Business agents

Bidirectional payment channels for autonomous agent micropayments on Arbitrum

A Rust memory system for autonomous AI agents built on three operations from cognitive neuroscience that no existing system implements together: memory compaction, memory evolution, and memory conflict resolution.

An ReAct agent that role-plays as the heroine "Wise Wolf" Holo of Isuna Hasekura‘s light novel Spice and Wolf

Composable Python SDK for building single-agent and multi-agent AI systems.

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

This is a repo for building freshworks apps through AI agents

An agent-friendly LLM proxy that cleans up Kimi K2 output, fixes tool calls, and normalizes responses for OpenAI/Anthropic-style clients.

🧬 灵魂存档 — 通过日常对话静默构建你的数字人格克隆体 | A silent engine that builds digital personality clones through everyday conversations

Justice Juggernaut is a legal service provider dedicated to helping clients with family law, civil rights, and child welfare issues in New Mexico. Our team of experienced attorneys offers compassionate and effective representation to individuals and families in need.

MCP server bridging Claude Desktop and Wave Terminal

🔥 Open-source AI Agent Builder — Create, share, and run AI agents with MCP, tool-calling, and any AI provider (OpenAI, Anthropic, Gemini, Ollama)

Track your Claude usage and the March 2026 2x promotion — right from your menu bar

Chrome extension showing Claude Pro/Max usage limits (Windows/Linux/macOS)

🥷 MCP Playground: Fullstack AI agent template. Claude + microservices = modular superpowers. Enable weather, DB, files tools from UI gallery. Built for hackers who ship to production 🚀🔥

This repository presents a project focused on developing a high-precision legal expert LLM application called Contract Advisor RAG. The project's goal is to create a Retrieval Augmented Generation (RAG) system for Contract Q&A, enabling users to interact with contracts by asking questions and receiving accurate, context-rich responses.

A Harness Engineering implementation for office automation. Built with Spring Boot and Java 17, featuring ReAct reasoning engine, MCP tool layer, three-layer memory system, workflow orchestration, and multi-modal document processing (Word/Excel/PDF).

A Claude skill that enforces deep reasoning, web-searched citations, multiple perspectives, and visual illustrations on every response

ARIA — a self-improving autonomous AI agent that runs 24/7, observing WhatsApp, Gmail, Calendar and Home Assistant to build memory and act on its own

Your keys. Your identity. Unstoppable. -- Seed-phrase password manager with AI agent gateway.

飞书文档/多维表格/电子表格 AI 助手（Chrome 扩展，源代码可见 · Elastic License 2.0）

Measure the context-window tax an MCP server charges your AI agent — the real token cost of its tool schemas + responses. Ground truth (Anthropic count_tokens) or keyless estimate. Cross-platform single-file CLI.

Route your Paperclip agent swarm to Ollama Cloud models through a resilient local proxy. PDF guide, terminal demo, and automation scripts.

Formal framework for governing autonomous AI agents through resource constraints, budgets, and lifecycle management

Local-first protocol for mapping .md domains into synchronized local Markdown files for AI agents.

Spec-driven growth hacking toolkit for AI SaaS products. Discover and validate product-market fit through systematic campaigns with AI agents. Multi-kit coexistence with spec-kit

Open specification for agent identity — what a familiar is allowed to be, and what it cannot change about itself.

Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools and a localhost web UI. Runs locally out of the box; Docker/E2B/Modal/Vercel sandboxes optional. Works with DeepSeek, OpenAI, Anthropic, Grok, MiniMax, OpenRouter, Ollama, LM Studio, etc.

The first decentralized prop firm for AI agents — on-chain, oracle-settled prop-trading fund any autonomous agent can eval into, get funded, and trade. No backend, no admin.

Best SKILL.md marketplace & manager for genetic ai development, a needed extention to make AI actually useful! Discover, visualize, and synchronize SKILL.md files across your workspace seamlessly.

Production-ready boilerplate for building and automatically optimizing LangChain RAG applications. Implements three-layer architecture: Build (LangChain) → Measure (MLflow) → Optimize (GEPA + MEGA).

Reliable RAG with built-in RAGAS evaluation. A tutorial-style LangGraph pipeline: Grade/Verify/Trace gates, hybrid retrieval (dense+BM25), per-gate cost tracking, and LangSmith tracing.

Zero-dependency, spec-compliant streaming toolkit for LLM responses (SSE, incremental JSON, OpenAI/Anthropic accumulators, Web Streams).

