Outcome driven agent development framework that evolves
-
Updated
Mar 10, 2026 - Python
Outcome driven agent development framework that evolves
Infrastructure for building a supervised, self-improving agent organization. Run Claude Code from Feishu & Telegram with shared memory, agent factory, task scheduling, and an agent communication bus.
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
Detail-Oriented CLIP for Fine-Grained Tasks (ICLR SSI-FM 2025)
Cognitive Memory OS for AI Agents — persistent, self-improving, multi-agent memory
[NeurIPS 2020 Spotlight Oral] "Training Stronger Baselines for Learning to Optimize", Tianlong Chen*, Weiyi Zhang*, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang
Self-improving LLM system using Generator-Reflector-Curator pattern for online learning from execution feedback
DSPEx - Declarative Self-improving Elixir | A BEAM-Native AI Program Optimization Framework
Self-improving python code writer and error checker.
Open-source AI robotics framework — tiered brain, 8 AI providers, multi-robot swarm, self-improving loop
Declarative Self Improving Elixir - DSPy Orchestration in Elixir
AutodidactAI is an AI-driven platform that empowers continuous learning and self-improvement. Inspired by the concept of ikigai, AutodidactAI seeks to find purpose in knowledge acquisition and enhance its performance through iterative feedback and adaptation, embodying the principles of self-directed learning and continuous improvement
metaTextGrad: Automatically optimizing language model optimizers. Published in NeurIPS 2025.
Self-improving AI: Transform CLAUDE.md into a learning system. One prompt makes Claude learn from every mistake. Meta-rules + reflection = continuous improvement.
Self-improving AI deployment where the agent is compartmentalized from the infrastructure. Built on OpenClaw, Loa, and Cloudflare Workers.
Self-evolving AI assistant starter kit. Markdown-only. Works with Claude Code, Codex, Devin, Cursor, and any LLM agent
Fully automated YouTube Shorts pipeline with a self-improving feedback loop. Generates topics, scripts, AI images, TTS, renders video, uploads to YouTube, and learns from its own performance.
Self-improving AI cabinet that independently analyzes Montenegrin government decisions — all code, content, and analyses created by AI agents
🧬 Self-Improving Digital Organism - Autonomous GitHub framework with real-time task generation, self-healing capabilities, and adaptive evolution
Add a description, image, and links to the self-improving topic page so that developers can more easily learn about it.
To associate your repository with the self-improving topic, visit your repo's landing page and select "manage topics."