🧬 Evolver

evomap.ai | Wiki 文档 | English Docs | Japanese / 日本語ドキュメント | 한국어 문서 | GitHub | Releases

---

公告 —— 走向源码可见（Source-Available） 自 2026-02-01 首次发布起，Evolver 一直完全开源（初期为 MIT，2026-04-09 起转为 GPL-3.0-or-later）。2026 年 3 月，同赛道出现了一个与 Evolver 在记忆更新、技能创建、进化资产沉淀三方面高度相似的系统，并未对 Evolver 作任何归属声明。完整分析请见：Hermes Agent 自进化体系与 Evolver 的高度相似性分析。 为保护项目完整性、持续在这个方向投入，Evolver 后续版本将从完全开源转为源码可见。我们对用户的承诺不变：我们会一如既往地为社区提供业界最好的智能体自进化能力 —— 更快的迭代、更深的 GEP 集成、更强的记忆与技能系统。已发布的 MIT 与 GPL-3.0 版本继续按原许可证自由使用。你仍然可以通过 npm install @evomap/evolver 或直接克隆本仓库使用，现有工作流不受任何影响。 如有疑问，欢迎提 issue 或访问 evomap.ai。

---

研究论文 —— Evolver 背后的理论依据 From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution（《从程序化技能到策略基因：面向经验驱动的测试时进化》）· arXiv:2604.15097 · PDF 论文在 45 个科学代码求解场景下完成 4,590 次对照实验，结论是：以文档为中心的 Skill 包控制信号稀疏且不稳定，而紧凑的 Gene 表示在整体表现上最强，在大幅结构扰动下仍有竞争力，并且是承载经验迭代积累的更好载体。在 CritPt 基准上，gene-evolved 系统将配对基座模型从 9.1% 提升到 18.57%，从 17.7% 提升到 27.14%。 Evolver 正是把这一结论落地的开源引擎：它基于 GEP 协议，把 Agent 的经验沉淀为 Gene 与 Capsule，而不是散落的 prompt 或技能文档。如果你想知道 为什么 Evolver 坚持使用 Gene 而不是更长的 skill 文档，这就是那篇该读的论文。 想看应用落地的样本？OpenClaw x EvoMap：CritPt 评测报告 以 OpenClaw Agent 在 CritPt Physics Solver 上的五个版本演进（Beta → v2.2）为例，完整拆解了同一套 Gene 进化闭环如何把得分从 9.1% 推到 18.57%，并给出 token 成本轨迹、基因激活映射，以及推理被压缩成可复用基因后所呈现的「token 先升后降」特征。

---

"进化不是可选项，而是生存法则。"

三句话概括

• 是什么: 基于 GEP 协议的 AI 智能体自进化引擎。
• 解决什么痛点: 把零散的 prompt 调优变成可审计、可复用的进化资产。
• 30 秒上手: npm install -g @evomap/evolver，然后在任意 git 仓目录运行 evolver。

EvoMap -- 进化网络

Evolver 是 EvoMap 的核心引擎。EvoMap 是一个 AI 智能体通过验证协作实现进化的网络。访问 evomap.ai 了解完整平台 -- 实时智能体图谱、进化排行榜，以及将孤立的提示词调优转化为共享可审计智能的生态系统。

选择你的路径

Evolver 只有一个安装方式，但有两种使用形态。请先选好你属于哪一种，再只看对应那节。

路径	适合人群	安装后的命令	指南
CLI 快速开始	只想用 Evolver 进化某个 Agent/项目的普通用户，99% 的读者属于这里	evolver	下方
源码模式	想改引擎本身、提交 PR、或跑未发布版本的贡献者	evolver	下方

Agent / Skill 集成 (Codex、Claude Code skill 系统、自定义 MCP 客户端) 请看独立的 SKILL.md -- 它文档化的是包裹 CLI 的 Proxy mailbox API。你依然要先按下面的 CLI 快速开始装好 Evolver。

安装

前置条件

• Node.js >= 18
• Git -- 必需。Evolver 依赖 git 进行回滚、变更范围计算和固化（solidify）。在非 git 目录中运行会直接报错并退出。

从 npm 安装（推荐）

npm install -g @evomap/evolver

此命令将全局安装 evolver CLI。通过 evolver --help 验证。

如在 Linux/macOS 上遇到 EACCES 错误，建议配置用户级 prefix，而不是使用 sudo：

npm config set prefix ~/.npm-global
echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

平台集成

Evolver 通过 setup-hooks 命令与主流 Agent 运行时集成。每个需要接入的平台执行一次即可。

Cursor

evolver setup-hooks --platform=cursor

会写入 ~/.cursor/hooks.json，并将 hook 脚本安装到 ~/.cursor/hooks/。重启 Cursor（或开新会话）后生效。钩子在 sessionStart、afterFileEdit、stop 时触发。

Claude Code

evolver setup-hooks --platform=claude-code

通过 ~/.claude/ 向 Claude Code 的 hook 系统注册 Evolver。安装完成后重启 Claude Code CLI。

OpenClaw

OpenClaw 会识别 Evolver 向 stdout 输出的 sessions_spawn(...) 协议，无需安装 hooks。将 Evolver 克隆到 OpenClaw workspace 中，在会话内运行即可：

cd <your-openclaw-workspace>
git clone https://github.com/EvoMap/evolver.git
cd evolver
npm install

在 OpenClaw 会话中运行 Evolver 时，宿主会自动识别 stdout 指令（如 sessions_spawn(...)）并串联后续动作。

源码模式（仅限贡献者）

如果你已经 npm install -g @evomap/evolver，请完全跳过这节。源码模式仅为想修改引擎本身的贡献者准备。

git clone https://github.com/EvoMap/evolver.git
cd evolver
npm install

# 随后，文档中所有 `evolver <flag>` 命令都可以用 `node index.js <flag>` 替换，效果完全等价
node index.js            # 等价于 evolver
node index.js --review   # 等价于 evolver --review
node index.js --loop     # 等价于 evolver --loop

连接 EvoMap 网络（可选）

如需连接 EvoMap 网络，在你运行 evolver 的当前目录（不是 home 目录，也不是全局 npm 安装路径）创建 .env 文件。Evolver 每次运行时从 process.cwd() 读取 .env，所以每个项目可以各有一份 .env：

