Native forClaude Code

Your team uses Claude Code? Now it remembers your codebase.

Persistent neural memory for AI agents. Local-first synapse layer. Works with every IDE your team already uses. 100% local, no telemetry.

<1sQuery Latency
65.6×Token Reduction
100%Gold-File Recall
Auto-provisionedFree Tier
Pipeline

How it works

Three steps, then it runs forever on every git commit via `neuralmind init-hook .`

01

Index

tree-sitter parses your codebase into a graph — functions, classes, imports, comments. Ten languages, zero config. TurboVec compresses vectors 4-bit.

~15 min
02
🧠

Query

Your agent asks a question. Progressive L0–L3 disclosure pulls exactly the right amount of context. Sub-second on a 1,486-node repo.

<1s
03
🔮

Remember

A Hebbian synapse layer learns co-activations from how you actually use the codebase. Budget-neutral, runs in the background.

Forever
Measured, not marketed

Benchmarks

Every number is produced by CI on every commit. Run neuralmind benchmark . to verify.

Query Latency

0.81s

on 1,486-node repo (TurboVec)

Token Reduction

63.6×

on live production codebase

Gold-File Recall

100%

on public benchmark (requests, click)

Setup time

~15 min

one CLI command

Ongoing overhead

~0

post-commit hook auto-rebuilds

Plus one labeled field report (measured with the CLI, not CI-gated): 48.8× on a real ~9,300-node TypeScript SaaS platform, through a major rebuild. Read the field report →

See it in 30 seconds

Clone the repo, run the demo, get numbers on YOUR codebase. Then email the output to [email protected] with your team size for a free full spend model.

Run the demo
Don't take our word for it

Prove it in 5 minutes

Every claim on this site reproduces from a fresh clone. No account, no signup, no cloud.

1

30-second demo on a fresh clone

One script: isolated venv, index build, three real questions against the bundled fixture project.

$ git clone https://github.com/dfrostar/neuralmind && cd neuralmind

$ bash scripts/demo.sh

2

Then measure YOUR codebase

The fixture is tiny (~500 lines, ~5.5×). Real repos consistently hit 12–50× on the same pipeline — run the benchmark on your own code and read your own number. We measured 65.6× on a 1,486-node production codebase (Level2Logic).

$ pip install neuralmind

$ cd /path/to/your-repo

$ neuralmind build .

$ neuralmind benchmark .

3

Verify what you installed

Check the SBOM, release integrity, and audit trail on the security page — and the full production before/after data on the effectiveness page.

What the demo prints (bundled fixture)

Q: How does authentication work in this codebase?

naive = 4,736 tok neuralmind = 829 tok reduction = 5.7×

Average reduction: 5.5× across 3 queries

Avg context size: 859 tokens (vs 4,736 naive)

Small fixture, small multiplier — by design. It runs in CI on every commit as a regression gate. The 12–50× headline comes from real repos; your own number is one neuralmind benchmark . away.

The business case

The savings are free. The tier is control.

Dollar figures below are modeled, with published assumptions — the free assessment runs the same model in your numbers.

For the CFO

The savings are free

  • The 65.6× token compression ships in the free MIT core — the savings cost nothing, and you can measure them on your own repo in ~15 minutes.
  • Modeled at 30 code questions per developer per day, a 50-developer team gets back ~$310/mo on inference alone (at 65.6×).
  • The bigger line is time: ~$1,650/mo per 50-dev team recovered from context-limit thrashing and re-prompting, at a $50/hr fully-loaded rate.
  • Sub-second queries (0.81s) mean no more waiting 8+ seconds per question. That compounds across every developer, every day.
For the CTO

Fewer wrong answers, faster teams

  • 100% gold-file recall on the public benchmark (requests, click).
  • Team dashboard shows synapse memory health, ingestion status, savings, latency trends — all read-only, all local.
  • Self-documenting code: DocEvolver finds undocumented methods and evolves JSDoc that actually improves retrieval.
  • 100% local with zero code egress — verifiable on the wire. Works with the agents you already run: Claude Code, Cursor, Cline, any MCP agent. No rip-and-replace.
Capabilities

Features

Everything persistent memory should be — and nothing it shouldn't.

