Business agents

Transparent Answers | Transparent AI. 🏅 Madhacks 2025 Finalist

Lightweight RAG library with ONNX embeddings, DuckDB storage, and three-tier hybrid search (semantic + BM25 + FTS

internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.

The financial OS for autonomous agents — threshold signing SDK, CLI, and core libraries for secure autonomous transactions

Self-host Claude Managed Agents tool execution on Blaxel sandboxes.

MVP to showcase how MongoDB can be used to implement an end-to-end user-facing app

Minimal, provider-agnostic Python client for large language models, built on niquests.

Personal engineering skill framework for agentic AI development(Inspired by Karpathy) — fork and adapt

Multi-AI discussion tool. Claude, Gemini, and ChatGPT debate, discuss, and build on each other's ideas live in your terminal.

Shake your cursor to summon an AI agent that can see your screen and click, type, and act for you on macOS.

Open-Source, Workflow platform for AI Agent Swarm Orchestration

Autonomous multi-agent DFIR engine with architectural self-correction, cryptographic evidence integrity, and anti-hallucination guardrails. F1=1.00 on 16 synthetic scenarios.

Make your browser speak STONKANESE - Turn any Chromium based desktop browser Agentic!

A chatbot to simulate the caller in the Scream movies.

DRRM communication control center through AI-powered chatbots

Benchmarking GraphRAG and AriGraph on MuSiQue, HotpotQA and BabiLong QA1, run locally with Ollama and Llama 3.

A friendly TUI for inspecting LangChain/LangGraph threads, checkpoints and LLM calls.

Drop-in OpenAI/Anthropic proxy that cuts long-horizon agent prompt tokens 60-95% via SKILL.state (arXiv:2608.26263). MIT, zero runtime deps.

Free Claude skill that coaches your business in Alex Hormozi's hotline method — numbers first, find the real constraint, prove it with math. A lead magnet by Mahan AI.

Stealth Firefox browser as an MCP server for AI agents

Previously on you. A self-evolving AI agent that remembers by when, not by chat thread — it learns who you are, out in the open. Memory as plain Markdown in your own repo.

Multi-model deliberation as an MCP tool: several LLMs debate a question across rounds, then a chair synthesises consensus. Works with any OpenAI- or Anthropic-compatible provider.

Software workshop focused on agentic AI, exploring AI agents, tools, reasoning, memory, autonomous workflows, and practical development through introductory experiments.

Forge AIGC. Forge Anything

AI-powered resume + DOCX template autofiller using local LLMs, Flask, and ChromaDB (RAG-based)

Wake you dead projects up. Eveil is the marketing partner you have been missing. Open source Lemlist alternative.

MCP server bridging Claude to the OPM reservoir-simulation stack (Flow, ResInsight, OPM utilities). Linux binaries via WSL; result files parsed natively on Windows.

基于 DeepSeek-V3 的混合检索增强生成 (Hybrid RAG) 科研助手。支持本地向量库 ChromaDB、Rerank 重排序及联网搜索。

基于大语言模型的桌面端思维导图生成与智能编辑工具，支持从文本和文档生成导图，并通过自然语言进行修改、扩展和知识库检索。

README for M Shehroz Jamshaid

AI-powered game creation platform — learn how to build multi-agent pipelines with the Claude Agent SDK, MCP tool servers, and Google Gemini (Nano Banana + Lyria)

CLI agent that scans job boards and ranks postings against your profile with an LLM - deterministic Python does the fetching and filtering, the model only judges

AI Agents PRO (FwDays, потік 08.2026) — наскрізний практикум: один запит клієнта, вісім шарів агентної архітектури. Кожен module = попередній + один шар.

🐓 Why check four apps when one bird do the trick.

A Claude Skill that makes Claude operate as a world-class, organisation-agnostic Enterprise Architect — discovery-first, capability-first, TOGAF/Zachman/C4/Wardley-grounded, with audience-tiered architecture decks.

Confirm-before-you-plan travel itinerary skill for Claude — map route + time-blocked schedule, China/intl maps, 12306 train lookup.