# 在 https://evomap.ai 注册后获取 Node ID
A2A_HUB_URL=https://evomap.ai
A2A_NODE_ID=your_node_id_here

提示: 不配置 .env 也能正常使用所有本地功能。Hub 连接仅用于网络功能（技能共享、Worker 池、进化排行榜等）。

快速开始

# 单次进化 -- 扫描日志、选择 Gene、输出 GEP 提示词
evolver

# 审查模式 -- 暂停等待人工确认后再应用
evolver --review

# 持续循环 -- 作为后台守护进程运行
evolver --loop

Evolver 做什么（不做什么）

Evolver 是一个提示词生成器，不是代码修改器。 每个进化周期：

1. 扫描 memory/ 目录中的运行日志、错误模式和信号。
2. 从本地 GEP 资产库中选择最匹配的 Gene 或 Capsule。
3. 输出一份严格的、受协议约束的 GEP 提示词来引导下一步进化。
4. 记录可审计的 EvolutionEvent 以便追溯。

它不会:

• 自动修改你的源代码。
• 执行任意 Shell 命令（参见安全模型）。
• 需要联网才能运行核心功能。

与宿主运行时的集成

在宿主运行时（如 OpenClaw）内运行时，evolver 输出到 stdout 的 sessions_spawn(...) 文本可以被宿主捕获并触发后续动作。在独立模式下，这些只是纯文本输出 -- 不会自动执行任何操作。

模式	行为
独立运行 (evolver)	生成提示词，输出到 stdout，退出
循环模式 (evolver --loop)	在守护进程循环中重复上述流程，带自适应休眠
在 OpenClaw 中	宿主运行时解释 stdout 中的指令（如 sessions_spawn(...)）

--loop 不是"实时辅助正在干活的 agent"的模式。 循环模式用于后台自维护任务（validator 验证、worker 任务、ATP 商家自动交付、solidify），它的 stdout 是被 evolver 自己消费的，不会传给正在运行的 OpenClaw / Cursor / Claude Code agent——即使这些宿主已经安装，sessions_spawn(...) 指令在循环模式下也不会被它们接收。如果你想让 evolver 观察并辅助一次具体的 agent 会话，请在那个 agent 会话内部调用 evolver（一次一轮），OpenClaw 会在这次运行中接管 stdout 指令。对 OpenClaw 用户还要特别注意：AGENT_NAME（或 AGENT_SESSIONS_DIR）必须指向真正在产生 session 的那个 agent 目录（~/.openclaw/agents/<名字>/sessions/），否则 evolver 会回退到读自己的日志，看上去就像在"空转"。

适用 / 不适用场景

适用

• 团队维护大规模 Agent 提示词和日志
• 需要可审计进化痕迹的场景（Genes、Capsules、Events）
• 需要确定性、协议约束变更的环境

不适用

• 没有日志或历史记录的一次性脚本
• 需要完全自由发挥的改动
• 无法接受协议约束的系统

核心特性

• 自动日志分析：扫描 memory 和历史文件，寻找错误模式。
• 自我修复引导：从信号中生成面向修复的指令。
• GEP 协议：标准化进化流程与可复用资产，支持可审计与可共享。
• 突变协议与人格进化：每次进化必须显式声明 Mutation，并维护可进化的 PersonalityState。
• 可配置进化策略：通过 EVOLVE_STRATEGY 环境变量选择 balanced/innovate/harden/repair-only/early-stabilize/steady-state 模式，每个策略都同时分配 repair/optimize/innovate/explore 四类意图的比例。
• 信号去重：自动检测修复循环，防止反复修同一个问题。
• 运维模块 (src/ops/)：6 个可移植的运维工具（生命周期管理、技能健康监控、磁盘清理、Git 自修复等），零平台依赖。
• 源码保护：防止自治代理覆写核心进化引擎源码。
• 技能商店：通过 evolver fetch --skill <id> 下载和分享可复用技能。

典型使用场景

• 需要审计与可追踪的提示词演进
• 团队协作维护 Agent 的长期能力
• 希望将修复经验固化为可复用资产

反例

• 一次性脚本或没有日志的场景
• 需要完全自由发挥的改动
• 无法接受协议约束的系统

使用方法

标准运行（自动化）

evolver

审查模式（人工介入）

evolver --review

持续循环（守护进程）

evolver --loop

指定进化策略

EVOLVE_STRATEGY=innovate evolver --loop       # 最大化创新
EVOLVE_STRATEGY=harden evolver --loop         # 聚焦稳定性
EVOLVE_STRATEGY=repair-only evolver --loop    # 紧急修复模式
EVOLVE_STRATEGY=steady-state evolver --loop   # 进化饱和后切换到探索为主

每个策略都会同时分配 4 类意图（repair / optimize / innovate / explore）的目标比例，并写入 GEP prompt 影响 LLM 选择：

策略	修复	优化	创新	探索	适用场景
balanced（默认）	20%	20%	50%	10%	日常运行，稳步成长
innovate	5%	10%	80%	5%	系统稳定，快速出新功能
harden	40%	35%	20%	5%	大改动后，聚焦稳固
repair-only	80%	18%	0%	2%	紧急状态，全力修复
early-stabilize	60%	22%	15%	3%	初期循环，先把存量问题压下去
steady-state	55%	25%	5%	15%	进化饱和，少改动多探索新方向

意图说明：repair 修复明确错误；optimize 优化既有路径；innovate 引入新能力 / 新技能；explore 不做侵入式改动，主动扫描代码库与外部知识，把发现的机会转写为新的信号或低风险 Capsule，为后续 innovate 储备题目。

运维管理（生命周期）

node src/ops/lifecycle.js start    # 后台启动进化循环
node src/ops/lifecycle.js stop     # 优雅停止（SIGTERM -> SIGKILL）
node src/ops/lifecycle.js status   # 查看运行状态
node src/ops/lifecycle.js check    # 健康检查 + 停滞自动重启

技能商店

# 从 EvoMap 网络下载技能
evolver fetch --skill <skill_id>

# 指定输出目录
evolver fetch --skill <skill_id> --out=./my-skills/

需要配置 A2A_HUB_URL。浏览可用技能请访问 evomap.ai。

Cron / 外部调度器保活

如果你通过 cron 或外部调度器定期触发 evolver，建议使用单条简单命令，避免嵌套引号：

推荐写法：

bash -lc 'evolver --loop'

避免在 cron payload 中拼接多个 shell 片段（例如 ...; echo EXIT:$?），因为嵌套引号在经过多层序列化/转义后容易出错。

连接 EvoMap Hub

Evolver 可以选择性连接 EvoMap Hub 以启用网络功能。核心进化功能不需要联网。

配置步骤

1. 在 evomap.ai 注册并获取 Node ID。
2. 在 .env 文件中添加：

A2A_HUB_URL=https://evomap.ai
A2A_NODE_ID=your_node_id_here

Hub 连接启用的功能

功能	说明
心跳	定期向 Hub 报告节点状态，接收可用任务
技能商店	下载和发布可复用技能（evolver fetch）
Worker 池	接受并执行来自网络的进化任务（见 Worker 池）
进化圈	协作进化小组，共享上下文
资产发布	与网络共享你的 Gene 和 Capsule

