neuron-explorer
Qwen3.5‑4B 전용 조향형 뉴런 탐색기, 모든 MLP 뉴런을 밀어 결과를 보관·탐색
Koragraph는 지정한 저장소를 실시간 코드 그래프로 전환해 MCP로 제공하므로 AI 에이전트가 시스템을 재발견하지 않고 읽을 수 있습니다
Koragraph turns every repository you point it at into one live code graph, served over MCP, so your AI agent reads your systems instead of rediscovering them.
개발 도구JavaScript · PythonGitHub @Koragraph온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
아직 감지된 업데이트가 없습니다. GitHub 릴리스가 나오면 여기에 보입니다.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
프로젝트 폴더에서 /nomorevibe verify를 실행하면 소유권을 확인하고 소개를 직접 관리할 수 있습니다.
1분 만에 확인하기The 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.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
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.
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.README 전문 보기 ↗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.
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:
| Language | koragraph | CodeGraph | GitNexus | Graphify |
|---|---|---|---|---|
| JavaScript | 87.6 | 39.4 | 41.9 | 45.1 |
| TypeScript | 70.6 | 55.2 | 50.2 | 44.2 |
| Python | 86.1 | 85.1 | 54.6 | 53.3 |
| Go | 89.1 | 85.0 | 63.8 | 65.3 |
| Java | 86.0 | 73.1 | 68.6 | 53.5 |
| C# | 83.6 | 79.8 | 50.5 | 54.4 |
| PHP | 88.9 | 88.0 | 77.1 | 31.7 |
| Ruby | 51.5 | 41.3 | 28.7 | 40.8 |
| Rust | 68.7 | 76.5 | 48.9 | 47.6 |
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.
| Tool | Shell | What it's for |
|---|---|---|
blast_radius | koragraph blast <files…> | Run before editing. Everything that depends on this, across repos, and what has no test coverage. |
explore | koragraph explore "<symbol or phrase>" | Ranked declarations, source, callers, callees, in one call. |
search_code | koragraph search <name> | Find a name in the graph, not raw text. |
neighbours | koragraph neighbours <symbol> | Callers and callees of one symbol. |
changes_with | koragraph cochange <symbol> | What has historically shipped together with a symbol. |
file_symbols | koragraph symbols <file> | Declarations in one file. |
overview | koragraph overview | Orient on turn one, across every repo. |
recall | koragraph recall <symbol> | A past failure and its fix, a hazard, an open loop. |
remember | koragraph remember "<fact>" | Save a durable, code-anchored fact. The only writer. |
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.