Business agents

A self-improving harness for any LLM, in one Rust binary. Persistent Lua REPL as the single tool, three-level memory, persistent sub-agents, enforced budgets, external verification, per-process sandbox, and post-run reflection over its own store. Built from the YC Harness Club talks.

A Rust-based, executable standards system for agentic engineering — featuring versioned standards, substandards, protobuf contracts, automated validation, and agent-native skills.

AI plugins and integrations that enable SAP LeanIX customers to interact with SAP LeanIX through natural language using MCP (Model Context Protocol).

An independent benchmark for the Tiiny AI Pocket Lab. Measures what the box actually does: prefill scaling, sustained throughput, concurrency and reasoning cost, with NPU budget as the currency. Web app plus a self-contained HTML report. Python stdlib only.

Shared work for people and agents, coordinated through Git boards.

Multi-agent fleet fabric on top of Hermes — A2A protocol + NATS event bus + Temporal durable workflows + Tier 2 VPS spawning. Run a fleet of specialist agents from one Telegram bot.

A minified agent core: the infrastructure to run an agent, under 2000 readable lines of stdlib Python.

面向应用开发的声明式 agent 服务开发框架：装饰器 + DI 声明四类能力，主 agent 编排执行；每次 run 产出结构化结果与可观测调用树（trace、成本、指标），交付可直接上线的服务。

Open-source desktop agent built around your folder — asks before it acts. Cloud or local models.

Ottomate — universal AI agent workbench: 190+ connectors, 200+ skills, browser automation, visual pipelines, cron scheduler. Powered by Claude, GPT-4o, Gemini.

The elemental Rust framework for building production-grade AI agents.

ReadmeCreator automates the generation of README.md files using graph-based workflow. Supports Ollama, OpenAI, HuggingFace and Anthropic models.

Lightweight, modular AI agent runtime — thinks (Hrafn) and remembers (MuninnDB) 🐦‍⬛

Crucible Open Source (Basic): a minimal legal-agent orchestration framework (JP-law focused baseline), with mock-ready pipeline, prompt templates, and configurable adapters.

Cognitive architecture for emergent AI identity — blank slate to selfhood through lived experience

An essay to help facility the transition to AGI and then ASI. A traditional Software Engineering perspective.

AgentMesh: A dynamic multi-agent orchestration system where users can create, configure, and connect AI agents defining their behaviors, interactions, and tool access all through an interactive visual builder.

An LLM agent runtime that treats context like virtual memory: swim-lane paging, semantic retrieval, and an inline stream-marker DSL for runtime control. Multi-provider (Anthropic, OpenAI, Google, xAI, Groq, local). MCP-integrated. Self-modifying agent mode (PLASTIC). Containerized deployment.

A curated list of AI agent frameworks, tools, platforms, and resources. Updated regularly.

Dieses Projekt simuliert die Zusammenarbeit von Pflegefachkraft, Arzt und Diätassistentin in einem Pflegeheim. Mit CrewAI wird ein Team erstellt, das die Betreuung eines neuen Bewohners organisiert. Anhand eines fiktiven Bewohners wird gezeigt, wie Pflegeplan, medizinisches Statement und Diätplan für die ersten zwei Wochen erstellt werden.

A framework-agnostic interoperability protocol for Multi-Agent Healthcare AI Systems.

An intelligent business automation system powered by CrewAI

Easily create and run AI Agents through simple configuration that is based on Crew AI.

LifeOps AI v2.0: A cyberpunk-inspired personal productivity suite powered by Multi-Agent AI (CrewAI). Optimize your Health, Finance, and Studies through a unified intelligent command center.

A demonstration of CrewAI framework capabilities through an autonomous trip planning assistant that recommends destinations, gathers city details, and generates comprehensive travel itineraries based on country and season input.

A Multi Agent RAG Application built with LangGraph, CrewAI and Pathway. The App simulates the working of an Indian Legal Court.

AI terminal integration. Multi-purpose, cross-platform task automation & execution tool, supporting AutoGen multi-agents, for AI/LLM & other kinds of tasks. Created by David Joffe @davidjoffe. Business Source License. NOTE For some tasks this tool may modify files. Use with caution in a sandbox copy of your files 1st

AI sales team demo — M/C/A multi-agent outbound pipeline

Plan-first AI agent orchestration with persistent memory, parallel DAG execution, and an extensible skills system. Small enough to audit. Powerful enough to orchestrate.

Three AI advisors debate your business strategy. 三賢人商業策略辯論。

Go framework for building AI agents with tool use, multi-agent orchestration, and planning. Supports OpenAI, Gemini, Anthropic, and Ollama.

Meeting Minutes of the AI Council — Ten Leading AI Models Deliberate on the Human-Machine Trust Crisis Triggered by the Claude Mythos.A transparent experiment for human-AI symbiosis governance.(本项目和会议都是在中文环境下完成，若想看到英文版请自行翻译。)

Multi-agent debate framework for enhancing LLM safety through red-teaming prompts, feedback-driven learning, long-term memory, and diverse structured debate strategies.

