self-improving-agent 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
Echo Agent 是一个可自托管、长期运行、持续学习的 AI Agent，面向个人与团队的私有自动化场景。它可以部署在自有服务器上，统一连接模型、工具、记忆、权限与消息入口。内置四层认知记忆、遗忘曲线与矛盾检测机制，能够在跨会话任务中持续沉淀上下文，并保持长期记忆的质量。针对命令执行、文件操作等高风险行为，它提供基于 LLM 的审批与解释机制，为关键操作建立可审计、可追溯的安全边界。原生支持 MCP、A2A、多模型路由、任务调度、工具调用和多通道接入，覆盖 CLI、Gateway API、微信、Telegram 等入口。它让 Agent 带着长期记忆和可进化技能，持续、安全地为你工作。
让你的经纪人自我提升。Reflexio 是一款人工智能代理自我提升工具，使您的人工智能代理能够持续从真实用户互动中学习。
An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU kernel through a structured, profile-driven workflow.
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
Claude Code 和 Codex CLI 的持久内存。自动提取知识图谱、多表示嵌入、3D WebGL可视化。LongMemEval R@5=97.45%。自托管，Ollama可选
Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_session_end hook.
Official implementation of Continual Harness (arxiv.org/abs/2605.09998) on ARC-AGI-3
Open-source, self-hosted AI agent that evolves its own code to perform better in your specific use-cases.
Browser-native agent · profiles · tools — by aratech | Zero installs, isolated, secured and self-evolving agent.
[COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"
Self-improving agent harness for ChatGPT and Codex on Mac. #1 on AssistantBench. On-disk memory, privacy zones, verified completion.
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.
Open-source search engine that automatically evolves your AI agent's prompts, tools, and harness logic through iterative evaluation — plug in Claude Code, Codex, Hermes, or any CLI agent.
Learn to build recursive self improvement agents
An OpenClaw skill that upgrades self-improving agents from reactive error logging to goal-driven capability evolution with curriculum, evaluation, transfer, and promotion.
AI Security Research Radar — AI for security and security for AI
AI Research Radar — Evidence-Grounded Trend Ledger for AI Systems
A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.
A self-improving Agent that utilizes AI to generate, validate, and execute MATLAB simulations.