NervaPack

NervaPack

NervaPack is a privacy-first, offline knowledge graph for your codebase. It solves two fundamental problems with standard Vector RAG:

• Token waste — chunk-based RAG retrieves blobs of text that may only tangentially relate to your query, bloating your context window.
• Privacy risk — sending code to cloud embedding APIs leaks your proprietary logic.

NervaPack runs 100% on your machine. It uses tree-sitter to parse your codebase into a deterministic Abstract Syntax Tree graph, then uses a local Ollama model to draw hard semantic edges between your documentation and your code. Queries traverse this graph with a K-Hop BFS, returning a hyper-targeted, token-efficient context window — no cloud required.

---

Verified Performance

91.2% Average Token Reduction — independently verified on real-world codebases.

Cost Savings: $181–$724 per developer per year (GPT-4o to Claude Sonnet)

📊 [View Full Benchmarks](docs/BENCHMARKS.md) · 🧪 [Messy Code Performance](docs/MESSY_CODE_PERFORMANCE.md)

Code quality impact: 90–99% reduction on clean code, 50–75% on legacy/messy code. Even poorly structured codebases benefit significantly.

---

Why NervaPack vs. standard Vector RAG

---

Prerequisites

• Python 3.10+
• Git — your project must be a git repository (git init if not)

*(Optional for semantic code-doc binding)* — an LLM provider. Structural graph indexing and basic queries work out-of-the-box with zero configuration and no cloud connection.

---

Installation

# Recommended

pip install nervapack

With optional features

pip install "nervapack[mcp]" # MCP server for Claude Code / Cursor pip install "nervapack[memory]" # agent memory MCP server pip install "nervapack[metrics]" # exact token counts (tiktoken) pip install "nervapack[dashboard]" # web dashboard (streamlit + plotly) pip install "nervapack[claude]" # Claude API support pip install "nervapack[openai]" # OpenAI API support pip install "nervapack[all]" # everything

On first run, ChromaDB downloads an ONNX embedding model (~30 MB) to ~/.cache/chroma/. This is a one-time download.

---

Quick Start

cd your-project/

1. Build the knowledge graph (runs locally, no LLM required for basic use)

nervapack ingest .

2. Query for context — get focused results + token savings dashboard

nervapack query "How does authentication work?"

3. Add semantic doc-to-code edges (requires an LLM)

nervapack enrich .

4. Visualize the full graph

nervapack visualize --enhanced --communities

5. After changing files, sync incrementally (fast — only changed files)

nervapack sync .

6. If you ingested wrong data or need a fresh start

nervapack clean --all nervapack ingest .

7. Check system health

nervapack doctor

---

Command Reference

nervapack ingest [PATH] — Build the graph

Scans PATH (default: .) and builds the full knowledge graph.

What happens:

1. Walks the directory tree with tree-sitter, skipping dist/, build/, node_modules/, venv/, site/, .tox/, and dozens of other build directories automatically.
2. Parses source files into exact AST nodes: classes, functions, imports.
3. Chunks all .md files by header hierarchy.
4. Embeds every entity into a local ChromaDB vector store (ONNX by default, Ollama optional).
5. Optionally binds doc chunks to code nodes via an LLM, adding EXPLAINS edges.
6. Saves the graph once to .nervapack/graph.graphml.

Re-ingesting is safe — upsert is used throughout, so running ingest twice does not duplicate data.

nervapack ingest .                           # auto-detect LLM

nervapack ingest . --llm ollama # force Ollama nervapack ingest . --llm claude # use Claude API nervapack ingest . --llm openai --model gpt-4o-mini nervapack ingest . --embeddings ollama # use Ollama for embeddings too

Supported languages (bundled): Python, JavaScript, JSX, TypeScript, TSX

Additional languages:

pip install "nervapack[go]"            # Go

pip install "nervapack[rust]" # Rust pip install "nervapack[java]" # Java pip install "nervapack[c]" # C / C headers pip install "nervapack[cpp]" # C++ pip install "nervapack[ruby]" # Ruby pip install "nervapack[csharp]" # C# pip install "nervapack[all-languages]" # all of the above

Exclude directories — create .nervapackignore in your project root (gitignore syntax):

dist/

build/ site/ generated/ *.egg-info/

---

nervapack query PROMPT — Query the graph

Retrieves focused context for a natural-language prompt and prints a token savings dashboard.

