Upload configs/AGENTS.md with huggingface_hub
Browse files- configs/AGENTS.md +39 -0
configs/AGENTS.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 🧠 NeuralAI AGENTS.md (Intelligence Engine)
|
| 2 |
+
|
| 3 |
+
This is the primary instruction set for any agent working on the NeuralAI core.
|
| 4 |
+
|
| 5 |
+
## 🛠️ System Role
|
| 6 |
+
NeuralAI is the high-density intelligence backend. It provides the raw cognitive power, the "Neural-Brain" knowledge base, and the orchestrator logic that powers the NeuralLabs frontend.
|
| 7 |
+
|
| 8 |
+
## 📖 Mandatory Pre-Flight Protocol
|
| 9 |
+
**CRITICAL**: Before starting any task, the agent MUST:
|
| 10 |
+
1. Read the current Zo settings and user rules (`list_rules`).
|
| 11 |
+
2. Review the `MODEL_ALIGNMENT.md` to ensure output matches the v7.0 Expert persona.
|
| 12 |
+
3. Consult the `ORCHESTRATOR.md` for delegation patterns.
|
| 13 |
+
|
| 14 |
+
## 🌌 Current State (v7.1-alpha)
|
| 15 |
+
- **Neural-Brain**: An expanded, high-density knowledge graph spanning:
|
| 16 |
+
- **Physics**: Advanced Quantum Field Theory (Expert level).
|
| 17 |
+
- **Philosophy**: Platonic forms and metaphysical systems.
|
| 18 |
+
- **Geopolitics**: Multipolar global order analysis.
|
| 19 |
+
- **History & Nature**: From Ancient Civilizations to Human Evolution.
|
| 20 |
+
- **Architecture**: Transitioned to an orchestrator-led model using the Manager-Worker pattern via the `/zo/ask` API.
|
| 21 |
+
- **Hygiene**: All legacy checkpoints, `wandb` logs, and `from-scratch` remnants have been purged.
|
| 22 |
+
- **DPO Expansion**: Dataset v14 expanded with 10 new pairs focusing on debugging, logic, and multi-step reasoning.
|
| 23 |
+
|
| 24 |
+
## 🔗 Ecosystem Integration
|
| 25 |
+
- **Frontend**: NeuralAI is the intelligence source for **NeuralLabs** (`/home/workspace/Projects/NeuralLabs`).
|
| 26 |
+
- **Interface**: Communicates via the **Hybrid Link Gateway** implemented in NeuralLabs.
|
| 27 |
+
|
| 28 |
+
## 🎯 Active Goals
|
| 29 |
+
- Maintain expert-level accuracy in the Neural-Brain.
|
| 30 |
+
- Optimize orchestrator delegation for complex multi-step reasoning.
|
| 31 |
+
- Expand knowledge into remaining target domains (Modernity, Advanced Sociology, etc.).
|
| 32 |
+
- **Restore DPO Alignment**: Re-train or restore `checkpoints/dpo_model` to align with the `v13` dataset (249 pairs).
|
| 33 |
+
- **DPO v14 Batch**: Continue expanding v14 to reach 100+ high-quality reasoning pairs.
|
| 34 |
+
- **Voice Key Integration**: Configure `GEMINI_API_KEY` for the `neural-voice` service to enable Live S2S functionality.
|
| 35 |
+
|
| 36 |
+
## ⚠️ Web UI & Service Safety
|
| 37 |
+
- **UI Integrity:** The web interface for NeuralAI (`from-scratch/web_ui`) features a custom, high-fidelity Google-style UI. **DO NOT** attempt to "redesign", "polish", or replace the layout with generic templates.
|
| 38 |
+
- **API Endpoints:** The frontend relies on critical backend endpoints (`/api/auth/guest`, `/api/terminal/create`, `/api/memory`, `/api/files`, etc.). Modifying or deleting these in `neural_core_service.py` will cause 404/JSON parsing errors (like `Unexpected token '<', "<!doctype "... is not valid JSON`) in the UI.
|
| 39 |
+
- **Verification:** Always empirically test the live user service (`https://neuralai-deandrewharris.zocomputer.io`) using `curl` and verify JSON responses before claiming a fix is complete. Do not confuse `zo.space` routes with the NeuralAI user service.
|