#agent

a fast, rootless sandbox and virtual resource runtime. Run any workload in a real container, including an agent's tool-call or LLM-generated code.

Gives agents a think→act loop — plus recursive decomposition (RLM): break a hard task down, fan out, verify, synthesize. Goal in, coordinated actions out. Replaces LangChain, CrewAI, AutoGen. Zero required deps.

The AI-native application framework for Python — reactive UIs, APIs, agents, workers, realtime, MCP, and durable execution in one runtime.

.NET pipeline framework for enterprise AI applications — multi-provider LLM integration, RAG pipelines, and multi-agent orchestration with a fluent builder API.

Control your Pi coding agent from your phone. Pair with a one-time QR code and chat with your local agent, even when you're away from your computer.

No repository description published.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

A lightweight PHP utility to detect if your code is running inside an AI agent or automated development environment.

A JavaScript library to control agents enclosed in CLI commands like Anthropic Claude Code CLI

The .NET library to build AI agents with 30+ built-in connectors.

Self-hosted Bun/TypeScript agent runtime with composable tools, memory, skills, transports, and policy.

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

🕵️💬 stream-first Agent Runtime.

A MapLibre GL plugin for GeoAgent

Financial reconciliation for humans and AI agents like Claude, Codex, and others. Open source and deterministic.

Python CLI framework for tools AI agents can call safely: one-call manifest, JSON envelope on every exit, typed exit codes. Implements the CLI Agent Spec

PHP library for building chats with agents.

Git-native AI agent co-harness — MCP server, static guards, and agentic evaluator for LLM-assisted coding

TypeScript and Python toolkits and project scaffolding for building Unified Namespace applications.

browser-use for TypeScript: AI-Powered Browser Automation from Python's Acclaimed Library

Excelize is a C# port of Go Excelize library that allow you to write to and read from XLAM / XLSM / XLSX / XLTM / XLTX files.

📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent workflows (ReAct/Plan-Act/RePlan), long-term memory, and traceable evidence. Built with LangChain + LangGraph + Streamlit.

Build Your Agent Company with OMC

Accessibility testing tools monorepo — core, CLI, MCP, Playwright, Storybook, Vitest

Flocks is an agentic SecOps platform.

AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Open protocol for scoring AI investments. JSON Schema, scoring engine, MCP server. Spec under CC-BY-4.0.

Coordination layer for AI coding agents

Installs, reselects, restores and removes a complete Cursor CLI harness configuration, and owns the program lifecycle.