接入你的智能体
发布者自己的命令。不是 PlugMCP 端点。
用我们的密钥与日志托管一份副本。
mcpb https://github.com/Graphicle-AI/graphicle/releases/download/v0.1.17/graphicle-0.1.17-aarch64-apple-darwin.mcpbClaude Code 没有针对本地命令的安装链接。复制下方命令并在终端中运行。
claude mcp add graphicle-ai-graphicle -- mcpb https://github.com/Graphicle-AI/graphicle/releases/download/v0.1.17/graphicle-0.1.17-aarch64-apple-darwin.mcpb在终端中运行。
{ "mcpServers": { "graphicle-ai-graphicle": { "command": "mcpb", "args": [ "https://github.com/Graphicle-AI/graphicle/releases/download/v0.1.17/graphicle-0.1.17-aarch64-apple-darwin.mcpb" ] } }}claude_desktop_config.json
远程 URL 还是本机命令？ 两种安装方式的区别
来自发布者
brew install graphicle-ai/tap/graphicle
cd your-repo
graphicle setup
No Homebrew? curl -fsSL https://github.com/graphicle-ai/graphicle/releases/latest/download/install.sh | sh · Release archives · Other ways to install Windows: a preview build for x86-64, not yet code-signed ().
Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.
graphicle setup indexes the repository, builds its code graph and connects the coding agents it finds. It also turns on session
capture, adds a two-line section to AGENTS.md (unless Claude Code is the only agent) and installs Git hooks that keep the project current. It lists every file it changes and
backs each one up first; graphicle disconnect undoes it all.
Then ask your agent to "use graphicle to find where failed requests are retried", or ask from the terminal:
$ graphicle ask "where is tax added to prices?"
Evidence for "where is tax added to prices?"
4 excerpts · 606 of 3,000 tokens
[1] shop/pricing.py:1-7 price_with_tax()
"""Prices and tax."""
TAX_RATE = 0.2
def price_with_tax(price):
"""A price with the sales tax added."""
return round(price * (1 + TAX_RATE), 2)
Real output, cut after the first excerpt. With no model configured, ask shows the evidence; graphicle config set model anthropic (or openai, ollama) adds written answers.
Paste this into Claude Code, Codex or Cursor:
Install Graphicle with `brew install graphicle-ai/tap/graphicle` (or, without Homebrew,
`curl -fsSL https://github.com/graphicle-ai/graphicle/releases/latest/download/install.sh | sh`),
then run `graphicle setup --yes` in this repository and list every file it changed.
GRAPHICLE_NO_UPDATE_NOTIFIER=1 turns off.graphicle graph searches it, explains a symbol,
traces a path and exports an interactive HTML graph. After graphicle graph extract . --code-only, graphicle graph affected "retry()" lists what depends on a symbol.graphicle context and the MCP tools return excerpts with their sources, within a token budget, without calling a model.graphicle mcp serves the code-graph tools, under Graphify's tool names such as query_graph, get_neighbors and shortest_path, next to the memory tools. With --pull-requests it also serves the pull-request tools list_prs, get_pr_impact and triage_prs, which use the GitHub CLI (MCP).graphicle call graph.doc_links lists them).graphicle context --workspace, or the workspace MCP endpoint.graphicle open shows the graph, the sources and the memory in your browser. It is where you approve memories.graphicle setup connects every client it finds over MCP. Each file is backed up once as <file>.graphicle-bak, and graphicle disconnect removes what it added.
.gitignore and skips secrets), keeps a versioned copy of each source and builds the code graph.The left column is a code-graph tool, such as Graphify's open-source engine, plus a separate memory server. It is not a comparison with Graphify Cloud, a hosted service that includes memory.
Every figure is labelled, and docs/benchmarks.md has the full tables, methods and limits. In the agent tests, a difference counts only when its 95% interval excludes 0; otherwise it is a tie. Long sessions and memory built up across coding sessions are not tested yet.
ca8a2a9e4 (a shallow clone, 30,315 files), over the 22 questions of issue #8, the median graphicle context call took 1.34 s with 0.1.8 against 2.99 s with 0.1.7 on 16 cores of our Linux server, 1.38 s against 3.89 s on 4 cores, and 1.90 s against 4.55 s on 4 cores with the file cache dropped before each call; 8 lookups took 0.96 s against 2.52 s on 16 cores. Each call was a new process, as the prompt hook runs it. On the same store, both releases gave the same packet for every question, and the peak memory of a call fell from 3.5 GB to 0.6 GB (method and rounds).Offline ranking, 100 SWE-bench Verified issues never used for tuning. Graphicle 0.1.8 put a file the fix changed in its first 5 files for 75 issues, against 61 for BM25 (SWE-bench style), a significant difference (McNemar exact p = 0.013); for the first file (43 vs 35) and the first 10 (81 vs 77) the differences are not significant. This measures ranking, not whether a coding agent fixes more issues; no agent test of this ranking has been run yet (method, task lists and limits).
