Custom agents

The Open Data QnA python library enables you to chat with your databases by leveraging LLM Agents on Google Cloud. Open Data QnA enables a conversational approach to interacting with your data by implementing state-of-the-art NL2SQL / Text2SQL methods.

Needle is a Discord bot that creates Discord threads automatically.

A background agent system for automating end-to-end software engineering tasks, direct from your github repos.

Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc)

Local-first, zero-key semantic code search for large and custom codebases — hybrid vector + keyword retrieval with symbol-aware chunking. Usable as a CLI, Python library, REST API, or web UI.

Native Swift SDK for building autonomous AI agents with Apple's FoundationModels design philosophy

An open-source AI agent hub for your own machine: build organizations of collaborating agents that message each other, run in the background around the clock, and share your existing AI subscriptions.

An open source, agentic Loom alternative. Record locally, make recordings AI-ready, and run workflows on top

海狸 IM (Beaver)｜全平台、功能齐全、易二开，一站式私有化即时通讯 & 实时音视频方案

Export your ChatGPT, Claude, Copilot, Gemini and Grok chat, using Tampermonkey on chrome, firefox, and other supported browsers, with rich Markdown formatting, a Table of Contents (TOC), YAML metadata, and more.

Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis, symbol search, and more.

Rust MCP server for multi-agent coordination: 45 tools and 25 resources, Git-backed archive, SQLite indexing, advisory file locks, a 16-screen TUI, a server-rendered web UI, and an agent-first robot CLI.

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can explore it.

Graphical management tool for Kubernetes on desktop and mobile.

Staged SFT→DPO→GRPO/OPD reinforcement learning pipeline for training a ReAct tool-use agent on arXiv paper retrieval tasks, with a deterministic snapshot-replay environment.

Yan's agent skills collection — Google Trends SEO workflows, AI news, autopilot, and more. For Claude Code / Codex / Cursor.

豆包工作系统化中文实践指南：教程、真实任务、Skills、连接器、自动化与多 Agent 工作流。

A non-linear AI agent workbench — session is a tree: branch anytime, and context follows the branch

Valuation of tokens corresponding to influential individuals on social platforms through AI algorithms

OpenClaw-Style Local-First AI Agent in Go - Low-Memory, Private, UI-Ready, Out-of-the-Box

Interact with the Deep Search platform for new knowledge explorations and discoveries

The definitive, open-source Swift framework for interfacing with generative AI.

参考GraphRag使用 Semantic Kernel 来实现的dotnet版本，可以使用NuGet开箱即用集成到项目中

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale.

Agent skill for production-grade ROS 2 development. Progressive-disclosure SKILL.md covering workspace, nodes, executors, QoS, ros2_control, Nav2, MoveIt 2, real-time, and deployment. Works with Claude Code, Codex, Cursor, Gemini CLI.

Built by Dig:An agent-readable, prompt-as-code design system for Codex, Cursor, and Claude Code: catalogs, layouts, blocks, workflows, and personal UI customization.

Copy. Paste. Run. — Production-tested Agent · Skill · Squad templates for Multica, bilingual (Chinese/English)

Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.

A modern terminal with a built-in multiplexer: close it and your sessions keep running. Run shells and tons of AI agents across your machines, then pick them up from desktop, browser, TUI and more. Written in Rust with no UI framework: interface drawn straight on the GPU. No Electron, GPUI or webview.

Open-source desktop coding agent where a lead model plans and cheaper models handle search, edits and review.

Field-tested guides, agents, scripts, and analytics from Microsoft FastTrack to plan, deploy, govern, and measure Microsoft 365 Copilot and Agent 365.

A collection of RAG systems powered by LLM.

[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use

Low-code/no-code python library that transforms plain English instructions into fully configured multi-agent AI teams

skilless.ai gives your AI Agents real data capabilities - web search, web scraping, video download/subtitle extraction, and media processing. One-line install, works with OpenCode, Cursor, Claude Code, and any AI agent that reads skill files.

Библиотека по разработке чат-ботов для мессенджера MAX

AI-powered COBOL to Java Quarkus modernization agents using Microsoft Agent Framework. Automates legacy mainframe code modernization with intelligent agents for analysis, conversion, and dependency mapping.

File-based kanban board for autonomous agentic loop. CLI and TUI for multi-agent workflows. Skills included.

Agent-Sandbox is an easy-to-use, enterprise-grade sandbox platform for AI Agents — letting them securely run untrusted LLM-generated code, Browser use, Computer use, and deploy websites, among other tasks.

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.

A hand-curated, topic-organized library of the best ML education — 923 docs (391 arXiv papers, 474 Stanford/MIT/Karpathy/fast.ai lectures, 58 explainer articles), normalized to Markdown with full provenance. Open it in Obsidian or point your agent at it. A clean ML corpus for learning, RAG & fine-tuning.

Open-source agentic AI Search Execution Platform. Track AI visibility, find opportunities, and let agents turn signals into prioritized actions and drafted fixes across ChatGPT, Claude, Gemini, Google AI Overviews, Google AI Mode, Perplexity, Grok, and Microsoft Copilot.

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.

让自动化AI科研只剩最后一块拼图

Offline Clash Royale AI agent research: native simulation, imitation learning, PPO, and interactive evaluation. 离线对局模拟、模仿学习、强化学习与交互评测。

Beta. Self-hosted panel for running a VPN for others: family, friends, a community or a small team. Hysteria2, VLESS REALITY and AmneziaWG, one link per person. Add servers from the browser over SSH; client-eye health checks and Telegram alerts; MCP for AI agents. Two static Go binaries, SQLite, no Docker.

