来子AI工窗语算求 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
来子AI工窗语算求,安被不此一下上算求,服务章当前算求
来子AI工窗语算求 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。
来子AI工窗语算求,安被不此一下上算求,服务章当前算求
来子AI工窗语算求 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:pip 安装(推荐)
pip install perseus
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install perseus
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/tcconnally/perseus
cd perseus
pip install -e .
# 验证安装
python -c "import perseus; print('安装成功')"
# 命令行使用
perseus --help
# 基本用法
perseus input_file -o output_file
# Python 代码中调用
import perseus
# 示例
result = perseus.process("input")
print(result)
# perseus 配置文件示例(config.yml) app: name: "perseus" debug: false log_level: "INFO" # 运行时指定配置文件 perseus --config config.yml # 或通过环境变量配置 export PERSEUS_API_KEY="your-key" export PERSEUS_OUTPUT_DIR="./output"
pip install perseus-ctx && cd your-project && perseus quickstart
That's the whole install. Perseus auto-detects your project language (Python, Rust, Node, Go, Java, C++, Docker), scaffolds context-appropriate memory queries, injects an active memory gate, and renders live workspace state — all before your AI assistant reads a single directive. No plugins. No SDK. Just a markdown file where your assistant already looks.

---
Works with any MCP-compatible assistant: Claude Desktop, Claude Code, Cursor, Codex, Hermes Agent, Rovo Dev. Full setup guide →
@query "docker ps --format 'table {{.Names}}\t{{.Status}}'"
mongo-dev Up 4 hours redis-dev Up 4 hours
docker build -t perseus .
docker run --rm -v /path/to/workspace:/workspace perseus mcp serve
See Container Runtime for full Docker and compose deployment.
pip install perseus-ctx
perseus mcp serve # stdio (Claude Desktop, Claude Code, Cursor, Codex)
perseus mcp serve --transport sse --port 8420 # SSE (remote agents, multi-machine)
perseus quickstart # auto-detects project, scaffolds context, renders
Smart init detects your stack and tailors the setup: - Python → @memory queries for test patterns, type annotations - Rust → trait bounds, lifetime annotations, cargo config - Node.js/TS → npm scripts, ESLint config, component patterns - Go, Java, C/C++, Docker — all detected automatically - Falls back to a sensible generic query when unknown
The output file name is the only assistant-specific detail:
| Assistant | Output file |
|---|---|
| Claude Code | CLAUDE.md |
| Hermes Agent | .hermes.md (top priority) or AGENTS.md |
| Cursor | .cursorrules or .cursor/context.md |
| Codex | AGENTS.md |
| Rovo Dev | AGENTS.md |
| Any other | Whatever your assistant reads at session start |
Hermes priority order:.hermes.md→AGENTS.md→CLAUDE.md. Render to.hermes.mdfor highest priority.
Keep it fresh with cron, launchd, systemd, or perseus watch:
```bash
hooks: enabled: true on_render_complete: - cmd: "notify-send 'Context refreshed'" on_directive_error: - plugin: "my_error_handler" ```
directives: aliases: "@q": "@query" "@svc": "@services" "@stale-skills": "@skills flag_stale=true category=all" ```
Pre-defined aliases: @q→@query, @r→@read, @svc→@services, @mb→@memory, @ag→@agora, @wp→@waypoint, @sess→@session. Config aliases override them.
```python
from perseus.registry import DirectiveSpec
def _resolve_service_status(args, cfg, workspace): import urllib.request try: resp = urllib.request.urlopen(args.strip(), timeout=5) return f"Status: {resp}" except Exception as e: return f"Error: {e}"
REGISTER = { "@service-status": DirectiveSpec( name="@service-status", resolver=_resolve_service_status, args=["url"], kind="inline", call_sig="acw", executes_shell=False, safe_for_hover=True, cacheable=True, summary="Check HTTP status of a URL", ) } ```
Use it in context files: @service-status https://api.example.com/health
Built-in directives always win collisions. Plugins respect the same permission profile as built-ins (executes_shell gates behind allow_query_shell).
Shell scripts or Python callbacks fire at render lifecycle points — on_render_start, on_directive_resolved, on_cache_hit, on_cache_miss, on_render_complete, on_directive_error:
```yaml
来子AI工窗语算求开始一下上算求的算求不此丁下上算求得不此丁下上算求的算求不此丁下上算求
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,来子AI工窗语算求 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | perseus |
| 原始描述 | 开源AI工作流:Live context engine for AI assistants — resolve-before-context, session waypoint。⭐7 · Python |
| Topics | workflowai-assistantcli |
| GitHub | https://github.com/tcconnally/perseus |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-07 · 更新时间:2026-06-08 · License:MIT · 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