augmented LLM with self reflection

🪞 An AI existential-psychology counselor asks you 3 meaningful questions every night for 21 days — and remembers, reflecting your own words back to you. Bilingual zh/en. A Hermes Agent skill. 每晚三个问题，一面慢慢显影的镜子。

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.

Personal Analytics project to increase knowledge workers' awareness about work and productivity.

An offline CLI for turning life goals into quests

A Claude skill blending psychology, philosophy, and wisdom traditions into a conversation partner with actual depth. Free, open-source, not a therapist.

WaqtX is a modern web app that transforms your life timeline into meaningful insights by combining personal time data, Islamic history, and daily reflection tools. It goes beyond simple age calculation by visualizing your journey, highlighting spiritual milestones, and encouraging mindful use of time through habit tracking and actionable insights.

[ICLR 2026]🌴 ARES is an open-source framework for adaptive multimodal reasoning, featuring a two-stage pipeline—Adaptive Cold-Start and Entropy-Shaped Policy Optimization—to balance reasoning depth and efficiency.

Monte Carlo Tree Search Self-Refine (MCTSr)

Decision Maker: A Calm Self-Reflection Tool

Code and data realeases for the paper -- TasTe: Teaching Large Language Models to Translate through Self-Reflection

[VLDB'25] Official repo for Paper "Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data Transformation"

An AI skill that interrogates you — with your consent — until the story you tell yourself gives way to what's actually true. Claude Code plugin / Agent Skill.

A sacred space for heartfelt conversations, where wisdom flows freely and memories gently fade like whispers at sunset.

Keyless heuristic self-inspection tool: an agent describes a thought or task and always gets back one metathought. Deterministic routing over an open CSV (no LLM). REST + MCP.

荣格.skill — 用阴影、投射、人格面具与个体化梳理更诚实的自我地图。Carl Jung.skill — Surface shadow, projection, persona, and individuation patterns for more honest self-exploration.

Self-Reflective Question Answering for Biomedical Reasoning. GRPO fine-tuning via QLoRA & Unsloth with rewards for correctness, relevance, groundness, utility & XML structure. Structured think → answer → self-reflection with context grading, relevance assessment & groundness evaluation. DeepEval LLM-as-a-Judge (GEval, Faithfulness, Relevancy).

The course equips developers with techniques to enhance the reliability of LLMs, focusing on evaluation, prompt engineering, and fine-tuning. Learn to systematically improve model accuracy through hands-on projects, including building a text-to-SQL agent and applying advanced fine-tuning methods.

Claude prompts that earn the right to advise you. Build → Validate → Reuse: rigorous, tested on yourself, then reused as an ongoing counselor. Starts with a full Vedic chart + Ayurvedic reading. MIT. Bilingual PT/EN.

一个支持自修改的 C++规则执行器虚拟机，支持动态修改指令和规则间调用