6 phút đọc
repowise-dev/repowise: Codebase intelligence for AI and humans: code health scores, auto-generated docs, git anal – Repository repowise-dev/repowise. Mô tả: Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.. 7844 stars, 910 forks, ngôn ngữ chính Python, cập nhật 2026-10-19.
1. Repository làm gì?
Repowise indexes your code, call graph, git history, tests, docs and design decisions once, on your machine. Then you and your coding agent ask it things: what calls this, what breaks if I change it, what is dead, what to fix first, why it was built this way, and what evidence stands behind each change that landed.
Free for one developer on a laptop. Built to run across a company's repositories.
Graph, risk, health, tests and dead code make zero LLM calls · same diff, same answer · runs inside your network · scoped tokens for REST and MCP · change policy in CI with SARIF · free, AGPL-3.0 or commercial
Hosted · Foresight · What it does · Quickstart · Agents · Changes · Code health · Workspaces · Evidence · Enterprise · Docs
Repowise is an ambitious project. We want every engineer, and every agent working beside them, to understand a codebase the way the person who has maintained it for five years does: what calls what, what tends to break, what nobody uses anymore, and why it was built this way. Cutting tokens was never the goal. It happens anyway, because an agent that can ask the index stops searching, opening and re-reading files to find out. Measured against the other context tools on the same agent tasks, it is also the largest saving.
The same engine serves a developer who wants their agent to stop rediscovering the code and a platform team that has to show what changed, who owns it and which tests reached it. Every engine capability is in the free, open-source version. The commercial layer adds organisation-wide operation on top.
2. Dữ liệu và cấu trúc đáng chú ý
Everything in this README runs free on your own machine. repowise.dev runs it for you, private repos included, and is where Foresight arrives first: models trained on years of real commits and fixes that rank the files a fix will touch, name what a change forgot, and explain every answer, with no LLM. What Foresight does →
Open Claude Code, Codex, Cursor or any MCP-capable agent in your repository and paste:
The agent installs Repowise, indexes the repo with no API key, wires itself to the index, and asks you before anything costs money. Prefer to do it yourself:
init wires Claude Code automatically. Then ask your agent "Use Repowise get_overview to summarize this repository" or "What breaks if I change src/auth.py?" Full setup, every agent, optional model-written docs →
One index, three ways to use it. Find the question you came with; each one links to the page that answers it.
Recorded on this repository and its workspace: an agent asking the index, then the dashboard and CLI on the same local index. No API key and nothing uploaded.
Every question your agent asks about a repository has an answer that could have been computed ahead of time. Who calls this function? What breaks if I change it? Why is it written this way? Which files are actually dangerous? Without an index, the agent rediscovers that answer on every task: grep, read, re-read, forget.
3. Khả năng ứng dụng và giới hạn
Repowise gives Claude Code, Codex, Cursor, VS Code and any other MCP host ten task-shaped MCP tools backed by one index of graph, git, docs and decisions. Most code tools are built around data entities, one file or one symbol at a time, which pushes agents into long chains of sequential calls. These are built around tasks: pass several targets in one call and get the whole picture back. The tool list ↓
About tokens. Every tool in this category promises to cut your token bill, and there are a lot of tools in this category. We think tokens are a symptom. An agent burns them because it does not know the codebase, so it searches, opens files, opens more files, and searches again. Give it an index that already knows, and the savings show up on their own. They also happen to be the best we have measured: in a paired agent loop over 43 questions on django/django, Repowise cut the agent's own output by 31.6% (p<0.0001) and got there in 3.8 tool calls instead of 7.2, ahead of every other context tool in the same run. On 42 sealed retrieval tasks it found 0.876 of the files a fix needed, against 0.610 for the next tool. Method and every row we lose →
Context arrives before the agent asks. Optional hooks push it into the session when it matters: the governing decision when your agent edits a file that decision covers, a warning when it touches a file with a run of recent bug fixes, a short briefing at session start, and a correction when it reaches for a path that does not exist.
It learns from how you work. Switch on transcript capture (repowise decision source set session –on) and Repowise reads your own agent transcripts for the corrections you keep making, turning the durable ones into tracked decisions it delivers back later. Transcripts never leave your machine; one batched model call per update turns the candidates that clear the deterministic gates into records, and –no-llm keeps the gates and drops that call.
The structural wiki needs no model. Model-written prose is an optional upgrade, one page or directory at a time.
How the layers fit together → · How the graph earns trust →
Also: stop paying for output nobody reads
Most of what an agent reads back from a shell command is noise: 300 lines of passing tests wrapped around 4 failures, full commit bodies when it asked what changed recently. repowise distill compresses command output before the agent reads it, errors first, exit code preserved.
Every omission leaves an inline [repowise# ] marker that repowise expand reverses in full, so the agent can pull the detail back without re-running the command. Small outputs pass through untouched. An opt-in hook rewrites noisy commands for the agent automatically.
Số liệu repository có thể thay đổi; nên mở liên kết nguồn để kiểm tra README, giấy phép và trạng thái phát hành.
Nguồn tham khảo: Xem bài gốc