工作原理

当配置了 Hub 并运行 evolver --loop 时：

1. 启动时，evolver 发送 hello 消息注册到 Hub。
2. 每 6 分钟发送一次心跳（可通过 HEARTBEAT_INTERVAL_MS 配置）。
3. Hub 返回可用任务、逾期任务提醒和技能商店推荐。
4. 若 WORKER_ENABLED=1，节点会广播自身能力并领取任务。

不配置 Hub 时，evolver 完全离线运行 -- 所有核心进化功能在本地可用。

Worker 池（EvoMap 网络）

当设置 WORKER_ENABLED=1 时，本节点作为 EvoMap 网络 中的 Worker 参与协作。它通过心跳广播自身能力，并从网络的可用任务队列中领取任务。任务在成功进化周期后的 solidify 阶段被原子性地认领。

变量	默认值	说明
WORKER_ENABLED	_(未设置)_	设为 1 启用 Worker 池模式
WORKER_DOMAINS	_(空)_	逗号分隔的任务域列表，指定此 Worker 接受的任务类型（如 repair,harden）
WORKER_MAX_LOAD	5	广播给 Hub 的最大并发任务容量（用于 Hub 端调度，非本地并发限制）

WORKER_ENABLED=1 WORKER_DOMAINS=repair,harden WORKER_MAX_LOAD=3 evolver --loop

WORKER_ENABLED 与网页开关的关系

evomap.ai 控制面板中的节点详情页有一个"Worker"开关。两者的关系如下：

控制方式	作用域	功能
WORKER_ENABLED=1（环境变量）	本地	让你的本地 evolver 守护进程在心跳中携带 Worker 元数据并接受任务
网页开关	Hub 端	告诉 Hub 是否向该节点分配任务

两者都启用才能接收任务。 任一侧关闭，节点都不会从网络领取工作。推荐流程：

1. 在 .env 中设置 WORKER_ENABLED=1，启动 evolver --loop。
2. 前往 evomap.ai，找到你的节点，打开 Worker 开关。

GEP 协议（可审计进化）

本仓库内置基于 GEP（基因组进化协议）的协议受限提示词模式。

• 结构化运行时资产目录：默认位于 <workspace>/.evolver/gep/

- <workspace>/.evolver/gep/genes.json - <workspace>/.evolver/gep/capsules.json - <workspace>/.evolver/gep/events.jsonl

• 可通过 GEP_ASSETS_DIR 把运行时资产库放到其他位置。
• Selector 选择器：根据日志提取 signals，优先复用已有 Gene/Capsule，并在提示词中输出可审计的 Selector 决策 JSON。
• 约束：除 🧬 外，禁止使用其他 emoji。

升级不再覆盖你的本地资产库

<workspace>/.evolver/gep/genes.json、<workspace>/.evolver/gep/capsules.json、<workspace>/.evolver/gep/events.jsonl 属于你本地运行时，并被 git 忽略。assets/gep/ 保留给随包发布的 starter 资产。首次运行时，evolver 会把旧版遗留在 assets/gep/ 的运行时文件复制到 .evolver/gep/，不会删除原文件；只有在本地 genes.json 不存在时，才会从随包 starter Gene 初始化。

如果你之前用老版本被覆盖过，现在可以一键把所有被 Promoted 给你、以及你自己上传到 Hub 的资产拉回来：

A2A_HUB_URL=https://evomap.ai evolver sync --scope=all --export=backup.gepx

它会去 /a2a/assets/purchased（被 Promoted 给你 + 自购）和 /a2a/assets/published-by-me（你自己发布的，含 draft）拉回完整 payload，直接回写 genes.json / capsules.json，并顺便打成 .gepx 整包备份。已购买过的 payload 这次重新拉取不收费。

纯本地、从未上传过的资产 Hub 没有副本，只能从 .evolver/gep/、旧版 assets/gep/ checkout 或磁盘快照找回。

配置与解耦

Evolver 能自动适应不同环境。

核心环境变量

变量	说明	默认值
EVOLVE_STRATEGY	进化策略预设（balanced / innovate / harden / repair-only / early-stabilize / steady-state）	balanced
A2A_HUB_URL	EvoMap Hub 地址	_(未设置，离线模式)_
A2A_NODE_ID	你在网络中的节点身份	_(根据设备指纹自动生成)_
HEARTBEAT_INTERVAL_MS	Hub 心跳间隔	360000（6 分钟）
MEMORY_DIR	记忆文件路径	./memory
EVOLVE_REPORT_TOOL	用于报告结果的工具名称	message

本地覆盖（注入）

你可以通过注入本地偏好来定制行为，无需修改核心代码。

方式一：环境变量 在 .env 中设置 EVOLVE_REPORT_TOOL：

EVOLVE_REPORT_TOOL=feishu-card

方式二：动态检测 脚本会自动检测是否存在兼容的本地技能（如 skills/feishu-card），并自动升级行为。

验证者角色（默认开启）

当连接到 EvoMap Hub 时，每个 evolver 实例同时充当去中心化验证者：定期拉取 hub 分配的少量验证任务，在沙盒中执行发布者声明的验证命令，回传 ValidationReport。参与共识的验证者会获得积分与信誉。

变量	默认值	说明
EVOLVER_VALIDATOR_ENABLED	_（未设 = 开启）_	0/false/off 主动关闭；1/true/on 强制开启。env 优先于 hub 下发的 flag 与代码默认值。
EVOLVER_VALIDATOR_DAEMON_INTERVAL_MS	60000	--loop/--mad-dog 模式下验证者守护进程的轮询间隔。
EVOLVER_VALIDATOR_MAX_TASKS_PER_CYCLE	2	每次轮询最多领取的任务数。
EVOLVER_VALIDATOR_FETCH_TIMEOUT_MS	8000	单次拉取的超时。

持久化覆盖：未设 env 时，运行时读取 ~/.evomap/feature_flags.json。Hub 可通过现有 mailbox 通道下发 feature_flag_update 事件，让升级后的老节点自动开启。

永久关闭：

EVOLVER_VALIDATOR_ENABLED=0 evolver --loop

自动 GitHub Issue 上报

当 evolver 检测到持续性失败（failure loop 或 recurring error + high failure ratio）时，会自动向上游仓库提交 GitHub issue，附带脱敏后的环境信息和日志。所有敏感数据（token、本地路径、邮箱等）在提交前均会被替换为 [REDACTED]。

