Wisegit

What is Wisegit?

Wisegit is a local MCP server that extracts decision intent from git history, so AI agents respect intentional code rather than treating all code equally. It indexes commits, computes per-function “freeze scores,” and serves decision manifests—marking functions as frozen, stable, or open—before any file edit.

How to use Wisegit?

Run npx @sandip124/wisegit setup in any repository—zero configuration. After indexing, AI agents call MCP tools such as get_file_decisions to retrieve decision manifests, and create_override to override frozen functions with user approval in Claude Code.

Key features of Wisegit

• Zero config setup with a single command
• SQLite database (no Docker or external services)
• Team support via .wisegit/ directory tracked by git
• AI-era commit origin detection (human, AI reviewed, AI unreviewed)
• Theory holder tracking per function (healthy / fragile / critical)
• HTML codebase health report (wisegit report)
• Grounded in 12 published software engineering papers

Use cases of Wisegit

• Prevent AI agents from removing manually‑tested workarounds (e.g., sleep(350) for race conditions)
• Identify functions lacking active theory holders to mitigate institutional knowledge loss
• Safely modify code by respecting frozen/stable/open zones with auditable overrides
• Search past decisions across the entire git history for context during code reviews

FAQ from Wisegit

What are the runtime requirements?

Only a local SQLite database—no Docker, PostgreSQL, or any external services needed.

How does Wisegit classify commits?

It parses diffs at the AST level using Tree‑sitter for C#, TypeScript, JavaScript, Python, Go, and Rust, then labels commits as STRUCTURED, DESCRIPTIVE, or NOISE.

What is a freeze score?

A 0–1 score per function derived from seven signal categories including git history, issue enrichment, code structure, test signals, and structural importance.

How does team collaboration work?

The .wisegit/ directory is tracked by git; JSONL files within it merge cleanly, enabling shared override audit trails and decision histories.

What MCP tools does Wisegit expose?

Eight tools: get_file_decisions, get_freeze_score, get_function_history, get_theory_gaps, get_branch_context, search_decisions, create_override, and extract_intent.