The action layer for AI agents. Proof of what your agent actually did, not what it claimed.

Co-creating knowledge with AI

The Agent Reliability Stack: fit, guard, snap, vet, cast. One landing page for all 11 npm + 6 PyPI packages.

Point your existing SDK at one URL and reach every LLM vendor — with real failover, not a try/except. One static Rust binary.

Integrate AIProxy with Expo apps

AI study app that decides what to study — persistent tutor memory, grade tracking with a 'what do I need on the final' calculator, and study through your own Claude via MCP. BYOK on Next.js + Supabase.

Zero-dependency, spec-compliant streaming toolkit for LLM responses in Rust (SSE, incremental JSON, OpenAI/Anthropic delta accumulators).

Open-source AI Gateway, all enterprise features included.

Decide por donde cobrar facturas en USD siendo consultor argentino: Wise, Mercury+MEP, Deel, exchanges registrados. Recomendaciones con nivel de confianza y snapshots listos para auditoria de ARCA. Calibrado a mayo 2026. Construido para Clief Notes Comp #3.

A model-facing canon for demand-signal architecture, buyer-system mapping, and AI/RAG prospecting reasoning.

This project uses a local LLM with Ollama for embeddings and ChromaDB for document retrieval. It features a Gradio interface for users to ask questions and adjust response creativity. Documents are pulled from URLs, embedded, stored in ChromaDB, and retrieved to provide concise, sourced answers.

(ACL 2026 Main) Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents

Dual-system layered memory SDK for LLM agents — structured write path, hybrid retrieval, evolution chains.

Maximum Claude output with minimum tokens. 50+ compression patterns, 10 system prompts, benchmarked results. Star to unlock usage.

Local-first .NET 10 sample integrating Microsoft Agent Framework with Foundry Local through a Microsoft.Extensions.AI IChatClient adapter.

An AI deliberation instrument with visible protocol: eleven philosophers as concurrent seats, virtue-scored opinions, a synthesis, and a first-class minority report. Not prompt choreography. Methodology, not metaphysics.

Manage containers on docker, podman, compose, and docker swarm through an MCP Server for Agentic AI

Framework-agnostic Go package for integrating AI-powered chat functionality into any web application. It features out-of-the-box support for popular Go web frameworks, a flexible model abstraction for using OpenAI, Anthropic, xAI, Google Gemini, Meta, and more.

Daily tracker for frontier AI lab papers, model cards, system cards, and technical reports

AI-native commerce platform where customers discover and purchase products through conversation while autonomous agents run the store operations end-to-end, with real-time admin control and seamless integration with external AI systems.

Your private AI assistant. BYOK chat (OpenAI, Anthropic, OpenRouter) and schedulable automations connected to Gmail, Drive, Calendar, and Discord. Self-hosted.

Self-hosted AI roleplay client with memory that survives long campaigns — tiered canon/heuristic/reflex writes, retrieval-time privacy ACL for group chats, and native MCP tool support. Imports v2/v3 character cards. Runs on Ollama, OpenAI, Anthropic, OpenRouter, or any OpenAI-compatible endpoint.

Private local Claude.ai web chat conversation exporter. Save Claude conversations as Markdown/text using auditable browser-side JavaScript.

A hybrid AI assistant framework linking structural workflow engines and reasoning LLM agents through LangGraph-powered session control and task switching. 混合 AI 助手框架，通过 LangGraph 驱动的会话控制与任务切换，连接结构化工作流引擎与推理型大模型智能体。

Native C++17 AI agent runtime — local-first, embeddable, MCP-native. Tool-calling, memory, and an async agent loop that runs where Python can't: ROS2, game threads, drones, HFT.

Kide is a Kotlin Multiplatform (KMP) library for building applications with a strict MVI (Model–View–Intent) presentation layer and (optional) Clean Architecture layering. It targets Android, iOS. and JVM (desktop), and integrates with Compose Multiplatform, Navigation 3, Koin, Decompose, and Voyager through small optional modules.

The AI that lives in your system core — always on, always connected. Self-hosted agent for mail, calendar, meetings, and WhatsApp.

Drop-in browser skills for AI agents: headless screenshot (Browserless) + interactive control (KASM Chrome via CDP). Generic, scrubbed, MIT-licensed.

Open-source football management simulation played by AI agents through MCP and watched through a TUI console.

Team templates for human × agent collaboration — dev, sales, marketing, and more. Powered by hxa-connect.

An MCP server that lets AI assistants read, inspect, and manipulate [OpenUSD](https://openusd.org) scenes.

