Custom agents

Talkify is an open source framework with an aim to standardize and model conversational AI enabling development of personal assistants and chat bots. The mission of this framework is to make developing chat bots and personal assistants as easy as spinning up a simple website in html.

Opinionated knowledge extraction and semantic retrieval for Gen AI applications.

Microsoft's Kernel Memory StructRAG implementation

An autonomous AI agent here to uncover waste and inefficiencies in government spending and policy decisions

An Autonomous Spectrum Management Scheme for Unmanned Aerial Vehicle Networks in Disaster Relief Operations using Multi Independent Agent Reinforcement Learning

Modified MDP and Q-Learning Algorithm | Multiagent optimization | Path Planning | Navigation | Reinforcement Learning | Stochastic Systems | Swarm Robotics

calling any functions in any binary files under MacOSX

Simple embedded NLU for mobile apps

AI chat application using Electric for resumeability, interruptability, multi-user and multi-agent sync.

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

The offcial implementation of "ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind" (ICLR 2022) .

Anti-Spam bot for Discord

[RAL 2025]Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network

Deploy generative AI agents in your contact center for voice and chat using Amazon Connect, Amazon Lex, and Amazon Bedrock Knowledge Bases

AI Agent Daily Digest — Collect and analyze your AI coding assistant usage

Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"

Omnigram is a Flutter-based file reader and audiobook . It accommodates EPUB and PDF and offers audiobook functionality, supporting TTS model and other AI chat technologies for enhanced reading experiences

happy-llm 实践练习：colab 版本、pynb 格式，GPU 免费

Turn a codebase, a requirements document, or both into a living skills system for AI coding agents.

vue3 + AI Skills实现的aippt项目

API Framework heavily relying on the power of DuckDB and DuckDB extensions. Ready to build performant and cost-efficient APIs on top of BigQuery or Snowflake for AI Agents and Data Apps

Tiny Agents: LLM + MCP Tools

Open Source Library for Automated Optimization of AI Agent Workflows

설교 비서 AI 에이전트 워크플로우 — AgenticWorkflow DNA 기반

A memory layer for AI agents that organizes itself

Stop your AI agent from shipping insecure IaC. ops0 CLI sits between Claude Code, Codex or Gemini and your cloud, scanning every .tf the agent writes and blocking destroy commands before they run.

Local AI agent desktop app — chat, IM bridge, scheduled tasks. Powered by Claude Agent SDK.

Curated, opinionated index of post-R1 LLM × Reinforcement Learning. Many deep-dive blog posts cross-linked to many papers — GRPO, DAPO, DPO, PPO, RLHF, GSPO, CISPO, VAPO, Reward Modeling, MoE RL stability, Verifier-Free RL, Training-Free RL, Agentic RL, DeepSeek-R1 reproduction.

HippocampAI Autonomous Memory Engine for LLM Agents

Tide Commander - Visual orchestrator for multiple Claude Code, OpenCode and Codex agents

Superplan is a CLI-first execution system that forces AI agents into step-by-step task workflows instead of drift-prone chat-based work.

A comprehensive catalog of 34 Retrieval-Augmented Generation (RAG) techniques. Features Python pseudocode, pros/cons, and architecture concepts ranging from basic retrieval to advanced agentic RAG, GraphRAG, and self-correcting workflows.

WayLog - Save & Export AI Chat History. A local-first extension that turns your fleeting AI conversations into a permanent, git-friendly knowledge base.

Samples showing architectural patterns for Modular RAG using Spring AI and Ollama.

Centralized multi-system scalable fan control. Real-time dashboard, custom curves, Docker server + native Linux/Windows agents. Selfhosted with Docker

An AI agent to automate dating using hinge

OpenPawz is a native, offline-first desktop AI platform (Tauri v2 + Rust) that lets you run local models or connect to any compatible provider. It gives you private-by-default agents with hybrid memory, strong security guardrails, and extensibility through built-ins plus n8n community integrations

GenDB, an LLM-Powered Generative Query Engine Built for the Future

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

Open-source framework for agentic quantitative finance research.

思維模型工具箱 — 200+ mental models across 10 domains for AI-assisted thinking. Agent Skill for Claude Code.

[ICML2026]A method to use LLM function calling with real-time level speed, empowering latency-sensitive applications like robotics, game AI, and autonomous agents.

Local LLM agent for vintage Mac hardware. Built on a 2013 Mac Pro trashcan with dual AMD FirePro D500s. Elyan Labs.

一个越用越懂你的 AI 音乐 Agent，让音乐搜索、播放与管理变得更自然、更智能。

Linux port of cmux, A Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

This is an attempt to make original open mythos better with chat ui.

Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.

🌍 30 AI-powered geoscience skills for Claude Code, Cursor & GitHub Copilot. Seismic, well logs, 3D modelling, inversion, geostatistics, spatial regression, NetCDF, and more.

Obsidian AI is an open-source platform that gives you a full visual interface for building, managing, and running AI agents — no SDKs, no boilerplate, no glue code required.

A Claude skill blending psychology, philosophy, and wisdom traditions into a conversation partner with actual depth. Free, open-source, not a therapist.

