Codehelper
Local-first code intelligence for AI coding assistants: MCP tools, symbol graph search, impact analysis, and auto-index watch for Cursor, Claude Code, and Codex.
README
Codehelper
Local-first repo intelligence for AI coding assistants.
Codehelper indexes git repositories on your machine, builds a symbol and call graph, and exposes 60+ MCP tools so Cursor, Claude Code, Codex, and other MCP clients can search, understand, and safely change your code — without uploading the whole repo to a cloud model.
Three reasons to use Codehelper
- Project-aware agents — Search symbols, callers, and blast radius locally instead of grepping whole files.
- Works offline — No API keys; your code stays on your machine.
- Fits your editor — MCP for Cursor, Claude Code, Codex; one
codehelper initper repo.
Installation
Linux / macOS (recommended):
curl -fsSL https://raw.githubusercontent.com/VeyrForge/codehelper/main/scripts/install.sh | sh
Windows (PowerShell):
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1
From source (requires Go 1.25+, CGO, and a C compiler):
git clone https://github.com/VeyrForge/codehelper.git && cd codehelper
npm run build
Prebuilt 3.0.1 bundles (Linux, macOS, Windows) include codehelper, MCP server, ge 1.0.0, and greencompress 1.0.0 on GitHub Releases.
Updates: codehelper upgrade downloads the latest release from VeyrForge/codehelper. codehelper update rebuilds from a local git checkout.
30-second example
cd your-git-repo
codehelper init
codehelper help tools --main
Reload Cursor or Claude Code after the first init, then call project_context once per session so the agent knows which tools exist and how fresh the index is.
See it work
No bundled demo video yet — here is a typical first session:
$ codehelper init
init: ready — index + watch daemon active
$ codehelper status
symbols: 1247 edges: 3891 freshness: current
$ codehelper help tools --main
project_context bootstrap tool catalog + index stats
query search the symbol graph
context source + callers + callees
impact blast radius before you edit
Recorded benchmark results: docs/BENCHMARK.md.
Supported platforms
| Platform | Install | Notes |
|---|---|---|
| Linux | scripts/install.sh |
Full support; primary CI target |
| macOS | scripts/install.sh |
Universal + per-arch release binaries |
| Windows | scripts/install.ps1 |
x64 supported |
| Client | Setup |
|---|---|
| Cursor | Per-project .mcp.json via codehelper init |
| Claude Code | Managed block in ~/.claude.json |
| Codex | Reads generated AGENTS.md |
How it works
| Layer | Technology |
|---|---|
| Indexing | tree-sitter parsers + SQLite symbol/call graph |
| Search | BM25 + trigrams + call-graph ranking (optional semantic rerank via local embed server) |
| MCP transport | stdio (default) or HTTP (codehelper mcp --http :8765) |
| Optional LLM | Green Engine embed/chat + Green Compress weights |
init indexes the repo, starts the watch daemon, wires MCP for your editor, and writes agent rules. Optional local dashboard: ge ui serve → http://127.0.0.1:8780
Full tool reference: docs/MCP_TOOLS.md
Benchmarks
See docs/BENCHMARK.md for recorded retrieval and indexing benchmarks on real repositories.
Documentation
- docs/MCP_TOOLS.md — MCP tool reference
- docs/BENCHMARK.md — benchmark results
- CHANGELOG.md — version history
- third_party/README.md — bundled Green stack binaries
Limitations
- Requires a git repository for indexing.
- CGO and a C compiler are required to build from source (tree-sitter).
- Semantic rerank and some enrichment features need optional local LLM services (Green Engine).
- Windows arm64 prebuilt CI is temporarily disabled; x64 is fully supported.
Contributing
Bug reports, benchmark results, compatibility notes, and suggested improvements are welcome on the official VeyrForge/codehelper repository.
To prepare a code change: fork the official repository only to open a pull request back to VeyrForge. Do not publish forks as competing distributions. See License and permitted use below.
Public release history
See CHANGELOG.md and GitHub Releases.
License and permitted use
Codehelper is source-available software — not open source.
You may download, clone, install, inspect, and run Codehelper for personal use or internal use within your organization.
You may fork the official repository solely for the purpose of preparing and submitting a contribution back to the official VeyrForge repository.
You may not redistribute Codehelper, publish modified builds, sell or sublicense it, offer it as a competing hosted service, or use its source code to create a competing product without written permission from VeyrForge.
Tutorials and blog posts may include short illustrative snippets from the published source for explanation, provided they do not redistribute the software or imply an open-source license.
For commercial redistribution, OEM licensing, or other usage not covered above, contact VeyrForge.
This section is a plain-language summary. The binding terms are in LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。