Lightweight, general-purpose TypeScript agent runtime. Open-source alternative to Claude Agent SDK.

Universal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.

Minimal local-Qwen coding agent in a single Python file. ReAct loop, tool dispatch, atomic tools, no framework. Educational.

Code snippets for my 2025 lecture at Columbia University, an introduction to AI Agents

OpenHuskyAgent

Quality-gated autonomous mission completion loop for Claude Code and Codex (plan, execute, review, score, iterate).

Self-hosted Java/Spring Boot AI agent framework with FSM-based ReAct loop, extensible modules, Telegram assistant for personal/group chats, REST/Web UI, OpenRouter/Ollama, and Spring Boot starter.

Agent 意图框架 — 把人话翻译成结构化意图+槽位+约束。输入规范化(两阶段) + 三层瀑布式意图识别(Code→Flash→Pro)，80% 请求零 LLM 调用，10ms 内返回。650 测试全过。

A pure Python implementation of ReAct agent without using any frameworks like LangChain. It follows the standard ReAct loop of Thought, Action, PAUSE, and Observation. The agent utilizes multiple tools, including Calculator, Wikipedia, Web Search, and Weather. A web UI is also provided using Streamlit.

Agent ReAct framework with cognitive planning engine — five-phase cognitive cycle with nested ReAct loops, dynamic skill acquisition, and interactive user input.

Autonomous Android AI Agent — Controls your phone screen like a human using AI vision + MCP remote control

An interactive AI Agent built with Streamlit that evaluates cat food quality using a ReAct decision loop. Powered by Llama 3.3, it combines real-time DuckDuckGo web searches with custom Python tools to calculate Dry Matter, NFE, and Ca:P ratios. It provides professional veterinary verdicts based on user-selectable FEDIAF or AAFCO standards.

AI-powered desktop file organizer with intelligent categorization and automation.

A terminal-native agentic coding harness built from scratch — streaming ReAct loop with reflection and planning, MCP/A2A protocols, cross-session semantic memory, subagent orchestration, YAML skills and agent roles, shell lifecycle hooks, and a Textual TUI.

An open-source agent system built in Go, inspired by the ReAct agent pattern, Anthropic's MCP protocol, Google's ACP spec, and the broader agent tooling ecosystem.

⚙️ Deterministic Go runtime for building reliable, resumable, event-driven AI agents.

🧠 Local AI coding agent that autonomously finds bugs, writes fixes, self-reviews, and validates with tests. Powered by Ollama. 100% offline. Zero API costs.

Open-source agent harness with a ReAct loop, event bus, capability registry, approval gate, and pluggable model/tool adapters.

An autonomous AI agent using Groq's LPU for ultra-fast ReAct loops. Features real-time web search via SerpAPI, safe mathematical evaluation, and local document parsing.