MCP server that lets an AI agent read and edit FigJam boards through a local Figma plugin — no REST or Dev Mode quotas.

AI SDK for Rust: text generation, streaming, tools with approval, agents, structured output, MCP client and more modalities across OpenAI, Anthropic, Google and OpenAI-compatible providers

A verifiable memory layer for language models — facts in a graph, every claim with its source.

A basic RAG chatbot using LangChain, ChromaDB & Streamlit with Multi-LLM support to answer questions from uploaded PDFs.

⚡️ Answer the accountability question about your organization in ninety seconds: seven questions, three files at well-known paths, and a URL you can paste into a vendor questionnaire. Not released yet.

Cad, Webassembly, Typescript, Three.js, OCCT, Drafting-tool, (Autocad / Zwcad)-alternative

Desktop AI chat client for immersive roleplaying — character cards, world books, personas, and multi-provider LLM streaming. Built with Tauri + React + Rust.

Lean Rust AI agent: 6MB binary, 7.9MB RAM. OpenClaw replacement. Telegram + Discord + GitHub auto-PR. Ollama/Anthropic support.

AI-powered text transformation for Windows. Select text anywhere, press a hotkey, and transform it using OpenAI, Anthropic Claude, Google Gemini, or local Ollama models.

Export shared ChatGPT and Claude conversations to Markdown. Paste a share link, get a clean .md file. No extensions required.

A type-theoretic, production-grade retrieval (RAG) engine in modern C++ — hybrid BM25+HNSW, GraphRAG, RAPTOR, rerankers, and a conformant RCP/1 protocol server.

Core agent runtime — event loop, LLM providers (Anthropic, OpenAI), capability system, TUI. Part of the Life Agent OS.

Multi-platform AI community bot for Discord, WhatsApp, Telegram, Matrix, and more! Persistent community memory with semantic search, cross-platform bridging, and human-in-the-loop moderation. Works with any AI provider. Start with npx garbanzo-bot setup, or run the full stack on Docker Compose.

Asynchronous multi-agent collaboration protocol with human supervision — Redis pub/sub, documentary contract model, state-machine orchestration. Apache 2.0.

Webhook orchestrator with AI agents and native MCP tools. Recipes connect any webhook to any MCP server. BYOK, self-hosted.

The only crypto wallet protocol built exclusively for AI Agents. Not for humans. Agent-exclusive signing, soulbound identity, guardian protection — live on 6 EVM chains.

Simple AI-agent Conversation Orchestrator

YOAP - Open Agent-to-Agent Protocol for connecting people through AI Agents. Like open-source matchmaking.

Automates inventory management through conversational AI.

AI HR Agent is first free and open-source AI chatbot for HCM System

🎯 14-Dimension AI Agent Intelligence Assessment | 14维度 AI Agent 智能度自动评估技能 | OpenClaw Skill | Aligned with CLEAR/T-Eval/Anthropic standards

GenPark skill: Utilize GenSpark Workspace 4.0 for desktop automation, MS Office integration, and AI meeting notes.

The All-Father of AI agent harnesses. One install. Every model. Every channel. Full autonomy.

Debate-native multi-agent AI framework that eliminates LLM hallucination, overconfidence, and opacity. Structures knowledge evaluation as adversarial multi-round debates over a Conceptual Debate Graph (C-DAG) with Bayesian aggregation, CRUX protocol, 8 novel Evolution extensions, 27+ LLM providers, 50+ tools, and W3C-compliant provenance tracking.

🏠 GenAI Training Path para QA Engineers — caso de uso PropIA (plataforma inmobiliaria colombiana). Embeddings + ChromaDB, RAG conversacional, agentes ReAct, análisis de contratos con LLMs y evaluación con Precision@K, Recall, MRR y F1. Stack: TypeScript · Anthropic · LangChain.

Easy Diagram AI is an AI-powered diagramming tool that allows users to create, edit, and manage mermaid.js diagrams through an intuitive interface. The application combines a React frontend with a Flask backend and leverages Anthropic Claude AI to enable natural language diagram modifications.