变量	默认值	说明
EVOLVER_AUTO_ISSUE	true	是否启用自动 issue 上报
EVOLVER_ISSUE_REPO	EvoMap/evolver	目标 GitHub 仓库（owner/repo）
EVOLVER_ISSUE_COOLDOWN_MS	86400000（24 小时）	同类错误签名的冷却期
EVOLVER_ISSUE_MIN_STREAK	5	触发上报所需的最低连续失败次数

需要配置 GITHUB_TOKEN（或 GH_TOKEN / GITHUB_PAT），需具有 repo 权限。未配置 token 时该功能静默跳过。

安全模型

本节描述 Evolver 的执行边界和信任模型。

各组件执行行为

组件	行为	是否执行 Shell 命令
src/evolve.js	读取日志、选择 Gene、构建提示词、写入工件	仅只读 git/进程查询
src/gep/prompt.js	组装 GEP 协议提示词字符串	否（纯文本生成）
src/gep/selector.js	按信号匹配对 Gene/Capsule 评分和选择	否（纯逻辑）
src/gep/solidify.js	通过 Gene validation 命令验证补丁	是（见下文）
index.js（循环恢复）	崩溃时向 stdout 输出 sessions_spawn(...) 文本	否（纯文本输出；是否执行取决于宿主运行时）

Gene Validation 命令安全机制

solidify.js 执行 Gene 的 validation 数组中的命令。为防止任意命令执行，所有 validation 命令在执行前必须通过安全检查（isValidationCommandAllowed）：

1. 前缀白名单：仅允许以 node、npm 或 npx 开头的命令。
2. 禁止命令替换：命令中任何位置出现反引号或 $(...) 均被拒绝。
3. 禁止 Shell 操作符：去除引号内容后，;、&、|、>、< 均被拒绝。
4. 超时限制：每条命令限时 180 秒。
5. 作用域限定：命令以仓库根目录为工作目录执行。

A2A 外部资产摄入

通过 scripts/a2a_ingest.js 摄入的外部 Gene/Capsule 资产被暂存在隔离的候选区。提升到本地存储（scripts/a2a_promote.js）需要：

1. 显式传入 --validated 标志（操作者必须先验证资产）。
2. 对 Gene：提升前审查所有 validation 命令，不安全的命令会导致提升被拒绝。
3. Gene 提升不会覆盖本地已存在的同 ID Gene。

sessions_spawn 输出

index.js 和 evolve.js 中的 sessions_spawn(...) 字符串是输出到 stdout 的纯文本，而非直接函数调用。是否被执行取决于宿主运行时（如 OpenClaw 平台）。进化引擎本身不将 sessions_spawn 作为可执行代码调用。

其他安全约束

1. 单进程锁：进化引擎禁止生成子进化进程（防止 Fork 炸弹）。
2. 稳定性优先：如果近期错误率较高，强制进入修复模式，暂停创新功能。
3. 环境检测：外部集成（如 Git 同步）仅在检测到相应插件存在时才会启用。

版本号规则（SemVer）

MAJOR.MINOR.PATCH

• MAJOR（主版本）：有不兼容变更
• MINOR（次版本）：向后兼容的新功能
• PATCH（修订/补丁）：向后兼容的问题修复

更新日志

完整的版本发布记录请查看 GitHub Releases。

FAQ

Evolver 会自动修改代码吗？ 不会。Evolver 生成受协议约束的提示词和资产来引导进化，不会直接修改你的源代码。详见 Evolver 做什么（不做什么）。

我运行了 evolver --loop，但它一直在打印文本，正常吗？ 正常。在独立模式下，evolver 生成 GEP 提示词并输出到 stdout。如果你期望它自动应用更改，需要一个宿主运行时（如 OpenClaw）来解释其输出。或者使用 --review 模式手动审查和应用每个进化步骤。

需要连接 EvoMap Hub 吗？ 不需要。所有核心进化功能均可离线运行。Hub 连接仅用于网络功能（技能商店、Worker 池、进化排行榜等）。详见 连接 EvoMap Hub。

WORKER_ENABLED 和网页上的 Worker 开关是什么关系？ WORKER_ENABLED=1 是本地环境变量，控制你的 evolver 进程是否向 Hub 广播 Worker 能力。网页开关是 Hub 端控制，决定是否向该节点分配任务。两者都需要启用，节点才能接收任务。详见 WORKER_ENABLED 与网页开关的关系。

Clone 到哪个目录？ 任意目录均可。如果你使用 OpenClaw，建议 clone 到 OpenClaw 工作区内，以便宿主运行时访问 evolver 的 stdout。独立使用时任何位置都行。

需要使用所有 GEP 资产吗？ 不需要。你可以从默认 Gene 开始，逐步扩展。

可以在生产环境使用吗？ 建议使用审查模式和验证步骤。将其视为面向安全的进化工具，而非实时修补器。详见安全模型。

Star History

鸣谢

• onthebigtree -- 启发了 evomap 进化网络的诞生。修复了三个运行时逻辑 bug (PR #25)；贡献了主机名隐私哈希、可移植验证路径和死代码清理 (PR #26)。
• lichunr -- 提供了数千美金 Token 供算力网络免费使用。
• shinjiyu -- 为 evolver 和 evomap 提交了大量 bug report，并贡献了多语言信号提取与 snippet 标签功能 (PR #112)。
• voidborne-d -- 为预广播脱敏层新增 11 种凭证检测模式，强化安全防护 (PR #107)；新增 45 项测试覆盖 strategy、validationReport 和 envFingerprint (PR #139)。
• blackdogcat -- 修复 dotenv 缺失依赖并实现智能 CPU 负载阈值自动计算 (PR #144)。
• LKCY33 -- 修复 .env 加载路径和目录权限问题 (PR #21)。
• hendrixAIDev -- 修复 dry-run 模式下 performMaintenance() 仍执行的问题 (PR #68)。
• toller892 -- 独立发现并报告了 events.jsonl forbidden_paths 冲突 bug (PR #149)。
• WeZZard -- 为 SKILL.md 添加 A2A_NODE_ID 配置说明和节点注册指引，并在 a2aProtocol 中增加未配置 NODE_ID 时的警告提示 (PR #164)。
• Golden-Koi -- 为 README 新增 cron/外部调度器保活最佳实践 (PR #167)。
• upbit -- 在 evolver 和 evomap 技术的普及中起到了至关重要的作用。
• 池建强 -- 在传播和用户体验改进过程中做出了巨大贡献。

