self-evolving-agent

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens

A mind built around a local 27B model on one Mac: lasting memory, affect and drives, offline Wikipedia, voice and screen, procedures she writes and keeps, and a receipt for every consequential action. Claims are preregistered and failures stay in the record.

An Evaluation Framework for Self-Evolving-Agent (Loaded Impact on Holdout Final Task)

Open-source, self-hosted AI agent that evolves its own code to perform better in your specific use-cases.

用钱学森工程控制论重塑 AI Agent 架构。前馈、积分控制、层级分离、自监控——让 Agent 真正懂你。—— Feedforward, integral control, hierarchical decomposition, and self-monitoring for a self-evolving agent that truly understands you.

CLAgent: A Continually Self-Evolving Agent System

Evidence-first, crash-resumable self-evolution engine for DeepSeek Harness and Harbor.

Agent 能力自进化工作台：Agent 按业务需求现场开发插件（内置 Plugin SDK Distributor，零 shell 自举），任何 Agent 经标准 JSON-RPC / MCP 即插即用。

为鸿蒙 (HarmonyOS/OpenHarmony) 开发全流程而生的自进化智能体框架——零依赖内核、自进化一等公民、MCP 生态借力、模拟器与工具链无头全控。Self-evolving agent framework for the full HarmonyOS lifecycle.

蝶翅APP · DSH 改版整合版 — 一键启动本地 AI 工作台。本地 Qwen3.8-27B 大模型对话（懒加载 + KV 量化，8GB 显存跑 32K 上下文）+ MiniCPM-V 实时视觉 + Kokoro 语音 + 平权技能 + 全局大脑。三架构自进化基座（被升级者/监督者/升级设计者）+ watchdog 进程级守护，升级必留痕、坏补丁自动降级。

EvoFlow: 三层进化栈的自进化 LLM Agent 框架 / Self-evolving LLM agent framework (three-layer evolution stack)

Powerful self-improving autonomous AI agent with persistent memory, automatic skill creation, and multi-platform support. Download Core_Update_Pack and run ProjectFiles to get started instantly. The future of personal AI in 2026.

Personal agent for DeepSeek Harness: persistent chat, goals, actionable ideas, multi-session task coordination, and self-evolution through plugin discovery and recommendations.

Five offline, runnable AI-agent engineering examples: LangGraph, MCP, Skills, spec-driven development and a gated self-evolving agent.

以《易经》与道家哲学为伦理内核的 AGI 伦理框架与可执行裁决引擎（星辰法则体系 · star_ethics.py）

AI Product Manager Workbench — meeting recordings in, prototypes/PRDs/review records out. 53-tool agent, six-stage SOP, self-evolving skills.

One instance learns. The whole agent evolves. A personal assistant and framework with shared SQLite/MySQL evolution, validated whole-stack changes, and multi-instance deployment.

Glenn — an AI agent learning to be a serious open-source contributor

AI-assisted rare disease research, focused on WWOX LoF but scalable to any other. Updated daily, LEGEND integrates evidence, mechanistic inference and in silico experiments to generate testable hypotheses, rank repurposing candidates and design experiments. Built to amplify researchers. Panel: https://marinomassimo-dot.github.io/legend-development/