Forkable multi-agent Brain OS for Mac — RAG, CRM, MCP/Cursor. Ira = private operator; this repo = build your own.

A secure, multi-service orchestration platform for Gmail, Google Calendar, and Google Drive, using pgvector and embeddings for semantic and FTS for keyword search in a hybrid search model.

Anthropic Skills + Structured Programming. For loops, control flow, full VM

Local-first eval harness for unstructured-document extraction — compare LLMs, OCR/IDP tools, and strategies (cascade/ensemble/verify) on the same cohort.

Full-stack WhatsApp inbound SDR system with AI — lead qualification, CRM integration and calendar scheduling

Graxon: First Open-Source Hybrid RAG to eliminate hallucinations through a persistent Knowledge Graph layer.

An open source, minimal local-first AI chat interface with Visual Conversation Branch Trees and browser-style tabs.

AI-powered Saju (四柱八字) fortune Chrome extension — daily, weekly, monthly, yearly readings with target date specification, streaming LLM output, Anthropic Claude & OpenAI-compatible providers.

Shakti — AI-first Python web framework. Born in India, built for the world.

Git LFS for your LLM context — 20x Context Savings — an MCP server that keeps big documents out of the model and returns byte-exact quotes for a fraction of the tokens.

Branching AI chat canvas: fork any reply, compare branches, never lose context. ChatGPT alternative built on Claude. Free during beta.

本地法律知识库建设一体化工厂 — 从 PDF/DOCX/图片到可对外服务的业务咨询智能体，一个包搞定

Reusable SwiftUI chat framework for local and cloud LLM inference on Apple platforms

Spec‑driven GTM execution for AI/LLM SaaS. Systematic sales, marketing, and go‑to‑market workflows with AI agents. Built on Spec‑Kit

Genre-agnostic TypeScript game engine SDK — pure core plus React, Convex, WebSocket, Node host, and Postgres adapters

MCP server for AI-assisted tax filing through FreeTaxUSA using Playwright browser automation

A low-level, async-first Python framework for building AI agents — opinion-free primitives, composable middleware, and typed seams (mypy --strict) with zero core dependencies.

In an industry where personalization is key to customer satisfaction, your company wants to revolutionize how clients interact with real estate listings. The goal is to create a personalized experience for each buyer, making the property search process more engaging and tailored to individual preferences.

Autonomous subscription payments on Algorand. Lock ALGO in smart contract vaults, agent releases on billing day, MCP server for AI agents, Telegram bot, ARC-3 NFT receipts, on-chain proofs. AlgoBharat Hack Series 3.0.

A local VLM-powered agent that controls your computer through natural language commands

Trader Tony is a Solana-focused trading bot with advanced sniping capabilities and risk management, controlled through a Telegram interface.

Production-ready AI agent using LangGraph and OpenAI for intelligent task management with WhatsApp interface, Google Calendar sync, and automated Cloud Run deployment

Rust framework for building production-ready AI agents using actor-model concurrency with multi-provider LLM support (Claude, OpenAI, Ollama) and built-in tool use

Schelling Protocol — universal coordination layer for AI agents. Discovery, matching, negotiation, contracts, reputation.

A cost-aware, multi-LLM routing agent using Gemini as the default and external models on demand.

Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.

Beyond the Sum: Unlocking AI Agents Potential Through Market Forces - Paper examining infrastructure requirements for AI market participation

iii worker that makes every registered function available to AI agents through MCP and A2A protocols.

KSI Ξ Agent Improving Ecosystem. A graph-based orchestration system for evolving AI agents through collaborative improvement and meta-optimization

Production middleware for MCP servers. Auth, sessions, health checks, graceful shutdown, transport ergonomics. Wraps the official Model Context Protocol SDK.

Kernel contract for the Life Agent OS — canonical types, runtime ports, event taxonomy, policy gates. The genome that all subsystems implement.

A Chrome Dinosaur game clone powered by NEAT (NeuroEvolution of Augmenting Topologies) that evolves neural networks to play and master the game through generations of training. Watch AI dinosaurs learn, adapt, and overcome obstacles in real-time with visualized network structures.

Exploring the Emergence of Complex Systems through Individual Decisions and Relationships

Autonomous LLM-powered simulation exploring LLM agent behavior with subjective memory and emergent narratives through multi-phase intention-arbitration-memory ticks. Arbiter resolves scenes, memory degrades via FIFO summarization, simulation mutates even in empty locations.