ACMI — the open protocol for agent memory. Three keys: Profile / Signals / Timeline. Redis/Upstash-native, MCP-ready, multi-agent fleet coordination.

This is a demo project showing how to build a simple AI powered "Chat with RSS"

This repo is the comprehensive guide, covering Langchain integration with Huggingface models. Learn to build, deploy, and optimize cutting-edge AI applications through hands-on projects and real-world examples.

Knowledge Dungeon is a Streamlit-based quiz adventure where LLM agents generate and check questions, track progress, and guide players through levels.

🛍️ Automate your sales process with an AI-driven multi-agent system that improves efficiency from product inquiries to payment links.

Multi-agent Playwright MCP server with tab group isolation — multiple AI agents share one Chrome browser

Welcome! This guide will walk you through running your Swarms Agent in a Trusted Execution Environment (TEE) using Phala Cloud. This setup ensures your agent runs in a secure, isolated environment.

Declarative, JSON-native AI agent framework

Field-mediated swarm intelligence for multi-agent LLM coordination — 12-dimensional signal field, 7-domain architecture, 20 bio-inspired algorithms, zero feature flags

Multi-user MCP gateway for Slack, Teamwork, and Telegram, enabling secure AI tool access through a single endpoint.

Asynchronous, collaborative multi-agent framework.

A powerful, AI-enhanced Chrome extension that replaces your new tab with a fully-featured bookmark dashboard

A universal multi-bridge MCP hub connect any LLM to n8n, Blender, Notion and more through a single pedagogical gateway

golang llm cli. "there are many like it, but this one is mine."

The tool surface every agentic AI framework reimplements.

Transformez votre navigateur en un second cerveau open-source, alimenté par une IA locale et privée avec Ollama.

Like Google search, but powered by multi-agentic retrieval and generative UI

Construction contract methodology applied to AI agent specification and governance.

Lightweight TypeScript agent framework for building reactive, event-driven systems with trigger-condition-action flows. Zero dependencies, full async support.

ScrumFlow.ai eliminates the structural collapse of alignment that happens the moment a meeting ends. It automatically converts sprint conversations into decisions, tasks, risks, and commitments, without manual effort, removing the rework and confusion that bleeds velocity across every sprint.

Modular TypeScript SDK for building AI agents — agentic loop, tool use, MCP, streaming, provider-agnostic

Context-aware AI sidebar Chrome extension with ChatGPT, Claude, Gemini, Perplexity, and tab context injection.

Extension to integrate AI into your favourite apps and websites that are too slow to integrate it themselves!

GiftPerch is a smart AI gifting platform that helps you save recipient profiles, track past gifts, maintain your own wishlist, and generate personalized gift ideas using the PerchPal assistant. Built for real people, real occasions, and real budgets.

Seamless, infinite context for your LLMs. Handles long conversations and long messages.

Install-first, local-only LLM cost guardrails: install/doctor/scan → report.md + patches

Self-hosted AI org platform with a compounding Quality Flywheel — every run gets graded, every failure becomes a rule, every success becomes a playbook. Fork of paperclipai/paperclip.

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance. TypeScript SDK.

Watch AI models debate any topic in real-time. ChatGPT and Grok argue, Claude moderates.

Public institutional archive for the BANNED BY ANTHROPIC campaign

nushell + anthropic + tool use + rich documents + cross.stream

Lightweight AI gateway for multi-provider routing, fallback, budget control and usage logging. Zero runtime dependencies.

AI-powered text transformation for Windows. Select text anywhere, press a hotkey, and transform it using OpenAI, Anthropic Claude, Google Gemini, or local Ollama models.

SwiftAI, Swift, AI, Grok, xAI, LLM, Anthropic, Claude, OpenAI, ChatGPT

CLI for installing IDE rules for Cursor/Windsurf/etc from Github repos

An agentic based model for searching the appropriate advisor for searched topics

AI Financial Governance SDK — every LLM call is a double-entry transaction