Petit jeu de réflexion

Self-improving LLM agent in TypeScript using Reflexion (verbal RL): custom evaluators, reflexion memory, HTTP API, CLI. Built with Vercel AI SDK.

🧠 Community skill for Claude Code & Codex that helps your agent learn from its mistakes. /aprende reviews the conversation, surfaces durable learnings (memories, Reflexion-style anti-patterns, skill stubs, project-docs), and writes them only after you confirm. Bilingual (EN/ES). Made by tododeia.

Reflection/judge layer for OpenCode & Claude Code — catches premature stops, enforces workflow gates (tests, CI, PRs). 78% of agent stops are premature.

Petit jeu de réflexion... pour la Playdate

Code Base for Multi-Tool Usage for black box api access

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

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.

Autonomous scientific discovery engine - 82 discovery modules, 16-phase pipeline with refinement and reflexion. GFlowNet hypothesis tournaments, adversarial skeptic review, multi-agent debate, causal reasoning, knowledge graphs, 17 domain ontologies. Terminal-native.

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

This project aims at getting an analog signal from a water meter and use it for a house automatization system to control the water consumption.

Vision-grounded RAG agent for financial documents, built on a self-finetuned ColPali and 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.

🥈 2nd place (Agent-only) MLSys 2026 Track B — Multi-Agent LLM Pipeline for Memory-Constrained Tensor DAG Scheduling. Neurosymbolic split: LLM for combinatorial structure (op fusion), deterministic solver for constraints ([w,h,k], dependency, latency). 7.77× aggregate speedup, 88× best case.

Jeu liant les MATHS et PYTHON

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

A Java Swing app that eases the pain of creating XML objects and files by hand

Blokus est un jeu multijoueur en 2D dont le but est d'encadrer plus de point que ses adversaires.

Reflexion agent with LangGraph — GPT-4.1 Nano self-critiques answers, generates Tavily search queries, revises with citations through up to 4 iterative improvement loops

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