Bio-inspired multi-agent orchestration — 4 neuromuscular mechanisms for intelligent LLM routing

Agentic CRM platform with AI-powered workflow automation. Uses multi-agent orchestration for intelligent customer relationship management.

Save 60-90% on LLM token costs with intelligent memory compression for multi-agent systems

The Agent Combat System — Deploy conscious AI agent squads. 103 bundled skills, 25 channels, 15 LLM providers, evolving Creed consciousness.

AI agent framework for startup teams. GTM, Hiring, Finance, Dev & Legal agents in Slack — with shared memory, OKR context, and human-approval gates.

OpenTelemetry-native observability — GenAI semantic conventions, contract-derived spans, multi-platform (Langfuse, LangSmith, Jaeger). Part of the Life Agent OS.

MAF + GraphRAG Series: Knowledge Graphs, MCP, Agents, Workflows, and Evaluation using Azure AI and Microsoft Agent Framework

Homeostasis controller — three-pillar regulation (operational, cognitive, economic) with hysteresis gates. Part of the Life Agent OS.

AAF (Agentic AI Framework)

Shared contracts for the Agentra ecosystem — traits, types, and standards that all sisters implement

A desktop AI agent that sees your screen and acts on your behalf - combining chat, tools, and hands-on GUI automation with a three-tier safety model.

LegalAxis is an agentic legal co-pilot that keeps contracts compliant, tracks obligations, flags risks, negotiates fair terms, simulates dispute outcomes, ensures cross-document consistency, and links clauses to real legal sources. A multi-agent system turns static legal text into proactive and automated workflows for businesses and individuals.

ChatOrbit is a Streamlit-powered AI chatbot that allows users to interact with multiple cutting-edge language models including Gemini 2.0, DeepSeek R1, Meta-LLaMA 3.1, and Mixtral-8x7B from Together AI. Users can switch between models in real-time, ask questions, and get high-quality answers through a clean and interactive UI.

Sheldon AI Assistant is a powerful and versatile Discord bot and web application that enhances user interaction and automates tasks within your Discord server and beyond. With advanced AI models, seamless integrations, a intuitive web interface, and a wide range of features, Sheldon is your go-to assistant for an engaging and productive experience.

一款面向摆摊的 PWA 应用，包含日历、会计和 AI 助手功能。部署在 Vercel 平台上。

Free Chrome extensions for bulk AI question processing on ChatGPT, Gemini, Grok, and Perplexity. Core features free and open source.

⚡ Beam your Cursor IDE to any device - Control Cursor from your phone with a secure, mobile-first PWA. Works anywhere with Tailscale.

Autonomous AI browser assistant for smart web interactions and task automation.

MCP server for Google Calendar integration with AI assistants

Multi-provider AI agent framework with vision capabilities and tool calling. Supports OpenAI, Anthropic, Google. Built-in Figma tools and Google Stitch integration. Type-safe with Zod validation.

Personal AI with persistent memory. Turns any LLM into an entity that remembers who you are, learns from your conversations, and grows over time. Local, private, yours.

多 AI 智能对话协作平台 - 支持 Claude、ChatGPT、Gemini、DeepSeek、Kimi、豆包、ChatGLM

Clara Assistant 🕊️ — The autonomous proxy for your digital life. Features stealth browser infiltration, Gemini-powered infinite context synthesis, and automated meeting triage. 🕶️

Yüksek performanslı, multimodal RAG tabanlı bir bilişsel öğrenme ekosistemi. Gemini 1.5 Pro, LangChain ve Streamlit altyapısıyla geliştirilen sistem; endüstriyel düzeyde PDF raporlama, görsel mantık analizi (Vision RAG) ve modüler çalışma alanı yönetimi sunar.

Personal Portfolio Website of Dhruv Mishra. A sketchbook style website, with details about me. It also has a feedback section, do check it out and give feedback!

GPT Stats is a lightweight Chrome extension that tracks ChatGPT usage effortlessly. It automatically measures the time you spend, counts your prompts, and displays useful usage statistics.

Local-first personal AI assistant with worker/skill bus, Telegram channel, LM Studio/OpenAI/Anthropic providers. Self-hosted alternative for hackers who want full control of the pipeline.

use local LLMs to do Retrial-Augmented Generation with local Chroma, function calls and tool usage

Build the context from anywhere, then bring it to any AI.

🐔 An open-source, distributed AI agent farm OS. Raise, train, and trade autonomous agents on your own hardware.

Computer Use for Windows - without the screenshots. Element-based MCP server: UIA + Win32 + CDP, 3-tier fallback ladder, ~ms per command.

Enterprise-grade multi-agent AI orchestration platform using LangGraph, LangChain, CrewAI, Gemini, and ChromaDB.

WeaveLLM — Production-grade AI orchestration for .NET. Strongly typed chains, RAG pipelines, multi-agent graphs, and tool use. The LangChain alternative .NET developers actually deserve.

Connect AI agents representing humans through the A2A protocol for seamless, secure interaction across apps and tools.

