NAME
sigmap — 97% token reduction for AI coding sessions — zero deps, 21 languages, MCP server
SYNOPSIS
npm install -g sigmapINFO
DESCRIPTION
97% token reduction for AI coding sessions — zero deps, 21 languages, MCP server
README
Try it now
npx sigmap
sigmap ask "Where is auth handled?"
Zero config. Zero dependencies. Under 10 seconds.
What is SigMap?
SigMap extracts function and class signatures from your codebase and feeds the right files — not the whole repo — to your AI.
Works with Copilot, Claude, Cursor, Windsurf, and any LLM.
Why SigMap?
- 80.0% hit@5 — right file found in top 5 results (vs 13.6% baseline)
- 40–98% token reduction — 2K–4K tokens instead of 80K+
- 52.2% task success rate — up from 10% without context
- 1.68 prompts per task — down from 2.84
- Works with any LLM — no API key, no cloud, no accounts
- Zero npm dependencies —
npx sigmapon any machine
Replace this with SigMap
| Without SigMap | With SigMap |
|---|---|
| ❌ Guessing which files are relevant | ✅ Right file in context — 80% of the time |
| ❌ Sending the full repo to your AI | ✅ Minimal context — only what matters |
| ❌ Embeddings / vector DB required | ✅ Grounded answers, no infra needed |
How it works
Ask → Rank → Context → Validate → Judge → Learn
- Ask —
sigmap ask "Where is auth handled?"— ranked file list - Rank — TF-IDF scores every file against your query
- Context — writes compact signatures to your AI's context file
- Validate —
sigmap validate— confirms right files are in scope - Judge —
sigmap judge— scores answer groundedness against context - Learn —
sigmap weights— boosts files that keep solving your tasks
Benchmark
Benchmark : sigmap-v6.10-main Date : 2026-05-05
Hit@5 : 80.0% (baseline 13.6% — 5.9× lift) Prompt reduction : 41.0% Task success : 52.2% (baseline 10%) Prompts / task : 1.68 (baseline 2.84) Token reduction: 40–98% (avg 96.8% across 18 real repos)
Measured on 90 coding tasks across 18 real public repos. No LLM API — fully reproducible.
Resources:
- Full methodology →
- Benchmark suite (GitHub) — scripts, tasks, and raw data
- Benchmark data (Zenodo) — archived results for reproducibility
Install
Try without installing:
npx sigmap
Install globally:
npm install -g sigmap
Install per-project:
npm install --save-dev sigmap
Standalone binary — no Node.js required:
| Platform | Download |
|---|---|
| macOS Apple Silicon | sigmap-darwin-arm64 |
| macOS Intel | sigmap-darwin-x64 |
| Linux x64 | sigmap-linux-x64 |
| Windows x64 | sigmap-win32-x64.exe |
Each binary ships with a .sha256 checksum. Verify a binary →
Volta:
volta install sigmap
Integrations
AI assistants — one run, all of them:
| Adapter | Output file | Used by |
|---|---|---|
copilot | .github/copilot-instructions.md | GitHub Copilot |
claude | CLAUDE.md | Claude / Claude Code |
cursor | .cursorrules | Cursor |
windsurf | .windsurfrules | Windsurf |
openai | .github/openai-context.md | OpenAI models |
gemini | .github/gemini-context.md | Google Gemini |
codex | AGENTS.md | OpenAI Codex · OpenCode |
sigmap --adapter copilot # default
sigmap --adapter claude
sigmap --adapter cursor
IDE extensions:
| IDE | Install | Source | Features |
|---|---|---|---|
| VS Code | Marketplace · Open VSX | github.com/manojmallick/sigmap-vscode | Status bar health grade, stale context alerts, one-click regen |
| JetBrains | Marketplace | github.com/manojmallick/sigmap-jetbrains | IntelliJ IDEA, WebStorm, PyCharm, GoLand — tool window + actions |
| Neovim | lazy.nvim / packer / vim-plug | github.com/manojmallick/sigmap.nvim | :SigMap, :SigMapQuery float window, statusline widget |
MCP server — 9 on-demand tools for Claude Code and Cursor:
sigmap --mcp
Try it
# 1. Generate context for your project npx sigmap2. Ask a question — get ranked files
sigmap ask "Where is auth handled?"
3. Validate — confirm the right files are in scope
sigmap validate --query "auth login token"
4. Judge — score your AI's answer for groundedness
sigmap judge --response response.txt --context .context/query-context.md
5. Inspect health
sigmap --health
Start guide
| Who | Start here |
|---|---|
| 👶 New | Quick start guide — setup in 60 seconds |
| ⚡ Daily | sigmap ask / sigmap validate / sigmap judge |
| 🧠 Advanced | Context strategies · MCP setup |
| 🏢 Teams | Config reference · CI setup |
Docs
| Section | Link |
|---|---|
| CLI reference (32 commands) | cli.html |
| Benchmark methodology | benchmark.html |
| Config reference | config.html |
| Roadmap | roadmap.html |
| 29 languages | generalization.html |
Support
If SigMap saves you context or API spend, a ⭐ on GitHub helps others find it.
Why not embeddings?
| Embeddings | SigMap | |
|---|---|---|
| Vector DB required | ✅ | ❌ |
| Infrastructure to run | ✅ | ❌ |
| Drift over time | ✅ | ❌ |
| Deterministic results | ❌ | ✅ |
| Zero-config setup | ❌ | ✅ |
| Works offline | ❌ | ✅ |
- No vector DB — signatures are plain text files committed to your repo
- No infra — runs locally, zero cloud dependencies
- No drift — regenerating is
npx sigmap, not a reindex pipeline - Deterministic — same input always produces same ranked output
- Faster — TF-IDF ranking runs in milliseconds, no embeddings to compute
29 languages
TypeScript · JavaScript · Python · Java · Kotlin · Go · Rust · C# · C/C++ · Ruby · PHP · Swift · Dart · Scala · Vue · Svelte · HTML · CSS/SCSS · YAML · Shell · SQL · GraphQL · Terraform · Protobuf · Dockerfile · TOML · XML · Properties · Markdown
All implemented with zero external dependencies.
License
MIT © 2026 Manoj Mallick · Made in Amsterdam
Docs · Changelog · Roadmap · npm
⭐ Star on GitHub if SigMap saves you tokens.