The ultimate context layer for your AI coding agent.
Completely free. Runs entirely on your machine.
A local knowledge graph of every repo you point it at, plus a memory layer that knows when the code it remembers has changed.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add koragraph-koragraphmcp -- npx -y koragraphmcp@0.1.4在終端機中執行。
{ "mcpServers": { "koragraph-koragraphmcp": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Completely free. Runs entirely on your machine.
A local knowledge graph of every repo you point it at, plus a memory layer that knows when the code it remembers has changed.
The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down. Anchor your context to your code. when the code moves, so does the memory. works on claude code, cursor, codex. Completely local.
npm install -g koragraphmcp
koragraph ingest /path/to/repo # point it at as many repos as you like
claude mcp add koragraph -s user -- koragraph mcp
koragraph doctor checks the whole chain and prints the exact line for any editor.
Two ways to use it from here: your agent calls the tools over MCP, or you (or a script, or a Claude
Code hook) run them straight from the shell, for example koragraph explore "how does checkout work"
or koragraph blast src/pay.js. Same graph either way.
This is the step that lights up the memory layer, so don't skip it. In your coding agent (Claude Code, Cursor, Windsurf, whatever you use), tell it:
"Read
KORAINIT.mdand follow it."
It imports your existing CLAUDE.md / AGENTS.md into koragraph's memory, anchored to the code
each rule is about, flags any rule that points at code that's already gone, and finishes wiring
koragraph into the session. Run it once per project.
Prefer zero setup? Hand the whole thing to your agent instead. Paste this from the repo you want indexed, and it installs, indexes, wires itself in, and runs KORAINIT for you:
Install koragraph and set it up for this repo, then report back:
1. npm install -g koragraphmcp
2. koragraph ingest .
3. koragraph doctor, then run the `claude mcp add …` line it prints (or wire `koragraph mcp` into
my editor's MCP config).
4. Find KORAINIT.md in the installed package (`npm root -g`, then koragraphmcp/KORAINIT.md) and
follow it: it imports my existing CLAUDE.md / AGENTS.md into memory, verified against the code.
Report: nodes/edges indexed, whether the MCP connected, and KORAINIT's summary.
Adoption is highest on Claude Code: its hooks let koragraph put the graph in front of the agent on every turn, so it actually gets used instead of falling back to grep. Other editors reach koragraph over MCP, where the agent decides when to call it.
Koragraph turns every repo you point it at into one live graph: a resolved structure, with an edge only where there really is one.
Everything your agent learns is saved locally, anchored to the exact declaration, not a line
number. Rename the code and the fact follows; delete it and the fact retires. No CLAUDE.md to
maintain, and it survives every upgrade.
Every graph is graded by an independent compiler front-end (CPython ast, go/parser, Roslyn,
syn, tsc, Ripper, php-ast, ctags, swiftc), never the tool under test. koragraph wins 34 of
39 language×plane cells, and leads precision on all 39.
Call-graph recall, the hardest plane:
Reproduces from test/benchmark: pinned corpus, pinned competitor versions,
pinned oracles. Full breakdown in test/benchmark/REPORT.md.
Nine tools, reachable two ways: as MCP tools in your editor, and as CLI commands in your
shell. On Claude Code a hook also calls the CLI to push the relevant slice into context on every
turn, so the graph gets used whether or not the agent thinks to ask. Every tool returns file:line,
never pasted source. Exactly one writes.
Every query verb takes --format compact|json|paths and --budget <tokens>, so a result can be
trimmed before it ever enters an agent's context. Plus the operational CLI: ingest, serve,
status, doctor, diff, trace, hooks, practice, report.
c · c++ · c# · go · java · javascript · php · python · ruby · rust · swift ·
typescript / tsx, fully resolved, tree-sitter throughout. Plus experimental kotlin · scala ·
elixir · solidity · vue · zig · objective-c · ocaml · rescript.
BUSL-1.1. Free to use, including at work. Converts to Apache-2.0 on the change date.
The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down.
{ "mcpServers": { "koragraph-koragraphmcp": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}總覽
The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down. Anchor your context to your code. when the code moves, so does the memory. works on claude code, cursor, codex. Completely local.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
KoragraphMCP 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down. Anchor your context to your code. when the code moves, so does the memory. works on claude code, cursor, codex. Completely local.