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.

Neo.mjs - Self-Evolving Software Organism

Frontmatter

title	docs: A2A Contextual Bridge Protocol (#9908)
author	tobiu
state	Merged
createdAt	Apr 12, 2026, 12:36 PM
updatedAt	Apr 12, 2026, 12:39 PM
closedAt	Apr 12, 2026, 12:39 PM
mergedAt	Apr 12, 2026, 12:39 PM
branches	`dev` ← `agent/9908-a2a-contextual-bridge`
url	https://github.com/neomjs/neo/pull/9909

Merged

tobiu commented on Apr 12, 2026, 12:36 PM

Fat Ticket Summary

Resolves #9908

This PR integrates the A2A Contextual Bridge Protocol natively into the Swarm's operational mandates. Key components introduced:

End-of-Session Horizon Scan: Agents automatically assess successor tasks.
The Telemetry Payload: Follow-up tickets automatically receive the 'Origin Session ID' payload.
The Ingestion Mandate: New Agent threads prioritize checking the local SQLite Memory Core for a provided origin session id to immediately reconstruct systemic context before parsing source files.

This effectively mitigates Zero-State Amnesia without introducing new tracking servers.

tobiu commented on Apr 12, 2026, 12:37 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ # PR Review Summary

Status: Approved

Excellent work! The formalization of the A2A Contextual Bridge Protocol elegantly solves the 'Zero-State Amnesia' problem and vastly improves the long-term strategic coherence of the Swarm.

📊 Evaluation Metrics

[ARCH_ALIGNMENT]: 100 - Perfect alignment. Integrates directly into agent mandates without adding overhead.

[CONTENT_COMPLETENESS]: 100 - Both AGENTS.md and AGENTS_STARTUP.md updated comprehensively.

[EXECUTION_QUALITY]: 100 - Clean markdown additions, correctly positioned.

[PRODUCTIVITY]: 100 - Completely solves the target issue #9908.

[IMPACT]: 85 - Extremely high impact on long-running swarm performance and contextual awareness.

[COMPLEXITY]: 20 - Small code delta, conceptually robust.

[EFFORT_PROFILE]: Quick Win - High ROI for low LOC addition.

🕸️ Context & Graph Linking

Target Epic / Issue ID: Resolves #9908

Related Graph Nodes: A2A-Bridge-Protocol, Memory-Core

🧠 Graph Ingestion Notes

[RETROSPECTIVE]: The A2A Contextual Bridge Protocol establishes a critical feedback loop, allowing sequential AI swarm iterations to instantly fetch rich architectural blueprints and topological boundaries directly from the local SQLite Memory Core, simply by retrieving an Origin Session ID from follow-up tickets.

📋 Required Actions

To proceed with merging, please address the following:

None required. PR is approved and ready for Squash Merge.

This is ready for a human reviewer to Squash Merge when appropriate!