10-part module to build AI-native apps. From data analysis to multi-agent model harness. For curious learners and serious AI builders.

Terminal AI coding agent built for DeepSeek. Features: MCP tool integration, Skills extension system, prefix-cache optimization for 97% live hit rate, 1M context window.

PsyDI: Towards a Personalized and Progressively In-depth Chatbot for Psychological Measurements. (e.g. MBTI Measurement Agent)

AI tools for building on Uniswap — skills, plugins, and agents for any coding agent.

Practical OpenClaw tips for memory, reliability, cost, automation, and multi-agent workflows.

Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and MCP tools for Claude Code, Codex, Copilot, Cursor and more, plus SDLC workflows, session memory, and Jev decision support that offloads bounded LLM decisions to save tokens.

Turn AI coding into an engineering process.

Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.

Open-source AI agent framework for security engineering across AWS, GCP, Azure, Kubernetes, GitHub & GitLab: AI-powered security review, findings triage, detection and response.

A free detector capable of identifying content generated by all advanced AI models.

Agentic Data Engineering Harness for building data pipelines, data products, data APIs, and data lakes autonomously

Make AI agents work like real teammates—taking ownership, collaborating, and delivering results.

Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.

Arabic home screen and Saudi screensaver for Android TV / Google TV, plus a safe speed-up. Your AI agent sets it all up. واجهة عربية وشاشة توقف سعودية لتلفزيونات أندرويد، يركّبها لك مساعد الذكاء الاصطناعي.

Instantly generate full-stack admin panels, APIs, and UI from your database schema—powered by AI agents & LLMs and hope to have a self evolving runtime in the future based on usage

the sane way to work with ai agent streams (type safety and stream resuming out of the box)

[ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Agent Space is an open-source framework that automatically selects the appropriate agent based on task requirements, executes the task, evaluates the results, and returns the result.

Ranking LLMs on agentic tasks

Framework for Generative Agents in Games

Open-source, fully private and local alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sources—built with Supabase, N8N on a React frontend using Ollama for local inference

Fast, cross-platform, real-time token usage tracker and cost monitor for Claude Code / Codex CLI / Antigravity CLI / Qwen Code / Cline / Zoo Code / Kilo Code / GitHub Copilot / OpenCode / Pi Agent / Piebald.

[NeurIPS 2025 & ICLR 2025 Financial AI Best Paper Award] A multi-agent framework that leverages LLMs to simulate socio-economic systems

[ICLR'26] Stronger-MAS: A RL Framework for multi LLM agent system; [arxiv] MetaAgent-X: End-to-End Reinforcement Learning Automatic Multi-Agent Systems

[EMNLP '26] Dependency-Aware Structural Retrieval for Massive Agent Skills

法穿AI Copilot

🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.

A curated collection of resources, papers, tools, and best practices for Context Engineering in AI agents and Large Language Models (LLMs).

🤖 Type-safe durable execution for agents and workflows. Resumable runs, append-only history, and compensable steps for TS/JS, React, Solid, Vue, and Svelte.

Academic literature discovery as a Skill — Claude Code · Codex · any agent that loads SKILL.md. Five sources · four tiers · single-file Shadcn report.

Frakio Work - 终极缝合 AI 工作台，致力于在一个对话中丝滑调用多 Agent 协作。Hermes 和 Pi 双重内核，Hermes管生活长期记忆进化，Pi 管编码等复杂任务

A repository for skills that are essential to my daily work

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

Agent Space is an open-source framework that automatically selects the appropriate agent based on task requirements, executes the task, evaluates the results, and returns the result.

Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond

TeamClaw, AI Agent Desktop Workspace

🏆 gym-cooking: Code for "Too many cooks: Bayesian inference for coordinating multi-agent collaboration", Winner of the CogSci 2020 Computational Modeling Prize in High Cognition, and a NeurIPS 2020 CoopAI Workshop Best Paper.

BondAI is an open-source tool for developing AI Agent Systems. BondAI handles the implementation complexities including memory/context management, error handling, vector/semantic search and includes a powerful set of out of the box tools and integrations.

AI App Bridge is a runtime bridge for AI agents to close the loop on mobile app iteration: inspect the running app, operate UI and WebView surfaces, collect structured runtime state, verify results, and continue improving the app.

Kiro Best Practices Boilerplate

MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

专门为 agent 打造的开源 agent 搜索工具，具备 200+的搜索源及多语言搜索能力，覆盖中文/英文/学术/代码/购物/金融/新闻/百科。

Agent-ready Amazon Scraper API: real-time product details (batch ASIN), offers & stock, reviews, search, best sellers, deals and seller data across 20 marketplaces. One pasted line for Claude Code / Codex / Cursor, an MCP server, or plain HTTP with 3 free calls a day and no key. Python examples inside.

本项目是基于webnovel-writer 改编的 OpenCode 版本，目标是让用户在OpenCode 使用长篇网文创作系统，解决 AI 写作中的「遗忘」和「幻觉」问题，支持 200 万字量级 连载创作。

An agentic skills framework & bundle-plugin engineering toolkit that works.

An LLM-based agent that will install the tools it needs.

Multi-agent autonomous framework — let your AI work while you sleep 🌙

Red Teaming python-framework for testing chatbots and GenAI systems.

数据分析智能体 (Data Analysis Agent)：基于LLM的智能数据分析智能体

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.