Universal Context Engine

NEURON CORE™

The Universal Persistent Memory Layer for AI Agents

A local-first, zero-dependency context engine (~10.46MB) that bridges multi-gigabyte codebases to LLM reasoning windows via the Model Context Protocol (MCP).

bash — shell session
$ cargo install neuron-core && neuron watch
[+] Compiled neuron-core production targets (v1.0.0-mcp)
[+] Added local symlink binary to user PATH
[✓] Watching workspace for structural signature mutations...

Binaries are published automatically via GitHub Actions on every tagged release. View all releases →

Model Context Protocol

MCP Tool Capabilities

5 native tools exposed over JSON-RPC 2.0 stdio — zero configuration required

Neuron Core MCP Server
get_project_context
Dense, deduplicated codebase map for agent reasoning windows
search_symbols
Fast SQLite FTS5 full-text lookup across all indexed symbols
get_impact_graph
Blast radius tracer — cascading downstream mutation impact
get_symbol_info
Exact definition snippet + semantic intent for any symbol
get_file_content
16 KB sanitized file explorer — inspect any file before editing
JSON-RPC 2.0 stdio transport Cursor compatible Claude Code compatible Copilot compatible

Localhost Perimeter Boundary

Zero-Cloud Local Pipeline

Local Workspaces
Local Storage
Local Source & Project Files
neuron.exe via mcp
Stdio Pipe / JSON-RPC
RAM-Only Deduplication & Sanitization
Secure Payload
Local Agent
Cursor / Claude / Copilot

*No raw files leave your machine. Only stripped structures, signatures, and sanitised text are emitted to reasoning engines.

Comparative Security Matrix

Core Agent Vulnerabilities vs. Neuron Handling

Raw Agent Bottlenecks

1. Context Saturation

Flat directory parsing drops full file content into LLM windows, wasting valuable tokens on repetitive boilerplates.

2. Cross-Project Blind Spots

Agents lack context of sibling projects or packages, making signature updates extremely error-prone.

3. Sensitive Data Leaks

Unprocessed logs, database connections, and environment files leak directly to commercial cloud providers.

4. Autonomous Resource Loops

Without monitoring, agents repeatedly run identical compiler routines and cycle through file reversions indefinitely.

Neuron Resolution Engine

1. Deduplication Stream Compiler

Filters project assets dynamically, keeping structure and signature definitions while stripping token bloat.

2. Cross-Project Dependency Linker

Maintains child-parent dependency trees with instant notification warnings when upstream APIs modify signatures.

3. Local Sanitization pipeline

Intercepts database queries and outputs to scrub passwords, raw keys, and proprietary tokens before payload delivery.

4. Self-Healing Loop Guards

Monitors system changes and blocks recurring file modifications. Instantly alerts user if loop count crosses threshold.

Functional Capabilities

Salient Features Dashboard

Native MCP Host

Provides stdin/stdout communication mapping perfectly to the standard Model Context Protocol. Exposes local context directly to agent plugins.

AST Symbol Indexing

Understands project structure at syntax level. Maps classes, structures, and declarations into SQLite index for sub-millisecond retrieval.

Multi-Project Linker

Establish topological linkages. Track parent-child workspace relationships and trace cascades when signature hashes change.

Inline Sanitization

Auto-detection engine that intercepts outputs and cleans credentials, authentication endpoints, and SSH keys in real-time.

Loop Guard Integration

Self-healing safety watch loops. Flags repetitive compile or command loops to prevent token waste and infinity execution states.

Auto-Maintenance

Automated database compression and log rotation. Evicts dead process locks and runs vacuum routines on database files.

Commercial Operations

Dual-Licensing & Enterprise Exemption

Neuron Core is committed to open source under AGPLv3. For proprietary environments, closed-source products, or custom integrations, we offer commercial licenses.

AGPLv3 Copyleft

Community Edition

Free

For developers, educators, and open-source contributors. Any derivative works must remain fully open-source under copyleft terms.

  • Local Context Indexing
  • Standard CLI Tools
  • Community Support
Popular
Proprietary Exemption

Team License

$199/month

For small teams and startups (up to 25 developer seats) embedding context tools into private, proprietary workflows.

  • 25 Developer Seats
  • Proprietary Use Exemption
  • Email Support (24h SLA)
Custom SLAs & OEM

Enterprise & OEM

Custom

For large organizations, compliance-driven teams, and commercial vendors looking to embed Neuron Core as an OEM component in proprietary SaaS/IDE platforms.

  • Unlimited Developer Seats
  • Custom Integration Support
  • Dedicated Enterprise SLAs
Contact Enterprise Operations (enterprise@ai-neuron.org)