Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. LongMemEval R@5=97.45%. Self-hosted, Ollama-optional

An autonomous content marketing team. Talk to your agents on Telegram. Always on. Auto-improving.

A self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.

An OpenClaw skill that upgrades self-improving agents from reactive error logging to goal-driven capability evolution with curriculum, evaluation, transfer, and promotion.

The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"

A self-improving AI agent that learns from experience. Runs entirely on a local 9B model. Security by absence — dangerous capabilities were never built.

A knowledge cycle for AI agents — one that grows with the people who shape it. Six-phase self-improvement loop, ADRs, JSON schemas, and a dependency-free Python reference.

A self-improving Agent that utilizes AI to generate, validate, and execute MATLAB simulations.

Personal operations system. Claude Code skills, hooks, and markdown files replace project management software. Standup plans your day, hooks track your work, retrospectives learn your patterns.

Adversarial agent swarm orchestrator — AI agents compete, evolve, and improve across providers

Analyze and classify agent skills for safety using structured local risk evaluation.

Self-improving AI voice agent that simulates sales calls, analyzes outcomes, and iteratively optimizes its script using LLM reasoning + workflow orchestration (n8n)

Controlled self-improvement system for AI agents with verification, rollback, and gated promotion.

Transform AI-generated text into natural human output with measurable evaluation and optional verification.

Verify structured agent outputs with deterministic results and signed receipts.

Experimental autonomous game studio by PlayDrop

An AI agent that automatically improves its own prompt based on output quality scores — runs a task, evaluates the result, rewrites the prompt, and tries again until it hits the target score.