An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.
An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.
Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).
Methodology and deterministic evaluation tools for iterative improvement of skills, repositories and agent workflows, with independent review and regression checks.
数字员工操作系统 — AI agent 像真正员工一样工作。3D 虚拟办公室 + 经验固化为可执行程序（测试门禁晋升 · LLM 审阅迭代 · 相似任务免 LLM）+ 职业发展 + 记忆
Governed evolution layer for OpenClaw and Atlas Memory: runtime ingest, audit trails, reviewable proposals, rollback-safe promotion, and restart-safe handoff workflows.
企业 AI 的迷宫经验编译器 —— 把 Agent 的踩坑与人工纠正，编译成可治理、可继承的经验胶囊。
基於 FAEM 方法論的 AI Agent Skills，專注於 Agent 建構、評估與持續演進。(FAEM Skills — Agent Skills based on Felix Agent Evolution Methodology for building, evaluating, and evolving AI Agents.)
Research platform for AI agent integrity under adversarial pressure: append-only hash-chained belief store with content-addressed artifacts and replay / regression / falsification / invariants gates.
SoulAgent - Claude Code skill / plugin Powered by AISOP/AIAP — chat, Yijing divination, and create / evolve AIAP packages from your terminal.
Rollback-first reliability layer for AI agents: trace failures, apply guarded changes, and rollback on regression.
中文 agent 工具调用基准：A 办公数据 / B 知识检索 / C 多工具编排，三场景一套客观判分口径，clone 即跑。
continuous-learning-v2 - Claude Code Skill
To associate your repository with the agent-evolution topic, visit your repo's landing page and select "manage topics."