← 项目档案
AI Agent Toolkit
面向 Windows 的本地 AI 编程工具集——多智能体工作流、Ollama 自动化与开发者仪表盘工具。
这是什么
问题
大多数 AI 编程工具都默认运行在云端和 Unix 环境。这个工具集探索一种本地优先、面向 Windows 的工作流，在自己的机器上运行和编排模型。
方案
基于 PowerShell 的工具集，自动化 Ollama、协调多个智能体，并提供小型仪表盘工具——让整个流程保持本地化、可脚本化且对 Windows 友好。
界面一览
Toolkit mapThe public documentation separates machine automation, the dashboard, conservative repo workers, and advisory role prompts.
技术栈
Automation
- PowerShell 5.1/7
- Windows Task Scheduler
- GitHub CLI
Local AI
- Ollama
- qwen2.5-coder:14b
- Aider
Control surface
- Python
- Streamlit
Platform
- Windows 10/11
- VS Code
- Cline
亮点功能
- Ordered inspect/install/model/validation bootstrap scripts
- Ollama lifecycle, model checks, diagnostics, and provider routing
- Streamlit dashboard with eight operational pages
- Conservative one-task repo worker that branches, validates, reports, and stops
- Six-role advisory pipeline that never edits the target repository
- Explicit safeguards against dirty worktrees, secrets, commits, and pushes
工程实现
- 过程 01
Wrap model automation in a conservative worker
- 背景
- A local model can edit quickly, but unattended commits, dirty worktrees, and sensitive-file changes create unacceptable risk.
- 方法
- Require a clean repo, create an isolated branch, run one task, validate, flag risky files, report, and stop without committing or pushing.
- 结果
- Automation is slower and deliberately human-gated, but its output remains reviewable and recoverable.
- 过程 02
Keep the six-role pipeline advisory
- 背景
- Multiple role prompts are useful for planning and review but can compound mistakes if each is allowed to mutate the repo.
- 方法
- Pass repository context through six sequential roles that only write a combined report.
- 结果
- The pipeline improves perspective without edit conflicts, though a human still has to turn advice into code.
实现细节
架构笔记
- Automation is scripted in PowerShell so it stays transparent and hackable.
- The repo worker delegates edits to Aider but wraps it in preflight checks, isolated branches, validation, risk scanning, and reports.
- The six-role pipeline is advisory: it passes repository context through Product, Tech Lead, Developer, QA, Reviewer, and DevOps prompts without changing files.
- The dashboard is split into config, data, services, pages, and UI modules rather than one Streamlit script.
挑战
- This is a personal toolkit shaped around one machine, not a general-purpose agent platform.
- Most scripts assume a C:\ai-agent-tools installation path and depend on locally installed Windows tooling and hardware.
- Local models provide continuity and privacy, but they do not match the capability or convenience of every paid model.
结果
A released v1.1.0 personal toolkit with documented setup, safety boundaries, diagnostics, dashboard modules, and repeatable local-model workflows. It is useful as a reference, not advertised as a polished cross-platform product.
规划与心得
复盘
- 01Local-first AI tooling trades convenience for control and privacy.
- 02Windows-native developer tooling is underserved and worth designing for.
下一步
- 01Remove hard-coded installation assumptions
- 02Add repeatable integration tests for worker safety
- 03Publish measured local-model comparisons