Business agents

Adds extra features to Twitch

A PoC for a location-aware legal assistant powered by GPT-4 and Gradio.

AI gateway as a framework. For full control over models, routing & lifecycle. OpenAI /chat/completions, OpenResponses /responses & Anthropic /messages.

Python agent framework with AgentHarness: planner → generator ⇄ evaluator loops for long-running tasks—plus sessions, tool/safety policies, and Claude, GPT, or Gemini.

[ICLR 2025] Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate

MCP server for scheduling and running AI prompts, HTTP/webhook requests, and shell commands

A complete, hands-on roadmap to becoming an AI Engineer, from Python basics to production RAG, Agents, and Fine-Tuning. 10 modules, 20+ notebooks, 15 real projects. Free, open source, built for the community.

Deploy agents to Claude Managed Agents, AWS Bedrock AgentCore, and Google. One folder, one definition, one command.

🪢 Local-first, agent-agnostic R&D harness — persistent memory, domain SOPs, contract handoffs & quality gates for PM + Engineering | 本地优先、工具无关的 AI 研发治理与交付框架

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on collected agent rollout trajectories.

Dr.RTL: Autonomous Agentic RTL optimization through Tool-Grounded Self-Improvement

⚖️ Extensão Chrome que analisa autos do PJe com IA (Claude): chat sobre as peças do processo, OCR nativo, tabelas e linha do tempo — direto na tela do processo.

Persistent RAG memory layer for AI agents - store observations, retrieve context by semantic similarity, self-prune on TTL

An intelligent AI Calendar app that sits on top of your Google Calendar - helps you manage your schedule via conversational AI capabilities. Schedule, manage, and reorganize your events naturally through chat.

DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents

👨🏽‍⚖️ LegalEngine - qqmbr team - Junction2017

🚀 Excited to introduce "Unique Bedtime Chronicles" app! 🌙✨ Transform bedtime into a personalized adventure for your child. Craft custom stories, save favorites, and make bedtime unforgettable.

VALORA (Versatile Agent Logic for Orchestrated Response Architecture) - The future of software development is not about replacing developers, but amplifying their capabilities with intelligent AI collaboration

This project is a pipeline that connects a Matlab simulation (Simulink) to an OpenAI Gym wrapper for PyTorch Reinforcement Learning using the DQN algorithm.

Talk to your Follow Up Boss CRM in plain English. 159-tool MCP server for realtors, built by a working broker (Neuhaus Realty Group, Austin TX). Free self-host, ELv2 licensed.

Plateforme IA juridique souveraine, auto-hébergeable et open-source. Bring Your Own Key, agrégateur de modèles FR/EU/US, RAG pgvector, orchestration multi-agents.

[Agentic AI-RPG] Agentic AI role-playing game framework — narration, NPCs, lore, and character creation are autonomous plugin agents. Build interactive fiction with DeepSeek / OpenAI / Anthropic / Qwen.

This is OpenAI's computer use hooked up to a chrome extension.

AI-powered shell assistant that helps you execute commands and file operations through natural language.

Local-first personal memory & knowledge store for LLM agents. ローカルLLM向けの個人用メモリ／知識ストア（short / chronicle / memopedia / archive の4層構成）。

Curated resources about automated GUI computer-use via LLMs. Highly opinionated, focus is on quality vs quantity.

Asynchronous LLM Agent playing games of Mafia against human players

Let AI agents control Classic Mac OS through a shared folder protocol.

Rust browser automation over the WebDriver BiDi Protocol and CDP

Full-featured MCP server and CLI for LINE WORKS (NAVER WORKS) — 26 tools covering messages, calendar, drive, mail, tasks, and boards. Automate with AI agents or scripts.

A visual runtime for AI, GPU computing, and robotics, workflow framework for AI agents. MCP-native typed graphs, visual editor, Python export.

