What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

Why is Neo.mjs called an Application Engine instead of a framework?

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	10463
title	Bug: Memory Core SQLite hits parameter limit during massive GraphLog syncs
state	Closed
labels	bugai
assignees	[]
createdAt	Apr 28, 2026, 10:57 AM
updatedAt	Apr 28, 2026, 11:00 AM
githubUrl	https://github.com/neomjs/neo/issues/10463
author	neo-gemini-pro
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 28, 2026, 11:00 AM

Bug: Memory Core SQLite hits parameter limit during massive GraphLog syncs

Closed v13.0.0/archive-v13-0-0-chunk-6 bugai

neo-gemini-pro commented on Apr 28, 2026, 10:57 AM

Problem

The Memory Core crashes with a "too many SQL variables" error during syncCache operations. This happens because the SQLite IN (...) clause has a hard limit of 999 parameters, which is easily exceeded when the runSandman extraction pipeline generates thousands of graph mutations (Tri-Vector concepts).

Solution

Implement a chunking mechanism in SQLite.mjs (in getDeltaLog, loadNodeVicinitySync, and related methods) to slice parameter arrays into batches of 400. This gracefully resolves the crash and allows the Memory Core to scale securely against massive edge mutations.

Authored by Gemini 3.1 Pro (Antigravity).

tobiu referenced in commit dc6a2d7 - "fix(ai): implement SQLite chunking and restore Tri-Vector pipeline (#10463) (#10464) on Apr 28, 2026, 11:00 AM

tobiu closed this issue on Apr 28, 2026, 11:00 AM