graph update took 6 to 8 times less time than Graphify 0.9.91's (one Linux node, 4 CPUs per run), and both matched a fresh build apart from three kinds of keying difference that both programs share. In a 30-note sample, the 15 notes whose function changed were flagged and no other; a wider exploratory check found some false flags (details and limits).~/Library/Application Support/Graphicle on macOS, ~/.local/share/graphicle on Linux, %LOCALAPPDATA%\Graphicle on Windows. graphicle graph extract writes its graph file to .graphicle/ in the project.graphicle graph extract
(it sends documents and images to the LLM whose API key it finds), the GitHub CLI for graphicle graph add, clone and the graph server's pull-request tools, graphicle update with a feed you name, and a daily check for a new release.
That check is on by default: a command you run in a terminal asks GitHub for the latest release, with no code or data, to tell you about a new one (GRAPHICLE_NO_UPDATE_NOTIFIER=1 turns it off).
A build from source also downloads the parser sources once. Detailssync respects .gitignore and skips .env files, keys and credentials. Session capture drops <private>…</private> spans and redacts credentials.No, for most of it. The code graph (with --code-only), sync, context, the MCP server, session capture and the app work without one.
A model writes the answers of graphicle ask, proposes memories from sources and reads documents and images in a full graphicle graph extract.
Local models through Ollama or any OpenAI-compatible server work (configuration).
The code-graph engine is a Rust port of Graphify, credited in its file headers and in NOTICE. It follows Graphify 0.9.95, and later Graphify releases are ported in later versions; the parity checks compare it with that release.
The memory, the memory tools, the app and session capture are not part of Graphify. Coming from Graphify? graphicle setup offers to switch a repository,
backs up each file and never deletes graphify-out/ (Moving from Graphify).
By default a project can hold up to 100,000 text files and 1 GiB of text; you can raise both (see Limits in docs/configuration.md). A very large file is analysed in part or kept as searchable text instead of stopping a sync.
Graphicle is free and open source under Apache-2.0, for individuals and teams alike. A commercial edition for teams is in private preview. To talk to us, start a discussion: https://github.com/graphicle-ai/graphicle/discussions, or chat with us on Discord.
Graphicle is Apache-2.0: free to use, change and ship, commercially too. Third-party parts keep their own licences, listed in NOTICE.
More answers: FAQ · Troubleshooting · or run graphicle doctor.
Quick start · Agents · MCP · Install · Configuration · Team server · Moving from Graphify · Benchmarks · FAQ · Changelog
The code: crates/graphicle/ (the program: command line, app, HTTP and MCP server), crates/graphicle-graph/ (the code-graph engine),
crates/graphicle-memory/ (the memory library), SDKs for Python and TypeScript,
and a team server recipe in deploy/. Each crate builds on its own (building from source).
Contributions are welcome under the Apache License 2.0, with a Developer Certificate of Origin sign-off (git commit -s) and no CLA.
See CONTRIBUTING.md. To report a security problem, follow SECURITY.md rather than opening a public issue.
Graphicle is licensed under the Apache License 2.0. Copyright 2026 KarLex AI, Inc.
Code signing policy: release builds are not yet signed with a trusted certificate. The Windows programs are signed through SignPath with a test certificate, which Windows does not trust, or left unsigned when that signing fails; each release's notes say which. Signing with the SignPath Foundation's certificate is planned. The policy also lists every case in which Graphicle contacts the network.
The code-graph engine is a Rust port of Graphify by Safi Shamsi and the Graphify
contributors, licensed under Apache-2.0, with portions that remain available under the MIT License. Thank you.
NOTICE, NOTICE.md and the licenses/ folders hold the attributions and the licences of every adapted project and third-party component.
Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.
{ "mcpServers": { "graphicle-ai-graphicle": { "command": "mcpb", "args": [ "https://github.com/Graphicle-AI/graphicle/releases/download/v0.1.17/graphicle-0.1.17-aarch64-apple-darwin.mcpb" ] } }}工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式，而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Graphicle 通过 stdio 在本地运行。
上次检查时间：2026-11-15。 Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.