🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

It shows case studies of the LangGraph agent.

It shows how to deploy and use an agent with LLM.

It shows a problem solver based on agentic workflow.

It shows an intelligent agent based on LangGraph for long form writing.

It is a chatbot based on LangChain.

It is a case study of an intelligent agent for Ocean.

Extending the capabilities of LLMs using Planning agents and using "knowledge providers"

A minimal, fully commented Python executive AI agent. For students, teachers and junior devs who want to understand agentic AI from the ground up.

Minimal, hackable AI agent built on the ReAct reasoning loop. No frameworks — just a transparent Thought → Action → Observation cycle you can read and extend in an afternoon.

A minimal, fully commented Python executive AI agent. For students, teachers and junior devs who want to understand agentic AI from the ground up.

A minimal, fully commented Python executive AI agent. For students, teachers and junior devs who want to understand agentic AI from the ground up.

Autonomous coding loop for OpenAI Codex and Google Gemini CLIs. Drop planning docs into a folder, set an iteration count, and loop-agent generates a backlog and runs plan → implement → review cycles to write your code. Independent-process reviews, atomic backlog updates, auto git rollback on failure, and safe rate-limit handling.

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.

从零构建 AI Research Agent：5 阶段渐进式学习，掌握 Agent Loop、Tool Use、Memory、Plan-and-Execute、生产增强。Python + GLM-4.7 + SQLite

Portfolio writeup of the deep-agent layer I shipped for the AMIQ platform (sobhanb-eth/ads-marketing-iq): ReAct + Plan-and-Execute, Strategy Agent with confidence-gated HITL, and the pending-actions API. 3,693 lines of agent code, all upstream.

A modular, general-purpose agent built with LangGraph, MCP, and LangSmith - demonstrated via GitHub code analysis.

Local-first multi-agent AI system built on LangGraph + Ollama. Router -> Plan -> Execute -> Verify pipeline with reflection loops, human-in-the-loop interrupts, and a live-streaming Flask UI. No API keys, no cloud — runs entirely on your machine.

Plan execution layer for AI coding assistants. One command — isolate, classify, execute, verify, merge. Works with Claude Code, Cursor, Windsurf, Aider, and any LLM.

Plan-and-Execute multi-agent orchestrator with bounded adaptive replanning. ~800 LoC TypeScript kernel. Real Anthropic web_search demo. No framework lock-in.