Give the agent the answerable shape of the codebase.

Any MCP-compatible client. repowise is agent-neutral: it works with Claude Code (primary, with one-command setup), Codex CLI, Cursor, Cline, and Windsurf, plus any tool that speaks the Model Context Protocol. The same ten tools are exposed over a single MCP endpoint, so you are not locked to one editor.

In a real agent loop (Codex, django/django, 43 questions against a bare-agent control), repowise cut output tokens 31.6% and reached an answer in 3.8 tool calls instead of 7.2, opening 3.0 files instead of 7.2. A second run on Claude Code held at 15.9%. Loading one commit's context on its own is a separate, easier number: 35.6x fewer tokens than reading every changed file, which measures one payload rather than a finished session.

Distill is index-aware output distillation. It compresses noisy command output such as pytest, git log, and git diff before the agent reads it, saving 60 to 90 percent of the tokens while preserving every error line. Measured savings: 61% on a pytest run with 11 failures (all 11 failure lines kept), 89% on git log, and 86% on a 30-commit git diff. It is fully reversible.

Every MCP response carries a _meta envelope with index_age_days, the indexed_commit, and a stale_warning that appears only when the index has actually diverged from HEAD. Silence means the index is current. This is honesty as a feature: the agent is told when to verify against source rather than trusting a snapshot blindly.

No. repowise is open source under AGPL-3.0 and self-hostable, and it speaks the open Model Context Protocol, so any MCP client can call it. You can run it fully local with your own API key, or fully offline via Ollama, and your code never has to leave your infrastructure.

get_overview (architecture map, module list, entry points), get_answer (a cited answer with calibrated retrieval_quality), get_context (a triage card for files, modules, or symbols), get_symbol (raw source bytes for one indexed symbol), search_codebase (semantic search over the wiki), get_risk (hotspot scores, dependents, and PR directives), get_change_risk (a pre-merge defect-risk score for a commit or diff range), get_why (architectural decision rationale and lineage), get_dead_code (unreachable code by confidence tier), and get_health (per-file code-health scores).

IDE indexes like Cursor and Continue are ephemeral, single-repo, and embeddings-only: they re-embed on demand and forget. repowise is a durable, structured layer every agent can call over MCP, enriched with code health, git history, ownership, and architectural decisions your editor never sees, and it spans multi-repo workspaces.

Yes. repowise auto-generates CLAUDE.md for Claude Code and a managed AGENTS.md for Codex, with architecture, entry points, hotspots, and conventions, and keeps them current as the codebase changes. Agents that read those files get accurate orientation before they make a single tool call.