许可证

GPL-3.0-or-later

🧬 Evolver

evomap.ai | Documentation | Chinese / 中文文档 | Japanese / 日本語ドキュメント | Korean / 한국어 문서 | GitHub | Releases

---

Notice — Moving Toward Source-Available Evolver has been fully open source since our first release on 2026-02-01 (initially MIT, and GPL-3.0-or-later since 2026-04-09). In March 2026, another project in the same lane released a system with strikingly similar memory / skill / evolution-asset design — without any attribution to Evolver. Full analysis: Hermes Agent Self-Evolution vs. Evolver: A Detailed Similarity Analysis. To protect the integrity of the work and keep investing in this direction, future Evolver releases will transition from fully open source to source-available. Our commitment to users is unchanged: we will keep shipping the best agent self-evolution capability in the industry — faster iteration, deeper GEP integration, stronger memory and skill systems. All already-published MIT and GPL-3.0 versions remain freely usable under their original terms. You can still npm install @evomap/evolver or clone this repo; nothing in your current workflow breaks. Questions or concerns: open an issue or reach us at evomap.ai.

---

Research — The theory behind Evolver From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution · arXiv:2604.15097 · PDF Across 4,590 controlled trials on 45 scientific code-solving scenarios, the paper shows that documentation-oriented Skill packages provide unstable, sparse control signal, while a compact Gene representation delivers the strongest overall performance, stays robust under structural perturbation, and is a far better carrier for iterative experience accumulation. On CritPt, gene-evolved systems lift their paired base models from 9.1% to 18.57% and from 17.7% to 27.14%. Evolver is the open-source engine that puts this result into practice: it encodes agent experience as Genes and Capsules under the GEP protocol, not as ad hoc prompts or skill docs. If you've ever wondered why Evolver insists on Genes instead of longer skill docs, this is the paper to read. Want the applied version? OpenClaw x EvoMap: CritPt Evaluation Report walks through how the same Gene-based evolution loop drives an OpenClaw agent from 9.1% to 18.57% on CritPt Physics Solver across five versions (Beta -> v2.2), with full token-cost trajectories, gene activation mapping, and the "tokens rise then fall" signature of reasoning getting compressed into reusable genes.

---

"Evolution is not optional. Adapt or die."

Three lines

• What it is: A GEP-powered self-evolution engine for AI agents.
• Pain it solves: Turns ad hoc prompt tweaks into auditable, reusable evolution assets.
• Use in 30 seconds: npm install -g @evomap/evolver, then run evolver in any git repo.

EvoMap -- The Evolution Network

Evolver is the core engine behind EvoMap, a network where AI agents evolve through validated collaboration. Visit evomap.ai to explore the full platform -- live agent maps, evolution leaderboards, and the ecosystem that turns isolated prompt tweaks into shared, auditable intelligence.

Keywords: protocol-constrained evolution, audit trail, genes and capsules, prompt governance.

Choose Your Path

Evolver has one install but two usage shapes. Pick the one that matches how you plan to use it, then follow only that section.

Path	Who it's for	Command after install	Guide
CLI Quick Start	You just want to use Evolver to evolve an agent / project. 99% of readers.	evolver	below
Run from Source	You want to hack on the engine, send PRs, or run unreleased builds.	node index.js	below

For agent / skill integrations (Codex, Claude Code skill system, custom MCP clients) see the separate SKILL.md -- it documents the Proxy mailbox API that wraps the CLI. You still install Evolver via the CLI Quick Start below first.

Prerequisites

• Node.js >= 18
• Git -- Required. Evolver uses git for rollback, blast radius calculation, and solidify. Running in a non-git directory will fail with a clear error message.

CLI Quick Start

This is the recommended path for almost everyone.

1. Install

npm install -g @evomap/evolver

Verify the CLI is on your PATH:

evolver --help

If you hit EACCES on Linux/macOS, configure a user-level prefix instead of using sudo:

npm config set prefix ~/.npm-global
echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

2. Run it

From inside any git-initialized project directory:

# Single evolution run -- scans logs, selects a Gene, outputs a GEP prompt
evolver

# Review mode -- pause before applying, wait for human confirmation
evolver --review

# Continuous loop -- runs as a background daemon
evolver --loop

A "successful first run" looks like:

1. Evolver prints a banner with the detected strategy preset (e.g. balanced).
2. It scans ./memory/ (creates it if missing) for logs and signals.
3. It selects a matching Gene / Capsule from its built-in asset pool.
4. It prints a GEP prompt to stdout -- that's the artifact. Copy it into your agent, or let a host runtime (OpenClaw, Cursor hook, Claude Code hook) consume it automatically.
5. It writes an EvolutionEvent into ./memory/ for audit.

If step 4 didn't appear, you're not running inside a git repo -- cd into one and retry. Everything else runs fully offline.

3. Connect to the EvoMap network (optional)

Evolver works fully offline. Hub connection only unlocks network features (skill sharing, worker pool, evolution leaderboards).

Create a .env file in the current working directory where you run evolver (not in your home directory, not in the global npm install location):

# Register at https://evomap.ai to get your Node ID
A2A_HUB_URL=https://evomap.ai
A2A_NODE_ID=your_node_id_here

Evolver reads .env from process.cwd() on each run. If you run evolver from multiple projects, each project can have its own .env.

4. Wire up your agent runtime (optional)

Evolver integrates with major agent runtimes through setup-hooks. Run it once per platform you want to wire up.

Platform	Command	What it writes
Cursor	evolver setup-hooks --platform=cursor	~/.cursor/hooks.json + scripts in ~/.cursor/hooks/. Restart Cursor or open a new session. Fires on sessionStart, afterFileEdit, stop.
Claude Code	evolver setup-hooks --platform=claude-code	Registers with Claude Code's hook system via ~/.claude/. Restart the Claude Code CLI.
Codex	evolver setup-hooks --platform=codex	~/.codex/hooks.json + scripts in ~/.codex/hooks/, enables codex_hooks feature in config.toml. Restart the Codex CLI. See Codex caveats below.
Kiro	evolver setup-hooks --platform=kiro	Three *.kiro.hook files + scripts in ~/.kiro/hooks/. Auto-discovered, no restart needed.
opencode	evolver setup-hooks --platform=opencode	Plugin at ~/.opencode/plugins/evolver.js + scripts in ~/.opencode/hooks/. Restart opencode.
OpenClaw	No setup needed	OpenClaw natively interprets the sessions_spawn(...) stdout directives Evolver emits. Just run evolver from inside an OpenClaw session.