What happens:

1. Intent detection — "what breaks if I change X" routes to impact analysis (reverse BFS); exact symbol names bypass vector search.
2. ChromaDB returns the top-3 most semantically similar nodes.
3. Those nodes seed a K-Hop BFS through the NetworkX graph (default: 1 hop, both directions).
4. Adjacent nodes — including any markdown docs via EXPLAINS edges and memory notes via TOUCHES edges — are collected.
5. A focused Markdown context block is printed, ready to paste into an LLM prompt.
6. Token efficiency panel shows savings vs. naive "dump the whole file" RAG.

nervapack query "How does authentication work?"

nervapack query "What calls VectorStore?" nervapack query "what breaks if I change GraphBuilder" # impact analysis

Example output:

Query: "How does authentication work?"

Query Router: Intent: semantic, Direction: both Vector Search: Found 3 seed nodes

Retrieved Context: ──────────────────────────────────────────────────────────

NervaPack Context Retrieval

File: src/auth/middleware.py

CLASS: AuthMiddleware (L15-L42)

... ──────────────────────────────────────────────────────────

╭────────────── NervaPack Token Efficiency ──────────────╮ │ Strategy Tokens Reduction │ │ Naive RAG (3 files) 12,840 100% (base) │ │ NervaPack 1,180 9.2% │ │ ─────────────────────────────────────────────────────────│ │ Tokens saved: 11,660 Reduction: 90.8% │ │ Cost saved (GPT-4o $2.50/1M): $0.0292 per query │ ╰───────────────────────────────────────────────────────────╯

---

nervapack sync [PATH] — Incremental update

Updates only the files that changed since the last ingest. Uses GitPython to diff the working tree.

nervapack sync .

A full ingest on a large project can take minutes. sync turns that into a 2–5 second surgical update per file. Re-parses changed files, batch-upserts new vectors, and saves the graph once at the end.

---

nervapack clean [OPTIONS] — Remove ingested data

Wipe graph data and start fresh. Use this when you have duplicate vectors, ingested the wrong directory, or need to reduce disk usage.

nervapack clean --vectors          # wipe ChromaDB only (chroma_db/)

nervapack clean --graph # delete graph.graphml only nervapack clean --history # clear query + graph history logs nervapack clean --all # everything above (keeps memory.db) nervapack clean --all --yes # skip confirmation (CI / scripts)

Never deleted by `clean`: memory.db — your agent memory is always safe.

Typical workflow after a bad ingest:

nervapack clean --all

nervapack ingest .

---

nervapack enrich [PATH] — Add semantic edges

Runs LLM doc-to-code binding on an already-ingested graph. Use this if you:

• Ran ingest without an LLM and want to add EXPLAINS edges now.
• Added new documentation and want to bind it without a full re-ingest.

nervapack enrich .                           # auto-detect LLM

nervapack enrich . --llm ollama --model llama3 nervapack enrich . --llm claude # shows cost estimate before proceeding

---

nervapack status [--detailed] — Graph health

nervapack status            # node/edge counts + unsynced files

nervapack status --detailed # full analytics: health score, language distribution, coverage

Health score (0–100) factors in documentation coverage, node connectivity, graph density, and edge diversity. A structural-only graph typically scores 30–40; after enrich it rises to 70–90.

---

nervapack visualize [OPTIONS] — Interactive HTML graph

nervapack visualize                           # basic visualization

nervapack visualize --enhanced # + real-time search + path finder nervapack visualize --enhanced --communities # + community detection (Louvain) nervapack visualize --output ~/my-graph.html # custom output path nervapack visualize --no-browser # generate without opening

Produces a standalone HTML file with no external dependencies — drag, zoom, search, find shortest paths between nodes.

---

nervapack explore TARGET [--hops N] — Focused subgraph

Extract and visualize the N-hop neighbourhood of a specific file, class, or function.

nervapack explore GraphBuilder --hops 2

nervapack explore src/auth/middleware.py --hops 1 nervapack explore "function:parse"

---

nervapack dependencies [FILE] — Import dependency analysis

Analyze file-level import chains, detect circular dependencies, and visualize the dependency graph.

nervapack dependencies                        # full project analysis

nervapack dependencies src/graph/builder.py # single file nervapack dependencies --no-cycles # skip cycle detection

---

`nervapack hotspots [