经 AI Skill Hub 精选评估,AI工作流 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g ax # 方式二:npx 直接运行(无需安装) npx ax --help # 方式三:项目依赖安装 npm install ax # 方式四:从源码运行 git clone https://github.com/Necmttn/ax cd ax npm install npm start
# 命令行使用
ax --help
# 基本用法
ax [options] <input>
# Node.js 代码中使用
const ax = require('ax');
const result = await ax.run(options);
console.log(result);
# ax 配置说明 # 查看配置选项 ax --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export AX_CONFIG="/path/to/config.yml"
###### the retro loop for AI coding agents
Make your agent learn. Reflects. Experiments. Improves. Across every session.
---
Every sub-agent you spawn finishes its work and disappears. Whatever it figured out - which command failed three times before the right one, which file actually mattered, which approach to skip - dies with it. The next sub-agent rediscovers it from scratch. Your own next session does too.
ax is the loop that closes before the session ends. A Stop hook fires at session-end (main or sub-agent), asks the agent for a structured retro (tried · worked · failed · next), and indexes the result as a typed experiment in a local graph. Friction patterns become proposals you triage. Accepted proposals become experiments with t+7 / t+30 / t+90 verdicts. The next session reads what worked.
What did this sub-agent learn? Which experiments are still open? Which skills earned their keep? Which hooks blocked anything useful? ax answers these by reading what already happened.

curl -fsSL https://raw.githubusercontent.com/Necmttn/ax/main/install.sh | bash
PATH="$HOME/.local/bin:$PATH" axctl ingest --since=7
Skills are distributed via the skills.sh marketplace. After the CLI is installed, drop the agent skills into your Claude Code session with:
npx skills add Necmttn/ax # installs ax:setup + ax:retro skills
Requires Bun ≥ 1.3 and SurrealDB ≥ 3.0. macOS-first; Linux works for ingest and CLI (no launchd reactivity).
For dev install, schema, queries, and benchmarks, see docs/development.md.
axctl ingest --since=7 # backfill last 7 days of transcripts + skills + git
axctl serve # live dashboard at http://127.0.0.1:8520
axctl skills taste # CLI view: which skills earned their keep
axctl recall "auth bug" # full-text recall across past sessions
axctl ingest [--since=N] [--reset] # backfill the graph
axctl ingest here [--since=Nd] # scope ingest to the git repo at $PWD
axctl derive-signals # re-run derive pass standalone
axctl derive-intents # re-run user-intent derive standalone
axctl serve # live web dashboard (API for ax studio)
axctl report # one-shot static HTML
axctl tui # interactive terminal dashboard
axctl recall <query> [--sources=turn,commit,skill] [--scope=here|all]
# cross-session BM25 full-text search
axctl context [file] [<query>] # file/agent-context grounding
axctl skills <search|taste|unused|pairs|recovery|classify|tag|lint|weighted|by-role|roles>
axctl insights <view> # 19 read-only graph views
axctl classifiers <list|eval|explain> # classifier coverage and turn explanations
axctl costs <summary> # token/cost usage by provider/model quality
axctl sessions <here|around <date>|near <sha>|show <id>>
# windowed session queries
axctl costs summary [--since=N] # estimated token cost by provider/model
axctl costs for --session <id> # cost for one session
axctl costs for --query <text> [--limit=N] # cost for sessions matching turn text
axctl costs for --terms <a,b,c> [--since=N] # cost for sessions matching any term
axctl costs for --commit <sha> # cost for sessions that produced a commit
axctl costs for --branch <name> # cost for sessions linked to a branch
axctl pricing [--query <model>] # inspect imported model pricing rows
axctl share <session-id> # publish a sanitized session share via GitHub Gist
axctl roles # list role labels with skill counts
axctl project <context|verify|harness>
axctl evidence <guidance-next|session-summary|weekly>
axctl improve <list|show|accept|reject|verdict|checkpoint|reset>
axctl retro <emit|list|reflect|plan> # the retro-loop CLI
axctl hook <fire> # hook helper invoked from settings.json
axctl hooks <summary|invocations|backtest>
axctl daemon <status|start|stop|restart>
axctl doctor # local-install health check
axctl install # wire launchd + hooks + DB
axctl uninstall # remove launchd + bin symlink
axctl update [--check] # pull latest release
axctl version [--check|--banner]
Full reference: docs/insights-cli-reference.md.
ax ships two installable skills so a Claude Code / Codex agent can query its own evidence graph mid-session:
npx skills add git@github.com:Necmttn/ax.git --skill axctl -g -a claude-code -a codex -y
npx skills add git@github.com:Necmttn/ax.git --skill retro -g -a claude-code -a codex -y
Recommended agent loop:
1. axctl project context --json before work - stack, recent friction, verification commands. 2. Do the work. 3. axctl project verify --json before reporting done - runs the checks the project actually expects.
高质量的开源AI工作流项目,值得关注
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:AI工作流 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | ax |
| Topics | AI工作流TypeScript智能代理 |
| GitHub | https://github.com/Necmttn/ax |
| License | NOASSERTION |
| 语言 | TypeScript |
收录时间:2026-06-01 · 更新时间:2026-06-01 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端