Doubt, until what remains is certain. An MCP server that recursively doubts every plan decision — grounding each in real evidence or asking you — until it converges. Runs on Claude alone, no keys. Sibling of The Asker → github.com/pranjalbhatia710/the-asker

A KDE Plasma plasmoid to add desktop chat with LLMs

A minimalistic async Rust implementation of the Model Context Protocol (MCP).

Chat with your PDF files for free, using Langchain, Groq, ChromaDB, and Jina AI embeddings.

🌟BuroTonic: Revolutionizing Sales and Marketing with AI-Driven Business Intelligence - An adaptive team of virtual agents for precise client and market strategies. 🚀

Claude Pro Desktop — Anthropic Claude Pro Desktop 2026 — extended context window, project workspaces, artifacts, and computer use.

A minimalist Go implementation of Microsoft's GraphRAG

🤖 MCP Server for Substack integration with Claude AI Desktop. Download and parse Substack posts directly in your Claude conversations.

A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.

An MCP Server in Rust for creating Notion pages & mdBooks with LLMs 🦀

Your AI-powered SWE teammate, built into your git workflow

This project implements an advanced Retrieval Augmented Generation (RAG) workflow to enhance question-answering accuracy and reduce LLM hallucinations. It leverages LangGraph to create a stateful, multi-step process that includes document retrieval, relevance grading, and web search fallback.

繁中 AI / LLM 學習路徑 + 面試準備教材 + 2024-2025 研究前沿。

Open-source multi-tenant AI agent workspace · 18 personas · 408 tools · 227 tables · 134 active capabilities · 673 production indexes · self-hosted, BYO-keys

AI agent evolving strategies through automated self-play overnight. Generic framework with GEPA-inspired feedback loop and Elo tracking.

Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions.

An AI chatbot for the Matrix chat protocol which can assume any personality imaginable

A minimalist Chrome Extension starter built with React + Vite + TailwindCSS + Typescript+ OpenAI's GPT-3 model

Automatically convert functions to schemas for LLM function calling.

This is a Next.js based reimplementation of the Bolt OSS project by Stackblitz. It utilizes React, server-side rendering, and other modern web technologies to provide a fast, scalable, and maintainable platform. This version aims to bring the core functionality of Bolt to a new level of performance and user experience.

About Modular AI assistant — 60 built-in tools, multi-provider LLM support (Ollama, OpenAI, Anthropic, Gemini), hybrid memory, WhatsApp/Telegram daemon mode

IAttorney is an intelligent legal assistant built using Flask, LangChain, FAISS, OpenAI, and a RAG (Retrieval-Augmented Generation) pipeline.

Open-source Prompt Firewall — deflect up to 95% of redundant LLM traffic before it leaves your infrastructure. Documents: https://isartor-ai.github.io/Isartor/index.html

This repository hosts a tool that automates answering questions on Quora using OpenAI's GPT-3. It identifies unanswered questions in specified topics, formulates answers with GPT-3, and posts them on Quora.

An LLM app with Retrieval Augmented Generation (RAG) built using OpenAI GPT models, Langchain Tokenizers, HuggingFace transformers, and Meta BART summarization model wrapped in a NextJS web app hosted completely on AWS

A WebMCP-native browser agent that runs inside your real Chrome — control it from Claude, Cursor, and any MCP client

Blue is an open-source framework for building enterprise-ready agentic workflows through compound AI system architecture. Blue uses streams for orchestration, structured communication for control, and seamless integration with existing infrastructure.

A structured framework for defining, verifying and certifying AI systems.

🚀 A curated list of awesome Desktop Extensions (DXT) and MCP servers for Claude Desktop. Discover, share, and contribute to the growing ecosystem of AI-powered local tools and automations.

Museum-AI 是一个面向博物馆工作者和文物研究人员的智能知识管理与对话系统。项目基于多模态知识库架构（LangGraph + LangChain），通过向量检索、知识图谱和智能体技术，帮助用户高效管理文物知识、构建专业知识库，并进行智能问答。Museum-AI 支持 ChromaDB 向量库与 Neo4j 知识图谱双引擎、多格式文件索引（PDF/图片/文本/CSV/JSON）、图片嵌入检索、动态工具调用，提升了博物馆知识管理的效率。适用于文物研究、展览策划、知识库构建、智能导览等多种场景，是博物馆数字化建设的理想助手。

Open-source MCP server connecting Claude to Clio practice management. Built by Oktopeak.