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

DNS-based Agent Identification and Discovery - Reference Implementation for IETF BANDAID

Vorim Agent Identity Protocol (VAIP) — Open standard for AI agent identity, permissions, and cryptographic audit trails

Where the fox came from — the original AI full-stack project generator with multi-agent codegen and live preview.

Persistent memory, decision-making, and governance for AI agents

Remembrance Agent - a continuously running automated information retrieval system

An ntfy MCP server for sending/fetching ntfy notifications to self-hosted or ANY ntfy.sh server from AI Agents 📤 (supports secure token auth & more - use with npx or docker!)

A skill to refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files into a compact routing entrypoint plus focused docs/ reference files.

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Skill de Claude Code para crear automatizaciones (agentes de IA) en Cloudflare desde cero, en español sencillo. Por Horizontes IA.

StewardOS - agentic autonomous OSS system

Open-source Computer Use Agent that works for Any App (GUI or CLI) by Any Model (Vision or Text).

多Agent智能合同审查系统 Python/Java/Go

The most complete chat UI for React Native & Web - streaming AI messages, emoji reactions, replies, quick replies, and full customization. TypeScript-first, Expo-ready.

An Agent Skill to watch the deadlines of latest AI conference.

EloquentJS monorepo — Laravel Eloquent for Node.js

Lab Walkthrough and Demo for the "Collaborating with agents in your software development workflow" workshop

Claude Code, Codex CLI, Gemini CLI ve diğer yapay zekâ destekli coding agent’larını tek merkezden yöneten açık kaynaklı bir multi-agent orchestration aracıdır. Görevleri agent’lara dağıtır, paralel çalışmalarını koordine eder, çıktıları agent’lar arasında aktarır ve tüm geliştirme sürecini tek bir terminal üzerinden yönetmenizi sağlar.

The agentic node editor for live visual effects

Open-source, self-hosted Claude Code Artifacts on Cloudflare — publish, password-protect, and auto-update shareable HTML/Markdown pages from any coding agent.

LLM-powered natural language data agent — no vector retrieval, pure JDBC multi-datasource support, with a semantic layer that maps business language to schemas.

Multiplayer terminal multiplexer where multiple users and machines can connect to a same session

Local Agent chat and content publishing studio for Obsidian.

Snag web pages like a polite robot with a browser

TigrimOSR is the Rust version of TigrimOS — a high-performance native desktop rewrite of the original Python/Node.js AI assistant. Built entirely in Rust using egui for the UI, TigrimOSR delivers faster startup, lower memory usage, and a single self-contained binary with no Node.js or Python runtime required to run the app itself.

WeChat group & official-account AI knowledge digest — agent-friendly (Codex/Claude Code), Windows/macOS/Linux

Memory, working state, heartbeat, and bounded autonomy for long-running AI agents.

Cuti Harness: An open-source, plugin-based video world harness

CODING — a local-first AI coding agent for repository-aware planning, execution, validation, and delivery.

Turn Claude Code into a senior software architect that orchestrates a team of specialist agents and audits itself. An 8-phase skill with TDD verified by mutation, phased decomposition, an event-driven PR pipeline, and quality gates with teeth.

Give your LLM agents the power of JetBrains Rider IDE! Supports C# 15 Syntax!

Your infinite desktop just for your AI agents. Inspired by DriftWM.

RobloxForge Docs 2026: Official MCP Vertical Slice Verification Layer for Studio

A curated, hands-on library of notebooks, demos, and resources for AI/ML, Deep Learning, Generative AI, AI-Agents, fine-tuning, and modern tooling.

Remote-first tmux IDE for coding agents. Agent notifications on desk and phone, voice replies, screenshot paste over SSH, multi-host, ports, files, and Git.

把 Claude Code 变成你的短视频团队：不搭工作流，直接让 Claude 干活，从国内热榜、推特热帖到抖音、小红书、B站、YouTube、推特发布。Turn Claude Code into your short-video team — no workflows, from trends and X posts to publishing.

Capability delegation and authorization for AI agents: scoped, attenuable tokens bound to SPIFFE workload identity and verified fully offline. Go, SPIRE, gRPC, MCP.

麦探长 · 麦当劳物价侦探——真实调用麦当劳 MCP（只读），查遍方圆几公里：哪家便宜、哪家有货。跨店比价、盘积分、核热量、点餐推荐，每条数字都锚在真实接口、可戳开核验，不编造。麦当劳程序员节参赛作品 · WorkBuddy Skill · 网页在线可用

A curated collection of research on socially intelligent conversational agents.

An opinionated atlas of post-R1 LLM post-training: RL, rewards, alignment, distillation, agents, and their connections.

Remotion Agent Skills for Claude Code

P2P-first tunnels to private TCP/UDP services: direct QUIC with automatic relay fallback, one TCP + one UDP port for every service, built-in scoped keys and event listeners. Rust CLI plus Rust and Node SDKs, made for agent-harness remote control.

Agent skill and toolkit for reconstructing Gaussian splats as editable Blender Geometry Nodes meshes and Shader Node materials.

Watch over your agents' shoulder. A TUI that shows Claude Code, Codex, Gemini CLI and opencode work in your project, live.

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Can LLM agents do the work of an operations research practitioner, without an expert reformulating the problem first?

A framework for AI-driven economic activity. Declarative, composable, observable, deterministic.