yoyo
Grounded codebase answers for AI coding agents.
Sponsor
Shoutout to xagi.in, the first sponsor of yoyo.
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Grounded codebase answers for AI coding agents.
Shoutout to xagi.in, the first sponsor of yoyo.
yoyo is a local MCP server for repository reading and change work. It exists to make coding agents less hallucinated, more grounded, and more truthful when they answer questions about a real codebase.
yoyo is a local MCP server for repository reading and change work. It is built for agents first, so they stay grounded in the repo instead of guessing from model memory.
The core product is not generic search. It is a smaller and more reliable interface to the repository:
judge_change for ownership, invariants, and regression risk before editsinspect for cheap structured reads like signatures, type surfaces, file structure, and exact excerptschange for error-bounded writes through one task-shaped surfaceEssays:
Headline WIP result: in one clean directed ripgrep read_only eval, Codex used yoyo for 22/22 tool calls.
That run asked three explicit engineer questions: find the 3 most likely files or symbols, decide which layer should own the fix, and state the invariants and blast radius. yoyo localized the bug to hiargs.rs, walk.rs, and gitignore.rs, placed ownership in crates/ignore, and surfaced the key invariants and regression risks without making edits.
Write-side WIP result: yoyo is strongest when read judgment narrows the surface first, then change executes the write cleanly. The first clean directed write_only batch now shows that on ripgrep, uuid, and httprouter. semver is tracked separately: the patch in src/eval.rs is correct and passes manual cargo test, but the fixture's exact verify command, cargo test --test *, is malformed and still needs fixing before strict scoring.
This is groundedness and tool-use evidence under direction, not yet a broad with-vs-without benchmark. The old 119/120 tool-accuracy benchmark still exists as a legacy regression report, and the current compare smoke runs are still 6/6 ties across v1.8.5 and v1.7.3.
Current directed artifacts:
See evals/README.md for the current eval direction.
Coding agents are strong at local editing and weak at repository truth. They guess ownership layers, invent file paths, over-read source files, and lose the actual invariants of the system.
yoyo narrows that gap. It gives the agent:
.bakes/latest/bake.dbThe point is not to make toy tasks look slightly faster. The point is to make answers more truthful and more grounded in the code that actually exists.
retry_plan: failed guarded writes come back as machine-readable guard_failure payloads, then narrow into a bounded inspect-fix-retry workflow instead of vague stderr.yoyo.json is missing, yoyo now creates it automatically for supported interpreted languages, but keeps runtime execution restricted until an agent updates the repo policy.boot now surfaces agent-managed config, managed paths, a concrete runtime-access example, and project conventions loaded from yoyo.json. That file is the repo contract for agents: style rules, frameworks, common commands, and runtime policy all live there so the same context does not need to be re-prompted every session. .bakes/ is managed cache and is ignored by default in git repos.
Small example: if an edit changes Python return "hello" into return missing_name, a plain editor saves a broken file. A guarded write rejects it, restores the original file, and returns enough structure for the next repair attempt to target the right lines.
yoyo is opinionated about depth. The primary languages are:
Rust and Go currently have the strongest read surface, including indexed structured signatures in inspect.
macOS (Apple Silicon):
brew tap avirajkhare00/yoyo
brew install yoyo
Linux (x86_64):
curl -L https://github.com/avirajkhare00/yoyo/releases/latest/download/yoyo-x86_64-unknown-linux-gnu.tar.gz | tar xz
sudo mv yoyo-x86_64-unknown-linux-gnu /usr/local/bin/yoyo
Check:
yoyo --version
Claude Code or Cursor:
{
"mcpServers": {
"yoyo": {
"type": "stdio",
"command": "/usr/local/bin/yoyo",
"args": ["--mcp-server"]
}
}
}
Codex CLI:
codex mcp add yoyo -- /usr/local/bin/yoyo --mcp-server
Gemini CLI:
gemini mcp add yoyo /usr/local/bin/yoyo --mcp-server
Then index the project once:
yoyo index --path /path/to/your/project
For Codex, add this to AGENTS.md:
## yoyo
Call `boot` and `index` first.
Prefer `inspect` for code reads, `search` over grep, and `change` for code changes.
Prefer `judge_change` before edits when ownership, invariants, or regression risk are unclear.
Prefer `impact` for relation and blast-radius questions.
Without this, the agent may see yoyo and still fall back to its default habits.
yoyo currently exposes 13 MCP tools:
boot, indexhelpinspect, search, askjudge_changemap, impact, routes, healthchangescriptThe MCP surface is intentionally smaller than the CLI surface. Humans still have broader CLI commands for debugging and direct use.
LSP is for humans inside an editor. yoyo is for agents working over MCP.
Use both. LSP while you write. yoyo when your agent needs to understand or change code it has never seen.
yoyo is a local MCP server for repository reading and change work. It exists to make coding agents less hallucinated, more grounded, and more truthful when they answer questions about a real codebase.
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。
Yoyo 透過 stdio 在本機執行。
上次檢查時間:2026-11-05。 yoyo is a local MCP server for repository reading and change work. It exists to make coding agents less hallucinated, more grounded, and more truthful when they answer questions about a real codebase.