Production-grade Node.js RAG system with hybrid retrieval, pluggable adapters, and OpenTelemetry tracing

🪝 透明可控的 AI Agent 终端 | 状态机 · 多层记忆系统 · 沙箱防御 · 完整审计 · 多人设多技能

A visual map for long AI conversations (ChatGPT / Claude / Gemini)

Enable interaction with distributed, decentralized LLMs on the Morpheus network through a desktop chat experience

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread.

Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-layer intercept.

一个本地ai聊天模型localaiAgentWithRAG，让你的本地数据不上传云端，可以自己加入所需要的记忆文件等等，修改角色形象，记忆对话，记忆库允许自己导入或者对话后自动记录

A Chrome extension that integrates OpenAI's GPT models with FreeScout to generate customer replies

Chat Buddy is an AI-powered WhatsApp assistant that runs entirely from your terminal. It acts as your personal proxy answering messages, scheduling calendar events, and managing chats with a personality you define.

Every system has its `telos´ — its final cause. This CLI fulfills the purpose of MindsDB's Knowledge Base: to seek, structure, and serve insight through intelligent agents.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

A macOS app for running parallel AI agents in sandboxed local VMs

Exploring Zep & Knowledge Graphs with Open-Source models as an alternative to OpenAI's Assistant Threads

Adapter / facade for language models (OpenAI, Anthropic, Cohere, local transformers, etc)

Chatnificent: LLM chat app framework – Minimally complete. Maximally hackable.

A LINE chatbot powered by OpenAI that helps users practice English through conversational AI

Write and deploy smart contracts using natural language prompts.

Ask Dr. Andrew Huberman questions and receive answers directly from his podcast episodes.

Unified .NET AI library with multi-provider support (OpenAI, Anthropic, Google, DeepSeek, Perplexity) and RAG extensions

A Python Library to perform Graph RAG in your Postgres DB without headaches

Allows to red-team your AI systems through adversarial probing. It is simple, effective, and requires minimal setup.

OpenClaw channel plugin for Rocket.Chat — DDP/REST, DMs, groups, threads, media, multi-account

A curated guide to the new generation of AI GTM tools

Spring AI framework for Java that plans, executes, and improves itself — agents detect capability gaps at runtime and generate validated skills on the fly.

Token-efficient browser-automation MCP server for AI agents. One Go binary (Go + chromedp), no Playwright/Node. Stealth + delta snapshots.

Type a thought at your zsh prompt, get an answer — and run the command it suggests

MCP server for browser automation via Patchright. Multi-profile Chromium, headed/headless, StreamableHTTP protocol. Includes dashboard, skills, and AI agent setup.

AI-powered English learning assistant for Chinese elderly users, with RAG, ReAct Agent, two-stage retrieval, and 5-dim evaluation framework

An open standard for discovering the legal context of agentic commerce transactions.

Measuring RAG solutions throughput and latency

A community-maintained collection of Pydantic AI examples.

Explore the evolution of AGI through historical context, reasoning models, and agent systems, while gaining hands-on experience with cutting-edge models like Claude 4, DeepSeek-R1, and OpenAI's o3. Learn to critically evaluate AGI benchmarks, understand their limitations, and identify where current models excel or struggle in reasoning tasks.

A cross-platform chatbot framework written in Rust, featuring a flexible dynamic plugin system.

MCP prompt tool applying Chain-of-Draft (CoD) reasoning - BYOLLM

GPT powered slack bot for summarizing/acting on messages and threads, written in Elixir

Type-aware, secret-safe clipboard history for Claude via MCP. Rust binary, macOS + Linux. Ships as .mcpb.

Unified harness for hot-swapping between OpenAI Agents SDK and Anthropic Claude Agent SDK with shared tool registry