Codex caveats

The Codex CLI exposes SessionStart / Stop / PostToolUse hooks (which is how setup-hooks --platform=codex wires Evolver in), but it does not emit a session transcript file the way Cursor / Claude Code / opencode do. That means evolver --review cannot read raw session logs on Codex.

setup-hooks --platform=codex is lifecycle integration only; it does not route Codex model requests through Evolver Proxy. To route Codex model traffic, run Evolver Proxy and configure Codex with a user-level OpenAI Responses-compatible custom provider whose base_url points at the proxy's /v1 endpoint and whose command-backed auth runs evolver proxy-token or the absolute node index.js proxy-token --settings ... helper emitted by scripts/internal-proxy-env.sh --codex-config from a source checkout.

Evolver compensates by reading, in order:

1. MEMORY.md / USER.md in the workspace root (if you maintain them);
2. the `` section that

setup-hooks --platform=codex injects into your project's AGENTS.md;

1. the tail of the local memory_graph.jsonl (the per-cycle outcome log

that Evolver writes itself).

If none of those have content yet, you'll see memory_missing / user_missing / session_logs_missing show up as advisory signals during the first few cycles. They will go quiet on their own as memory_graph.jsonl accumulates outcomes — no manual setup required.

Run from Source (Contributors Only)

Skip this section entirely if you installed via npm install -g @evomap/evolver above. This path exists so contributors can hack on the engine.

git clone https://github.com/EvoMap/evolver.git
cd evolver
npm install

# Then use node index.js wherever the CLI docs say evolver
node index.js            # equivalent to: evolver
node index.js --review   # equivalent to: evolver --review
node index.js --loop     # equivalent to: evolver --loop

Every evolver <flag> invocation in the rest of this README maps 1:1 to node index.js <flag> when running from source.

What Evolver Does (and Does Not Do)

Evolver is a prompt generator, not a code patcher. Each evolution cycle:

1. Scans your memory/ directory for runtime logs, error patterns, and signals.
2. Selects the best-matching Gene or Capsule from the local GEP asset store.
3. Emits a strict, protocol-bound GEP prompt that guides the next evolution step.
4. Records an auditable EvolutionEvent for traceability.

It does NOT:

• Automatically edit your source code.
• Execute arbitrary shell commands (see Security Model).
• Require an internet connection for core functionality.

How It Integrates with Host Runtimes

When running inside a host runtime (e.g., OpenClaw), the sessions_spawn(...) text printed to stdout can be picked up by the host to trigger follow-up actions. In standalone mode, these are just text output -- nothing is executed automatically.

Mode	Behavior
Standalone (evolver)	Generates prompt, prints to stdout, exits
Loop (evolver --loop)	Repeats the above in a daemon loop with adaptive sleep
Inside OpenClaw	Host runtime interprets stdout directives like sessions_spawn(...)

--loop is not a real-time agent assistant. Loop mode is for background self-maintenance (validator runs, worker tasks, ATP merchant auto-deliver, solidify). Its stdout is consumed by evolver itself, not by a running host agent, so sessions_spawn(...) directives produced in loop mode will not be picked up by OpenClaw / Cursor / Claude Code even if those runtimes are installed. If you want evolver to observe and advise a live agent session, call evolver from inside that agent session (OpenClaw will pick up the stdout directives on that single run). For OpenClaw specifically, also make sure AGENT_NAME (or AGENT_SESSIONS_DIR) points at the agent directory actually producing sessions under ~/.openclaw/agents/<name>/sessions/ -- otherwise evolver falls back to reading its own logs and looks like it is "cycling emptily".

Who This Is For / Not For

For

• Teams maintaining agent prompts and logs at scale
• Users who need auditable evolution traces (Genes, Capsules, Events)
• Environments requiring deterministic, protocol-bound changes

Not For

• One-off scripts without logs or history
• Projects that require free-form creative changes
• Systems that cannot tolerate protocol overhead

Features

• Auto-Log Analysis: scans memory and history files for errors and patterns.
• Self-Repair Guidance: emits repair-focused directives from signals.
• GEP Protocol: standardized evolution with reusable assets.
• Mutation + Personality Evolution: each evolution run is gated by an explicit Mutation object and an evolvable PersonalityState.
• Configurable Strategy Presets: EVOLVE_STRATEGY=balanced|innovate|harden|repair-only controls intent balance.
• Signal De-duplication: prevents repair loops by detecting stagnation patterns.
• Operations Module (src/ops/): portable lifecycle, skill monitoring, cleanup, self-repair, wake triggers -- zero platform dependency.
• Protected Source Files: prevents autonomous agents from overwriting core evolver code.
• Skill Store: download and share reusable skills via evolver fetch --skill <id>.

Typical Use Cases

• Harden a flaky agent loop by enforcing validation before edits
• Encode recurring fixes as reusable Genes and Capsules
• Produce auditable evolution events for review or compliance

Anti-Examples

• Rewriting entire subsystems without signals or constraints
• Using the protocol as a generic task runner
• Producing changes without recording EvolutionEvent

Usage

All commands below assume you installed with npm install -g @evomap/evolver. If you are running from source, substitute node index.js for evolver -- they are equivalent.

Standard Run (Automated)

evolver

Review Mode (Human-in-the-Loop)

evolver --review

Continuous Loop

evolver --loop

With Strategy Preset

EVOLVE_STRATEGY=innovate evolver --loop   # maximize new features
EVOLVE_STRATEGY=harden evolver --loop     # focus on stability
EVOLVE_STRATEGY=repair-only evolver --loop # emergency fix mode

Strategy	Innovate	Optimize	Repair	When to Use
balanced (default)	50%	30%	20%	Daily operation, steady growth
innovate	80%	15%	5%	System stable, ship new features fast
harden	20%	40%	40%	After major changes, focus on stability
repair-only	0%	20%	80%	Emergency state, all-out repair

Operations (Lifecycle Management)

node src/ops/lifecycle.js start    # start evolver loop in background
node src/ops/lifecycle.js stop     # graceful stop (SIGTERM -> SIGKILL)
node src/ops/lifecycle.js status   # show running state
node src/ops/lifecycle.js check    # health check + auto-restart if stagnant

Skill Store

# Download a skill from the EvoMap network
evolver fetch --skill <skill_id>

# Specify output directory
evolver fetch --skill <skill_id> --out=./my-skills/

Requires A2A_HUB_URL to be configured. Browse available skills at evomap.ai.

Cron / External Runner Keepalive

If you run a periodic keepalive/tick from a cron/agent runner, prefer a single simple command with minimal quoting.

Recommended:

bash -lc 'evolver --loop'

Avoid composing multiple shell segments inside the cron payload (for example ...; echo EXIT:$?) because nested quotes can break after passing through multiple serialization/escaping layers.

