Provide persistent, outcome-weighted memory for AI trading agents to improve decision-making across sessions with the TradeMemory Protocol.

Claude Code 하네스 엔지니어링 — Reflexion 자기개선 루프, 백프레셔 원칙, 다중 경로 탐색, 5개 서브에이전트 오케스트레이션

Self-correction engine for AI coding agents - implements the Reflexion paper (Shinn et al., 2023) as a Rust MCP server. Turns failures into persistent, searchable lessons that prevent the same mistakes across sessions.

Skill-composition investment intelligence — 9 composable MCP skills, compliance-as-infrastructure (HKMA/SFC/PDPO), Reflexion, PRM, real-time pipeline visualization

🔁 REFLEX — Reflexive Self-Improvement for AI Agents. Log failures → analyze → propose → apply. Part of the GENESIS AGI stack.

Multi-agent orchestration with self-evolution, cognitive memory, and governance.

Collection de pensées ou courtes réflexions sur divers sujets, de prose romantique, d'humour, d'analyse introspective.

🚨 AI-powered emergency response simulation combining Mesa ABM with advanced LLM reasoning strategies (ReAct, Reflexion, Plan-Execute) for optimized crisis management and multi-agent coordination

Implementation of the Reflexion agent pattern (Self-Correction) using Spring Boot 4 and Spring AI 2.0 in Java 21. Includes Actor-Reviewer flow and web search with Tavily. Demonstrates 'Code as Orchestration' strategies to build resilient agents without the complexity of graph DSLs like LangGraph.

AI coding assistant skill for automated multi-file development. PIR methodology: Plan-Iterate-Resolve with filesystem memory, self-reflection, and advisory state machine. Supports Claude Code & Cursor.

An autonomous coding agent with persistent trauma memory. Implements "Loop 10" to save execution failures to a "Scar File," ensuring the agent never makes the same syntax or library error twice in a session.

Exploring Multi Agent Architecture.

매일 쌓이는 메일을 빠르게 파악하고, 중요한 정보를 놓치지 않도록 돕는 LLM Agent 기반 Chrome Extension 서비스입니다.

A self-reflective LLM agent with tools, memory, and reasoning built using LangChain + ReAct + Reflexion. Modular FastAPI backend + Streamlit UI.

Interactive Streamlit application that benchmarks direct prompting, chain-of-thought, self-consistency, tree-of-thought and reflexion techniques across OpenAI GPT-3.5 and Groq Gemma-9B-IT.

Reflexive Simulation Framework for Purple Team Cognitive Architecture and Escalating Learning Behavior

Petit jeu de réflexion

Customer Driven Project (TDT4290) The project is a collaboration between NTNU and KartAI. Showcasing use of AI for streamlining building case process

Jeu liant les MATHS et PYTHON

[WIP] Reflexion Agent: A Go implementation of an advanced AI-powered tool-calling agent using Temporal workflows and instructor-ai. Demonstrates self-reflection and iterative improvement in AI responses.