Local Coding Agent

Name: Local Coding Agent
Author: pvnc228

作者：pvnc228版本 1.2.0i★ –i在你的电脑上运行

注册名称io.github.pvnc228/local-coding-agent

安装

概览

作者提供的说明（英文原文）

Delegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 其他

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
注册中心没有列出需要填写的密钥。

你需要

PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "local-coding-agent": {
      "command": "uvx",
      "args": [
        "local-coding-agent",
        "serve-mcp",
        "--workspace",
        "your-value"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add local-coding-agent -- uvx local-coding-agent serve-mcp --workspace your-value

这个服务器需要在启动命令中填入值，请复制设置后自行填写。

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "local-coding-agent": {
      "command": "uvx",
      "args": [
        "local-coding-agent",
        "serve-mcp",
        "--workspace",
        "your-value"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器需要在启动命令中填入值，请复制设置后自行填写。

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "local-coding-agent": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "local-coding-agent",
        "serve-mcp",
        "--workspace",
        "your-value"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 pvnc228 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32415 个服务器的 0%
发布到注册中心的时间比此分类中其他 32415 个服务器的 91% 更新
基础检查结果等于或优于此分类中其他 32415 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Local Coding Agent 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.2.0）于3天前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, Safe Fetch

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新

安装

Safe Fetch

作者：Sanoy24

MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.

在你的电脑上运行今天更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Local Coding Agent

Local execution and safety layer for delegating coding tasks from cloud agents to models on your own machine.

What is Local Coding Agent?

Local Coding Agent lets a cloud coding agent delegate a narrow task to a local model without giving that model unrestricted access to your repository. Connect Codex, Claude Code, Cursor, Windsurf, Cline, OpenCode, Antigravity, or another compatible harness through MCP, the reusable Agent Skill, or the local-agent CLI. The cloud agent stays in charge of the larger task; Local Coding Agent supplies the controlled local execution path.

The calling agent sends a focused goal, a workspace, an allowlist of files, and checks. Your local model returns a proposal for review. The local model proposes; the controller verifies. A change is only reported as applied after the declared file scope held, the patch passed static analysis, and a real external test runner confirmed the configured checks. If a post-apply check fails, the change is rolled back and the rollback is itself verified against recorded file digests. The local model does not receive unrestricted shell or write access to your workspace.

Use the Desktop Harness when you want a Windows interface for local chat, model selection, sessions, task status, and change review. Use the CLI for terminals, scripts, CI, or direct integration with a coding harness. Both use the same controller and safety rules.

You keep control of Git and delivery. Local Coding Agent does not create commits, push branches, publish releases, or download a model on its own.

What the gate refuses

The same gate backs apply_proposal, local-agent apply, and the desktop apply action:

A patch that touches a file outside the declared scope is rejected before the workspace is touched (error.kind: patch_outside_scope).
An apply with no targeted check is refused — no external evidence, no apply (error.kind: apply_requires_checks).
A patch that fails the post-apply checks is rolled back; the result is "rejected" with error.kind: post_apply_check_failed.
A rollback that cannot be confirmed against the recorded baseline is reported as workspace_modified: true with workspace_state: "unknown" and risk kind rollback_failed — never as a clean restore.

Choose your download

Current public release: v1.2.0

Choose the CLI release for terminal workflows, scripts, CI, or integration with another AI coding environment. It provides the local-agent command, MCP server, Agent Skill, diagnostics, sessions, model tools, and task delegation.

Download the CLI wheel or CLI source archive. Windows users can download the Desktop Harness installer and verify the published files with SHA256SUMS.txt.

The v1.2.0 release contains the CLI archives and the Windows Desktop Harness installer. Local inference remains local; install Ollama or run a compatible local model server before requesting live model responses.

Desktop Harness

Open the Harness, choose a workspace, select a local model, and start working. The desktop application brings the complete local coding workflow into one focused interface:

Interactive Chat for questions, explanations, and everyday coding work.
Chat, Build, Plan, and Auto modes for different kinds of requests.
Delegated Tasks for handing a focused coding change to a local model.
Workspace sessions so you can return to previous conversations and tasks.
Model discovery, model profiles, context settings, hardware telemetry, and diagnostics.
Clear status messages when the local backend is ready, unavailable, or needs attention.
Reviewable code changes and checks before changes are applied.

The 30-second tour below follows one delegated change: the local model proposes, the controller checks scope, a real test runner decides, and a failed check rolls the change back. Click it for the video with sound.

