 12M+ vec/s throughput (4.85× faster than FAISS C++) while drastically cutting memory footprint for vector databases and local AI research.

A training-free, retrieval-side memory framework for long-horizon LLM agents — high accuracy at an order-of-magnitude smaller context budget.

SharpAI is an embeddable embeddings, completions, and model management platform using llama.cpp via LlamaSharp, with a built-in Ollama-compatible webserver.

Python package that constructs a structured markdown knowledge base from external sources such as PDFs, websites, and GitHub repos with LLM summarization. Ideal for RAG, search-friendly LLM contexts (/llms.txt), and chatbots.

RAG Poisoning Lab — Educational AI Security Exercise

🐝 Distill personal semantics into verifiable AI skills and teachable assets.

👌🏻 Pick code into Markdown. Apply Markdown to code. Built for LLMs and quick backups.

A simple example for a game using CogentLM inference

curl for x402 and MPP paid APIs. CLI + MCP proxy that auto-pays any endpoint on Base, Solana, and Tempo. Zero crypto code on the buyer side.

AI mobile automation starter repo for AIVane. Android REPL beta, Python client, skills, examples, and protocol docs for AI agents.

Automated Interpretability and Feature Discovery in Language Models with AI Agents

Bitrix24 channel plugin and skill for OpenClaw — chat with your AI agent through Bitrix24 Messenger

A simple collection of tools for better plan management by AI agents on OpenCode.

Keep the agent awake, even when the lid closes.

Local-first MCP coordination hub. One local daemon serves multiple AI assistants across IDEs — shared meetings, tasks, messages, and project registry. Works with Claude, Cursor, VS Code, Zed.

AI browser automation conductor — type a prompt, watch it happen live, get a reusable skill

Secure VPN-routed Chrome environment for AI agent persona management. Headless display, Mullvad VPN, CDP + WebSocket browser control, VNC monitoring. Works with Hermes Agent and OpenClaw.

Residential proxy SDK for Python. 175M+ IPs across 195+ countries. pip install iploop

Natural language task management via WhatsApp/Slack → Notion, with automatic GBrain knowledge enrichment

AI agent skill for searching flights, tours & excursions with real prices and booking links. Works with Claude Code, Cursor, Gemini CLI, Copilot and 30+ AI agents.

基于 Spring Boot 3.5 + Java 21 + Spring AI + Vue 3，实现 AI 情感咨询、深度思考智能体、RAG 知识库检索、多工具调用等核心功能。支持恋爱报告生成、地图服务集成、PDF文档处理等实用场景。架构清晰、文档完善，非常适合作为 AI 应用学习和简历项目，学习门槛低

Install Kodus AI Agents in your own infra.

Enterprise-Ready Bi-Temporal Knowledge Graph Platform

7 AKU-architected skills for OpenCode + Obsidian MCP: obsidian-mcp, inbox-triage, connection-review, weekly-synthesis, context-maintenance, vault-health-feedback, note-promotion. Knowledge Activation v4 with validators, EDD evals, and CI. Built on obsidian-mcp-server. Works with OpenCode and Claude Code.

AI-powered news intelligence with 8 Vertex AI agents monitoring 50+ sources. Real-time executive dashboard, daily briefs, and smart alerts. Built on Firebase + A2A protocol.

Trust and delegation controls for Paperclip agent teams, powered by AgentVeil Protocol.

a vision first broswer tool

Automated comic cataloging tool that identifies issues directly from cover images using a vision-language model, then cross-references results with the Grand Comics Database and the ComicVine API to generate structured, high-confidence collection data with minimal manual entry.