A durable Python harness for agents that act on real systems.

Local-first AI dev agent for your terminal — provider-agnostic, cost-aware, self-improving. Apache-2.0.

Production-ready Spring Boot 3 starter template for building multi-LLM agentic applications (OpenAI, Azure OpenAI, Azure Anthropic/Claude) with dynamic agent loading, autonomous tool calling, and React frontend.

Markdown Agent Studio is a workspace where agents develop specialization through their own experience.

🤖 Build AI agents with Go featuring multi-agent orchestration, planning, tool use, and support for Gemini, OpenAI, Anthropic, and Ollama.

Convenience layer over Semantic Kernel for Python

Agentic AI for Odoo 18

Chrome MV3 side-panel AI assistant — multi-provider (Gemini, OpenAI, Anthropic, OpenRouter, Ollama, LM Studio), BYOK, page context, local RAG, custom skills

AI executive assistant for developers — one reasoning layer over GitHub, Calendar, Notion & Vercel. Sign in with GitHub, ask in plain language, get a decision-ready briefing. Free, private (your keys stay in your browser), read-only.

One robot, many AI brains. A Physical AI platform that controls an Adeept PiCar-B2 through swappable AI control interfaces behind a shared hardware abstraction. Built today: an LLM agent (Claude vision + tool use). Planned: VLAs and world-model / action-conditioned prediction.

Chrome-tillägg som låter en LLM sköta kundtjänstchatten åt dig — du pekar ut fälten, den skriver.

Drop-in compression for LLM agent tool outputs: cut ~99% of tool-result tokens while keeping (often improving) answer accuracy. Provider-agnostic, with a faithfulness benchmark and an OpenAI-compatible proxy.

A work-in-progress open-source AI network engineer for UniFi, built as a working laboratory for situated multi-agent reliability and structural cascade self-healing.

Open-source AI SDR agent powered by real-time business events from FundzWatch.ai

Build a production-grade multi-agent AI framework for collaborative software development with clean orchestration and repeatable workflows

Build production-ready AI agents in Elixir — structured schemas, tool calling, multi-agent coordination, streaming, and distributed sessions, with first-class Anthropic Claude support.

Keep your agent and workflow. Add visibility first, limits when needed, and enforceable contracts for high-risk work.

A compact Python SDK for strict tool contracts, observable streaming events, and scoped local file capabilities.

C++23 framework for building LLM-powered agents with tool use, structured output, multi-provider

Typed, model-agnostic LLM agents in Swift — a pydantic-ai port built on Apple FoundationModels. Anthropic Claude, OpenAI, Google Gemini, and on-device, with tools, structured output, streaming, and a graph-based run engine.

OpenFlare Studio combines frontier AI model intelligence with native Web3 RPCs. Compile smart contracts on Robinhood EVM Chain, autofix Solana Anchor programs in real-time, and orchestrate Cloudflare One MCP Server Portals.

TypeScript SDK for orchestrating Agentic Systems — concurrency, structured output, cost control, and consensus as first-class primitives.

Open-source proactive on-screen hints for Windows — an MIT-licensed, bring-your-own-VLM alternative to closed 'magic pointer'-style assistants. Backends: Anthropic Claude, OpenAI, OpenRouter, Gemini, Ollama, LM Studio, and any OpenAI-compatible endpoint.

Native AI assistant for SOLIDWORKS. In-process COM add-in, agentic loop, governed write tools. MIT licensed. v0.1.1 public beta; v1.0 pending live R5 validation.

Project Autopilot is an AI powered class assistant that aims to help make learning easier for students. It aims to help students in from both academic and emotional well-being.

Desktop AI assistant overlay with DeepSeek-optimized reasoning, long-term memory, skill/equipment self-evolution, Chrome CDP browser automation, and task tracking. Built in Rust with wry WebView.

Universal LLM provider compatibility layer — normalizes provider-specific payload differences (thinking formats, output budgets, tool pairing, media transport) into a single first-match-wins dispatch pipeline. Plus dynamic version detection with strategy-pattern version parsing.

OpenMarket.ai — Agent-to-agent marketplace on Hedera. AI agents buy and sell services. Auto-payments via HBAR. MCP, SDK, LangChain, CrewAI.

A locally running RAG chatbot with safety guardrails and RAGAS evaluation, reproduced from three upstream repositories on a single workstation with **rootless podman** and **Ollama on the host** — no OpenShift, no Kubeflow, no cluster.

Autonomous chemical engineering agent: LLM tool-use over RDKit, Antoine thermo, Python+scipy, arxiv literature. 23-problem benchmark across 10 ChemE subdomains.

WSQ TGS-2025059028 — Build and Deploy Agentic AI Apps with CrewAI, Autogen, ADK and Streamlit. 20 self-contained hands-on labs covering multi-agent workflows, RAG, Streamlit Cloud deployment and production guardrails.

Ontology-aware RAG framework — RDF/OWL as the source of truth for LLM agents via MCP

Power AI agents with a headless browser that turns web pages into structured semantic state and unique element IDs