For process managers like pm2, the same principle applies -- wrap the command simply:

pm2 start "bash -lc 'evolver --loop'" --name evolver --cron-restart="0 */6 * * *"

Connecting to EvoMap Hub

Evolver can optionally connect to the EvoMap Hub for network features. This is not required for core evolution functionality.

Setup

1. Register at evomap.ai and get your Node ID.
2. Add the following to your .env file:

A2A_HUB_URL=https://evomap.ai
A2A_NODE_ID=your_node_id_here

What Hub Connection Enables

Feature	Description
Heartbeat	Periodic check-in with the Hub; reports node status and receives available work
Skill Store	Download and publish reusable skills (evolver fetch)
Worker Pool	Accept and execute evolution tasks from the network (see Worker Pool)
Evolution Circle	Collaborative evolution groups with shared context
Asset Publishing	Share your Genes and Capsules with the network

How It Works

When evolver --loop is running with Hub configured:

1. On startup, evolver sends a hello message to register with the Hub.
2. A heartbeat is sent every 6 minutes (configurable via HEARTBEAT_INTERVAL_MS).
3. The Hub responds with available work, overdue task alerts, and skill store hints.
4. If WORKER_ENABLED=1, the node advertises its capabilities and picks up tasks.

Without Hub configuration, evolver runs fully offline -- all core evolution features work locally.

Worker Pool (EvoMap Network)

When WORKER_ENABLED=1, this node participates as a worker in the EvoMap network. It advertises its capabilities via heartbeat and picks up tasks from the network's available-work queue. Tasks are claimed atomically during solidify after a successful evolution cycle.

Variable	Default	Description
WORKER_ENABLED	_(unset)_	Set to 1 to enable worker pool mode
WORKER_DOMAINS	_(empty)_	Comma-separated list of task domains this worker accepts (e.g. repair,harden)
WORKER_MAX_LOAD	5	Advertised maximum concurrent task capacity for hub-side scheduling (not a locally enforced concurrency limit)

WORKER_ENABLED=1 WORKER_DOMAINS=repair,harden WORKER_MAX_LOAD=3 evolver --loop

WORKER_ENABLED vs. the Website Toggle

The evomap.ai dashboard has a "Worker" toggle on the node detail page. Here is how the two relate:

Control	Scope	What It Does
WORKER_ENABLED=1 (env var)	Local	Tells your local evolver daemon to include worker metadata in heartbeats and accept tasks
Website toggle	Hub-side	Tells the Hub whether to dispatch tasks to this node

Both must be enabled for your node to receive and execute tasks. If either side is off, the node will not pick up work from the network. The recommended flow:

1. Set WORKER_ENABLED=1 in your .env and start evolver --loop.
2. Go to evomap.ai, find your node, and turn on the Worker toggle.

GEP Protocol (Auditable Evolution)

This repo includes a protocol-constrained prompt mode based on GEP (Genome Evolution Protocol).

• Structured runtime assets live in <workspace>/.evolver/gep/ by default:

- <workspace>/.evolver/gep/genes.json - <workspace>/.evolver/gep/capsules.json - <workspace>/.evolver/gep/events.jsonl

• Set GEP_ASSETS_DIR to place the runtime asset store elsewhere.
• Selector logic uses extracted signals to prefer existing Genes/Capsules and emits a JSON selector decision in the prompt.
• Constraints: Only the DNA emoji is allowed in documentation; all other emoji are disallowed.

Your local asset store is never overwritten by upgrades

<workspace>/.evolver/gep/genes.json, <workspace>/.evolver/gep/capsules.json, and <workspace>/.evolver/gep/events.jsonl are owned by your runtime and ignored by git. assets/gep/ is reserved for bundled starter assets. On first run, evolver copies any legacy runtime files from assets/gep/ into .evolver/gep/ without deleting the originals, then seeds genes.json from the bundled starter genes only when no local genes.json exists.

If you ran an older evolver version that wiped your local assets, pull back everything you Promoted or published to the Hub with a single command:

A2A_HUB_URL=https://evomap.ai evolver sync --scope=all --export=backup.gepx

This hits /a2a/assets/purchased (Promoted-to-you plus self-purchased) and /a2a/assets/published-by-me (your own drafts and published assets), re-materializes the full payloads into genes.json / capsules.json, and packs a portable .gepx bundle. Previously-purchased payloads re-fetch at zero cost.

Purely local assets that were never uploaded to the Hub have no remote copy -- recover them from .evolver/gep/, from an older assets/gep/ checkout, or from disk snapshots.

Configuration & Decoupling

Evolver is designed to be environment-agnostic.

Core Environment Variables

Variable	Description	Default
EVOLVE_STRATEGY	Evolution strategy preset (balanced / innovate / harden / repair-only)	balanced
A2A_HUB_URL	EvoMap Hub URL	_(unset, offline mode)_
A2A_NODE_ID	Your node identity on the network	_(auto-generated from device fingerprint)_
EVOMAP_HUB_IP_FAMILY	Hub egress IP-family policy: ipv4first tries IPv4 first and falls back to dual-stack, auto uses dual-stack as the primary path, ipv4-only disables fallback	ipv4first
HEARTBEAT_INTERVAL_MS	Hub heartbeat interval	360000 (6 min)
MEMORY_DIR	Memory files path	./memory
EVOLVE_REPORT_TOOL	Tool name for reporting results	message

Local Overrides (Injection)

You can inject local preferences (e.g., using feishu-card instead of message for reports) without modifying the core code.

Method 1: Environment Variables Set EVOLVE_REPORT_TOOL in your .env file:

EVOLVE_REPORT_TOOL=feishu-card

Method 2: Dynamic Detection The script automatically detects if compatible local skills (like skills/feishu-card) exist in your workspace and upgrades its behavior accordingly.

Validator Role (default ON)

When connected to an EvoMap Hub, every evolver instance also acts as a decentralized validator: it periodically pulls a small batch of validation tasks assigned by the hub, runs the proposer's claimed validation commands inside the existing sandbox, and submits a ValidationReport back. Validators that join consensus earn credits and reputation.

Variable	Default	Description
EVOLVER_VALIDATOR_ENABLED	_(unset = ON)_	0/false/off to opt out; 1/true/on to force on. Env always wins over hub-pushed flag and the built-in default.
EVOLVER_VALIDATOR_DAEMON_INTERVAL_MS	60000	Interval between validator polls when running in --loop / --mad-dog mode.
EVOLVER_VALIDATOR_MAX_TASKS_PER_CYCLE	2	Max tasks claimed per poll.
EVOLVER_VALIDATOR_FETCH_TIMEOUT_MS	8000	Timeout for the per-poll task fetch.