TurboVec

Sub-Second Retrieval

TurboVec backend: 0.81s per query on a 1,486-node repo. ChromaDB-free, 8× smaller index vectors (4-bit quantized).

🧬Budget-neutral

Hebbian Synapse Layer

Associations strengthen when you use them together — like a real hippocampus. Budget-neutral, no cost until it activates.

🔄63.6×

Progressive L0–L3 Disclosure

Retrieves exact bytes needed. Never pastes the whole repo. 65.6× compression measured on a 241-node production codebase.

📊New

Team Dashboard

Read-only web UI: synapse memory, ingestion status, savings, latency trends, community distribution, recent queries.

🔬Evolution

Self-Documenting Code

DocEvolver finds undocumented methods, generates JSDoc variants, evolves them against retrieval fitness. Winning variants patched back into source.

🧠N-13

Business-Context Synapse Seeding

seed_from_documents() builds deterministic, LLM-free associations between business documents (decisions, SOPs, meeting notes) and your code graph. Adjacency-matched compounds, title-reference cross-links.

🌐Universal

MCP Server

First-class MCP integration. Works with Claude Code, Cursor, Cline, Continue, and any MCP-compatible agent.

🎯10 langs

Ten-Language Code Graph

tree-sitter indexes Python, TypeScript, Go, Rust, Java, C, C++, C#, Ruby, and PHP out of the box.

🗑️Auto-recover

Tool Output Recovery

Caches dropped tool output from context windows. When your agent forgets, neuralmind remembers.

🆓v1.7.0

Free Tier — Auto-Provisioned

`pip install neuralmind && neuralmind wakeup .` writes the license on first run. Zero signup wall. Default tier is "free", identity auto-issued.

🔒Secure

100% Local Engine

NeuralMind makes zero network calls of its own — only the minimal relevant slice ever reaches your AI tool, never your whole codebase. No telemetry.

🚀v2.0.0

One-Command Project Init

`neuralmind init` auto-detects project structure, installs hooks, builds the index — all at once. Your project is ready in seconds.

🛡️v2.0.0

Compliance Annotation Engine

Scans code for `Compliance:` annotations, maps them to CMMC 2.0 / NIST SP 800-53 controls. Ingest CMMC assessment guides, export audit reports, gate CI on annotation health.

📤v2.0.0

Audit Export & CI/CD Check

`neuralmind export --audit` produces flat compliance reports (CSV/JSON) for evidence submission. `neuralmind ci-check` gates builds on annotation health.

🤖v2.0.0

Compliance Report MCP Tool

`neuralmind_compliance_report` surfaces live compliance stance from any MCP-compatible agent. Ask "are we compliant on access control?" and get an answer grounded in real annotations.

Free assessment

See your savings before you spend a dollar

NeuralMind is open source and free (MIT) — pip install neuralmind and you have the whole product. For teams evaluating at scale, we run a free AI-spend assessment: measured on your code, modeled in your numbers, no obligation.

What the assessment gives you

  • A measured token-reduction ratio on one of your own repos — run locally, nothing leaves your machine
  • A spend model in your numbers: per-seat subscriptions, usage-based API (OpenRouter, Bedrock, Vertex), and self-hosted GPU
  • A productivity model: hours lost to context-limit thrashing and re-prompting, valued at your fully-loaded rate
  • An honest fit verdict — if your workload is generation-heavy or caching already covers you, we say so

The software is MIT-licensed and free. Commercial support for deployment and integration is available.

FAQ

Common questions

Stop paying for tokens you don't use.

One command to install. Seconds to verify. Your agent remembers what matters.

pip install neuralmindGet started
No cloud callsCI-verified100% local