CLI installation

Requirements:

Python 3.10 or newer.
Git on PATH for workspace operations.
Ollama or an OpenAI-compatible local model server for live inference.

Install the CLI package:

pipx install local-coding-agent

Or install from a checkout:

git clone https://github.com/pvnc228/local-coding-agent.git

cd local-coding-agent python -m pip install -e .

Check the installation:

local-agent doctor

local-agent test-run --mock

Add --json where supported when the output will be consumed by another tool.

Connect another AI coding agent

Local Coding Agent can provide its capabilities to other AI coding environments through MCP or an Agent Skill:

local-agent init-mcp --auto --write

local-agent init-skill --write

Start the MCP server manually when a client needs an explicit command:

local-agent serve-mcp --workspace . --enable-tasks

See local_coding_agent/docs/MCP_INTEGRATION.md for client configuration examples and skills/local-coding-agent/SKILL.md for the reusable Agent Skill.

A typical coding request

Choose a workspace and a local model.
Ask a question or describe the change you want.
Inspect the suggested code change in the application.
Run the relevant checks and apply the change when it looks right.

The application keeps the workflow understandable: you can see what is being changed, which checks are being run, and whether the local backend is available. Commits, tags, pushes, and publishing remain under your control.

CLI commands

Command	Purpose
`local-agent delegate`	Give a focused coding task to a local model.
`local-agent decompose`	Break a larger request into smaller coding tasks.
`local-agent apply`	Apply a reviewed change and run its checks.
`local-agent chat`	Run a prompt or a persistent chat session.
`local-agent sessions`	List or inspect saved sessions.
`local-agent profiles`	Inspect configured model profiles.
`local-agent memory`	Inspect model memory and VRAM settings.
`local-agent calibrate`	Calculate safe worker bounds for a VRAM budget.
`local-agent benchmark`	Run the local coding benchmark.
`local-agent doctor`	Diagnose Python, Git, Ollama, RAM, VRAM, and models.
`local-agent monitor`	Serve the local metrics dashboard.
`local-agent test-run --mock`	Run deterministic local workflow checks.

Examples:

local-agent chat "Explain what context_manager.py does"

local-agent chat --repl --session-id refactor-session local-agent delegate --task task.json --model qwen2.5-coder:7b --json local-agent apply --patch-file patch.diff --workspace . --file src/foo.py --check "pytest tests/" local-agent monitor --port 8765

Open http://127.0.0.1:8765/dashboard to view queue load, latency, tokens per second, and change records.

The CLI also exposes preview surfaces that are not part of the stable contract and may change without notice: ui/app, lsp, serve-acp, skeletonize, lint-patch, scan-models, spill-read, and grep. The stable, tested set is the table above plus desktop, chat, serve-mcp, init-mcp, and init-skill.

Field results & limitations

The published numbers come from a 20-task suite, so treat them as directional rather than settled:

On that suite, qwen3.8-27b-q4 scored 100.0% correctness with a 95% Wilson interval of [83.9%, 100.0%], and qwen3-8b-q6k scored 90.0% [69.9%, 97.2%]. The wide intervals are the small sample size, not a rounding artifact.
Small models handle single-file work in this harness; cross-file coordination (Tier 3 in the capability ladder) needs the host agent to decompose the task into atomic envelopes first.
Results are model and hardware specific. Reproduce them with local-agent benchmark before relying on any figure.

See local_coding_agent/docs/BENCHMARK.md for the methodology and the full table.

Local models

Model profiles describe the provider, model, context window, generation limits, and keep-alive behavior. The Harness can discover installed Ollama models and local GGUF files, while the CLI exposes the same information for scripts and integrations.

local-agent profiles list --json

local-agent memory status --json

Documentation

Quickstart
FAQ
MCP integration
Security policy
Changelog
Architecture reference
Protocol reference
Benchmark methodology
Roadmap
Runtime setup tips: context, KV cache, thinking and CPU limits

The same pages open inside the Desktop Harness under Help, and local-agent help-docs prints them in a terminal.

License

Local Coding Agent is distributed under the MIT License.

Local Coding Agent

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“其他”中的其他服务器比较i

常见问题

替代选择

Spec Driven Development

Remote Desktop Commander

Safe Fetch

作者的 README

Local Coding Agent

What is Local Coding Agent?

What the gate refuses

Choose your download

Current public release: v1.2.0

Desktop Harness

CLI installation

Connect another AI coding agent

A typical coding request

CLI commands

Field results & limitations

Local models

Documentation

License