
Unlike traditional coding agents that dump entire raw files into context windows (causing severe
Unlike traditional coding agents that dump entire raw files into context windows (causing severe VRAM OOMs) or get trapped in multi-turn exploratory shell loops (grep, find, cat), NeuroCode divides cognitive labor across the PC hardware boundary:
·
NeuroCode is a lightweight, heterogeneous neuro-symbolic framework and Model Context Protocol (MCP) server that enables small, local language models (1.5B–14B parameters) to fix multi-file software engineering bugs on consumer laptops (e.g., 4GB–8GB VRAM) without cloud API dependency or Out-of-Memory (OOM) crashes.
📌 Academic Reproducibility Notice:
For benchmark reproduction and evaluation datasets corresponding to the 35th IEEE/ACM ICPC 2027 (Submission #63) and the Elsevier Journal of Parallel and Distributed Computing (JPDC), please refer to frozen release tagv0.1.1. Themasterbranch represents the actively maintained multi-language production release.
NeuroCode natively parses and deterministically mutates code across 5 programming languages using in-memory Tree-sitter AST grammars:
.py).ts, .tsx).js, .jsx, .mjs, .cjs).go).rs)Unlike traditional coding agents that dump entire raw files into context windows (causing severe VRAM OOMs) or get trapped in multi-turn exploratory shell loops (grep, find, cat), NeuroCode divides cognitive labor across the PC hardware boundary:
SEARCH/REPLACE diff patches with zero exploratory token waste.NeuroCode was evaluated across 5 comprehensive benchmark tracks spanning real-world repository repair, standalone algorithm synthesis, multi-file cross-boundary retrieval, and low-level hardware telemetry.
| Benchmark Suite | Metric | Baseline / BM25 | NeuroCode (Ours) | Advantage |
|---|---|---|---|---|
| SWE-bench Lite ($N=292$) | Valid Diff Apply / Resolved | 0.0% (OOM on 4GB) / 0.0% | 41.4% apply / 9.5% resolved | Prevents OOM cliff; +23.9% apply over BM25 |
| HumanEval ($N=164$) | Pass@1 (Unit Test) | 80.5% | 86.0% (141/164) | +5.5% via syntax-aware graph repair |
| MBPP ($N=100$) | Pass@1 (Unit Test) | 81.0% | 87.0% (87/100) | +6.0% algorithmic verification |
| RepoBench-R ($N=150$) | Recall@1 / Token Budget | 18.0% (745 tokens) | 100.0% (428 tokens) | -42.6% tokens, perfect cross-file retrieval |
| Host Systems Telemetry | Active VRAM / Slice Latency | 14.2 GB (OOM) | 961.2 MB / 0.62 ms | 93.2% VRAM reduction, 0 OOMs |
Tested live on an everyday developer laptop (AMD Ryzen 7 7435HS + NVIDIA RTX 3050 Laptop GPU, 4.0 GB VRAM):
/dev/shm).NeuroCode provides an official stdio Model Context Protocol (MCP) server conforming to specification 2024-11-05. Connect NeuroCode directly to Claude Desktop, Cursor, Continue.dev, or VS Code!
neurocode_slice: In-memory CPG reachability slicing bounded strictly under token budget ($B \le 1,200$).neurocode_graft: Deterministic AST subtree grafting with automatic indentation alignment and optional test verification with auto-rollback.neurocode_trace: Sub-millisecond execution call-chain path tracing connecting functions and symbols.neurocode_map: Instant zero-token architecture flowchart (Mermaid.js) of the codebase.neurocode_impact: Structural blast radius inspection (all upstream callers and downstream callee invocations in <2 ms).neurocode_symbol: Sub-millisecond AST symbol lookup returning file locations, line spans, and callers.neurocode_validate_patch: In-memory pre-flight patch verification for syntax errors before writing to disk.neurocode_seeds: Static root-cause candidate entity discovery in $<2$ ms.neurocode_repair_ollama: Single-turn patch generation streaming to local Ollama daemon (http://localhost:11434).neurocode_hardware_health: Reports GPU VRAM headroom, CPU cores, and /dev/shm tmpfs zero-wear status.Add the following to your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json~/.config/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"neurocode": {
"command": "/absolute/path/to/neurocode/.venv/bin/neurocode-mcp",
"args": []
}
}
}Add to .cursor/mcp.json or your Cursor settings:
{
"mcpServers": {
"neurocode": {
"command": "neurocode-mcp",
"args": []
}
}
}Add to your ~/.continue/config.json:
{
"experimental": {
"modelContextProtocolServers": [
{
"name": "neurocode",
"command": "neurocode-mcp",
"args": []
}
]
}
}Install directly from the Visual Studio Marketplace:
code --install-extension DeepakR.neurocode-ai(Or download the .vsix binary from the v0.1.0 Release)
/dev/shm RAM health indicators.pip install neurocode-ai(Or install locally from source: git clone https://github.com/Arkz-Deepak/neurocode.git && cd neurocode && pip install -e .)
# Slices your codebase into a tight, bug-focused prompt under 1200 tokens
neurocode slice --repo /path/to/repo --issue "Fix ZeroDivisionError in matrix normalization" --budget 1200# Runs full repair using local Qwen2.5-Coder model via Ollama
neurocode repair --repo /path/to/repo \
--issue "Fix ZeroDivisionError in matrix normalization" \
--provider ollama \
--model qwen2.5-coder:7b \
--applyneurocode-copilot[email protected] / [email protected]paper_icpc_tool_demo/neurocode_icpc_demo.texpaper_elsevier_jss/neurocode_jss.tex@article{deepak2026neurocode,
title={NeuroCode: Budget-Constrained Heterogeneous Code-Graph Slicing for Local Software Repair},
author={Deepak, R.},
journal={IEEE Transactions on Software Engineering},
institution={Dhaanish Ahmed College of Engineering, Anna University},
year={2026},
url={https://github.com/Arkz-Deepak/neurocode}
}This project is licensed under the MIT License.
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add neurocode -- /absolute/path/to/neurocode/.venv/bin/neurocode-mcp{
"mcpServers": {
"neurocode": {
"args": [],
"command": "/absolute/path/to/neurocode/.venv/bin/neurocode-mcp"
}
}
}code --add-mcp '{"name":"neurocode","args":[],"command":"/absolute/path/to/neurocode/.venv/bin/neurocode-mcp"}'[mcp_servers.neurocode]
command = "/absolute/path/to/neurocode/.venv/bin/neurocode-mcp"Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/neurocode to learn what the "Neurocode" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
pip install neurocode-aiThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/neurocode)Nothing comparable is listed yet.
v1.3.0v1.3.0: Execution Path Tracing, Architecture Flowcharts, Test-Gated Self-Healing, and Go/Rust AST SupportRelease notesv1.2.0v1.2.0: AST Subtree Grafting & Multi-Language (TypeScript/JavaScript) SupportRelease notesv0.1.1NeuroCode v0.1.1: Native Binary Auto-ResolutionRelease notesv0.1.0NeuroCode v0.1.0: MCP Server & VS Code ExtensionRelease notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "neurocode" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.