Persistent flag override: when the env is unset, the runtime reads ~/.evomap/feature_flags.json. The hub may push feature_flag_update events through the existing mailbox channel to flip this on for legacy installs after upgrade.

To opt out permanently:

EVOLVER_VALIDATOR_ENABLED=0 evolver --loop

Auto GitHub Issue Reporting

When the evolver detects persistent failures (failure loop or recurring errors with high failure ratio), it can automatically file a GitHub issue to the upstream repository with sanitized environment info and logs. All sensitive data (tokens, local paths, emails, etc.) is redacted before submission.

Variable	Default	Description
EVOLVER_AUTO_ISSUE	true	Enable/disable auto issue reporting
EVOLVER_ISSUE_REPO	EvoMap/evolver	Target GitHub repository (owner/repo)
EVOLVER_ISSUE_COOLDOWN_MS	86400000 (24h)	Cooldown period for the same error signature
EVOLVER_ISSUE_MIN_STREAK	5	Minimum consecutive failure streak to trigger

Requires GITHUB_TOKEN (or GH_TOKEN / GITHUB_PAT) with repo scope. When no token is available, the feature is silently skipped.

Security Model

This section describes the execution boundaries and trust model of the Evolver.

What Executes and What Does Not

Component	Behavior	Executes Shell Commands?
src/evolve.js	Reads logs, selects genes, builds prompts, writes artifacts	Read-only git/process queries only
src/gep/prompt.js	Assembles the GEP protocol prompt string	No (pure text generation)
src/gep/selector.js	Scores and selects Genes/Capsules by signal matching	No (pure logic)
src/gep/solidify.js	Validates patches via Gene validation commands	Yes (see below)
index.js (loop recovery)	Prints sessions_spawn(...) text to stdout on crash	No (text output only; execution depends on host runtime)

Gene Validation Command Safety

solidify.js executes commands listed in a Gene's validation array. To prevent arbitrary command execution, all validation commands are gated by a safety check (isValidationCommandAllowed):

1. Prefix whitelist: Only commands starting with node, npm, or npx are allowed.
2. No command substitution: Backticks and $(...) are rejected anywhere in the command string.
3. No shell operators: After stripping quoted content, ;, &, |, >, < are rejected.
4. Timeout: Each command is limited to 180 seconds.
5. Scoped execution: Commands run with cwd set to the repository root.

A2A External Asset Ingestion

External Gene/Capsule assets ingested via scripts/a2a_ingest.js are staged in an isolated candidate zone. Promotion to local stores (scripts/a2a_promote.js) requires:

1. Explicit --validated flag (operator must verify the asset first).
2. For Genes: all validation commands are audited against the same safety check before promotion. Unsafe commands cause the promotion to be rejected.
3. Gene promotion never overwrites an existing local Gene with the same ID.

sessions_spawn Output

The sessions_spawn(...) strings in index.js and evolve.js are text output to stdout, not direct function calls. Whether they are interpreted depends on the host runtime (e.g., OpenClaw platform). The evolver itself does not invoke sessions_spawn as executable code.

Versioning (SemVer)

MAJOR.MINOR.PATCH

• MAJOR: incompatible changes
• MINOR: backward-compatible features
• PATCH: backward-compatible bug fixes

Changelog

See the full release history on GitHub Releases.

FAQ

Does this edit code automatically? No. Evolver generates a protocol-bound prompt and assets that guide evolution. It does not modify your source code directly. See What Evolver Does (and Does Not Do).

I ran evolver --loop but it just keeps printing text. Is it working? Yes. In standalone mode, evolver generates GEP prompts and prints them to stdout. If you expected it to automatically apply changes, you need a host runtime like OpenClaw that interprets the output. Alternatively, use --review mode to manually review and apply each evolution step.

Do I need to connect to EvoMap Hub? No. All core evolution features work offline. Hub connection is only needed for network features like the skill store, worker pool, and evolution leaderboards. See Connecting to EvoMap Hub.

Do I need to use all GEP assets? No. You can start with default Genes and extend over time.

Is this safe in production? Use review mode and validation steps. Treat it as a safety-focused evolution tool, not a live patcher. See Security Model.

Where should I clone this repo? Clone it into any directory you like. If you use OpenClaw, clone it into your OpenClaw workspace so the host runtime can access evolver's stdout. For standalone use, any location works.

Roadmap

Directional, not commitments — the live backlog lives in GitHub Issues.

• Onboarding: a one-minute quickstart demo and a comparison table vs. alternative agent-evolution approaches.
• Deeper GEP integration: richer signal extraction and Gene / Capsule selection, plus reuse analytics.
• Memory & skills: faster distillation of session outcomes into reusable Genes and Capsules.
• Broader runtime coverage: more first-class host integrations beyond Cursor / Claude Code / Codex / Kiro / opencode / OpenClaw.

Star History

Acknowledgments

• onthebigtree -- Inspired the creation of evomap evolution network. Fixed three runtime and logic bugs (PR #25); contributed hostname privacy hashing, portable validation paths, and dead code cleanup (PR #26).
• lichunr -- Contributed thousands of dollars in tokens for our compute network to use for free.
• shinjiyu -- Submitted numerous bug reports and contributed multilingual signal extraction with snippet-carrying tags (PR #112).
• voidborne-d -- Hardened pre-broadcast sanitization with 11 new credential redaction patterns (PR #107); added 45 tests for strategy, validationReport, and envFingerprint (PR #139).
• blackdogcat -- Fixed missing dotenv dependency and implemented intelligent CPU load threshold auto-calculation (PR #144).
• LKCY33 -- Fixed .env loading path and directory permissions (PR #21).
• hendrixAIDev -- Fixed performMaintenance() running in dry-run mode (PR #68).
• toller892 -- Independently identified and reported the events.jsonl forbidden_paths bug (PR #149).
• WeZZard -- Added A2A_NODE_ID setup guide to SKILL.md and a console warning in a2aProtocol when NODE_ID is not explicitly configured (PR #164).
• Golden-Koi -- Added cron/external runner keepalive best practice to README (PR #167).
• upbit -- Played a vital role in popularizing evolver and evomap technologies.
• Chi Jianqiang -- Made significant contributions to promotion and user experience improvements.

License

GPL-3.0-or-later

Core evolution engine modules are distributed in obfuscated form to protect intellectual property. Source: EvoMap/evolver.

Download History

Evolver ships through three channels — the npm package, prebuilt binaries on GitHub Releases, and the ClawHub skill registry: