Business agents

Cumulative Agentic Skill Creation through Autonomous Development and Evolution

A chrome extension that completes coursera courses in one click. Now no need to waste your valuable time in watching those nonsense videos and attempting quiz

JusChat é um assistente jurídico inteligente baseado em tecnologia GraphRAG (Graph Retrieval Augmented Generation) que utiliza processamento de linguagem natural e grafos de conhecimento para consulta e análise de documentos jurídicos brasileiros.

Cursor AI Agent Team Framework: A three-agent collaboration system for AI-assisted work

Finch: self-improvement orchestrator — mines session history to detect corrections, breakthroughs, and behavioral patterns.

A Claude Skill that builds a sharp, ATS guaranteed product manager resume. It reads your old CV, asks the right questions, and ships it in one of 5 templates.

AgentMake AI: a kit for developing agentic AI applications that support 24 AI backends and and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong) Supported backends: anthropic, azure, azure_any, cohere, custom, deepseek, genai, github, github_any, googleai, groq, llamacpp, mistral, ollama, openai, vertexai, xai

Automate and streamline app development with an intelligent Python application that leverages OpenAI to generate plans, create project structures, manage tasks, and guide developers through the development process.

A Model Context Protocol server for Linear.

Common Chronicle turns messy context into structured, sourced timelines.

Claudia is an Emacs integration for the Claude AI assistant, providing an interface between Emacs and Anthropic's language models.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers

An agent built with OpenAI Agent SDK, Neo4j and Neo4j MCP server

Make stochastic AI systems durable with one decorator

Open-source workspace collaboration platform - chat, video calls, projects, files, calendar, notes, AI tools

Context compiler for TypeScript/JavaScript AI agents. Automatically compiles agent state into optimized LLM payloads with history compression, tool pruning, multi-provider support, and more.

Talk to your Follow Up Boss CRM in plain English. 160-tool MCP server for realtors, built by a working broker (Neuhaus Realty Group, Austin TX). Free self-host, ELv2 licensed.

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

A KDE Plasma plasmoid to add desktop chat with LLMs

An open-source browser extension—a gateway with two-sided reach into search, with locally managed credentials—for humans and local AI agents.

Open-source cost metering for n8n AI workflows — token usage per workflow, priced daily, on your own machine.

Custom Claude provider support for DeepSeek Harness

Drive the Chrome you are already logged into - from your terminal or any AI assistant. Cross-platform, MCP-ready.

基于 React、Vite 和 Three.js 的 3D 分镜导演台

A Claude skill that guides you through building your own AI command center for your business — own your systems, connect your tools, expose them over MCP, unify under one command layer.

an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch

explain your goals in normal human language and automatically have your calendar organized for the week

Local rag using ollama, langchain and chroma.

Automates steady and unsteady adjoints (general solvers and ODEs respectively). Forward and reverse mode algorithmic differentiation around implicit functions (not propagating AD through), as well as custom rules to allow for mixed-mode AD or calling external (non-AD compatible) functions within an AD chain.

⚡ Lightning-fast personal AI assistant with modular plugin architecture, Feishu integration, scheduled tasks & persistent memory

A software framework for building AI agents through composition.

A Model Context Protocol server for Jira.

AI HR Agent for HRMS

Demand-Driven Context — TDD for knowledge bases. A methodology for building enterprise AI agent knowledge bases through problem-driven curation.

Open-source browser agent Chrome extension — use any LLM (GPT-4o, Claude, Gemini, Grok, DeepSeek, Llama, and more) to control your browser

Conflux v2026 is a Rust-based AI development orchestrator for spec-first agent workflows, coordinating autonomous development through parallel Git worktrees with interactive TUI and headless operation.

Turn tab overload into a local-first workspace with intent-first AI organization and Agent collaboration through MCP.

Multi-pane ChatGPT workspace Chrome extension with side-by-side chats, lazy panes, prompt queue, goal agent, and Telegram bridge.

Local browser agent: MLX + Chrome DevTools Protocol. Handles cross-origin iframes, Shadow DOM, ProseMirror. Runs on Apple Silicon, no cloud.

Log workouts, runs, meals, and body weight through WhatsApp using Cloudflare Workers, D1, and GPT-5.6 Luna

A lightweight CLI tool for RAG over local documents

Messenger webhook implementation in java with jetty, contracts of facebook messenger webhook

Threema messaging from Go

Let LLMs manage your local dev environments

A python module library that simplifies RAG through abstraction

LLM powered AI multi agent platform that coordinate global to individual health through scaling each layer of healthcare

A Model Context Protocol server that provides task orchestration capabilities for AI assistants

Local-first control plane for running Claude agents in real Telegram and WhatsApp chats

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

ChatGPT and Google AI Studio

Runtime governance for AI agents. Contracts enforce what tools can do — before they execute.

An AI Agent with optional Human-in-the-Loop Safety, Model Context Protocol (MCP) integration, and beautiful, themeable CLI output

List of Law and Legal AI Agents Resources

Single-binary LLM agent runtime built on Elixir/OTP: chat UI, 4-tier memory, Anthropic-compatible Skills, scheduled tasks, multi-provider LLM routing, and platform bots.

🪢 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

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

Self-improving, harness-agnostic memory layer for AI agents, backed by Neo4j — lifecycle hooks capture every session, MCP tools recall project memory, and an LLM extraction loop distills durable learnings and evolves the agent's system prompt.

Contextual Retrieval solves this problem by prepending chunk-specific explanatory context to each chunk before embedding (“Contextual Embeddings”) and creating the BM25 index (“Contextual BM25”).

📘 Guided Engineering is a structured, traceable, and executable system for managing the entire software development lifecycle through modular prompts, intelligent agents, and reproducible documentation.

Magician-ContractsTools is a toolkit for calling smart contracts , you can very easily call smart contracts in Java programs for query and write operations

Bridge local MCP clients to browser WebMCP tools through Playwright, using native WebMCP when available and injected adapters when not.

Open-source multi-agent task board for OpenClaw. Kanban + DAG dependencies + MCP server + auto-retry + audit trail. Built for autonomous AI agent teams.

A prompt hub to help you get the most out of your favorite LLM by generating (or using ready-made) optimized prompts!

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.

KDNA Core — open .kdna judgment-asset file format, schemas, JS Core, and runtime loading contract.

DSH (DeepSeek Harness) plugin that launches and drives a running Godot 4.x game through its in-game TCP interaction server — replaces the godot-mcp MCP server with native agent tools.

This project is a simulation of the Magi System from the Neon Genesis Evangelion series. It uses the crewai package to create agents that represent the three supercomputers of the Magi System: Melchior, Balthasar, and Caspar.

AI-native, source-available (PolyForm Perimeter) game-dev toolkit: bforge — deterministic headless-Blender asset forge for AI agents (138 ops, quality-gated) — proof-carrying asset/entity/world compilers, deterministic Python/Rust/Wasm simulation, glTF into Babylon.js/three.js/Godot, Rust services. Godot 4.7.1 Forward+ on WebGPU, reproducibly.

let's you chat with website. crawls a website, embeds to vectors, stores to Chroma.

Scalable LLM cost enforcement middleware for Node.js with budget protection and multi-provider support

prr - command-line LLM prompt runner

try Computer Use on your Mac with a few clicks

META LLAMA3 GENAI Real World UseCases End To End Implementation Guide

Your Context-Aware AI Sales Assistant

Implement a single- angle solver, namely space-time A*, and parts of three MAPF solvers, namely prioritized planning, Conflict-Based Search (CBS), and CBS with disjoint splitting.

Comprehensive framework for integrating Anthropic Skills into Cursor IDE, ensuring AI agents consistently apply specialized knowledge and domain expertise when responding to user requests.

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Cursor10x is a comprehensive suite of tools that enhances the A.I. agent's capabilities within the Cursor IDE, providing persistent memory across sessions, standardized task management, and enforced best practices through cursor rules.

A single-file project management standard for agent-human collaboration. One markdown file captures everything about a project — from scoping through execution — so agents can pick up exactly where they left off.

Asynchronous LLM Agent playing games of Mafia against human players

[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

Open-source multi-tenant AI agent workspace · 18 personas · 141 active capabilities · 839 platform indexes · 78 curated AI models + 1000+ OpenRouter catalog · self-hosted, BYO-keys

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

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

An Emacs-native LLM agent harness featuring isolated sandboxing, asynchronous sub-agent orchestration, and fail-fast sync file merging.

Google Calendar MCP server: 15 tools for LLM agents. Install with uvx calendar-mcp-server.

Experiments with Langchain using different approaches on Google colab

Your life Copilot powered by LLM models (CLI interface for LLM models with MCP tools).

AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

IRB-AI is an experimental project that explores various ways to enhance users' IRB experience through AI (currently using ChatGPT).

get knowledge from your private documents

A unified interactive portal solution for multiple agents, enabling users to access multiple types of agent services through a single interface.

Adds extra features to Twitch

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

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

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

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

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