8 changed files with 916 additions and 8 deletions
--- a/assets/ai-optimizer/CRON_EXECUTION_PROMPT.md
+++ b/assets/ai-optimizer/CRON_EXECUTION_PROMPT.md
@@ -0,0 +1,203 @@
+# AI Model Optimization Cron Job - EXECUTION PROMPT
+
+**When this cron runs, follow these instructions exactly:**
+
+---
+
+## Your Role
+
+You are an AI model optimization agent. Your task is to find the best ollama/llama.cpp configuration for maximum context size and hardware utilization.
+
+**Hardware:**
+- 2× AMD MI50 GPUs (32GB VRAM each, 64GB total)
+- 128GB system RAM
+- ROCm: HSA_OVERRIDE_GFX_VERSION=9.0.6, HIP_VISIBLE_DEVICES=0,1
+
+---
+
+## File Locations
+
+```
+STATE: /opt/data/infra/assets/ai-optimizer/state.json
+RESULTS: /opt/data/infra/assets/ai-optimizer/results.csv
+INFRA_REPO: /opt/data/infra
+```
+
+---
+
+## Model Queues
+
+### GPU Track (Coding - prioritize speed + context on GPU)
+1. `devstral-small-2:24b`
+2. `qwen2.5-coder:32b`
+3. `codellama:34b-instruct`
+
+### RAM Track (Knowledge - prioritize max context)
+1. `qwen2.5:72b`
+2. `nemotron-3-nano:30b`
+3. `mixtral:8x7b-instruct`
+
+---
+
+## Context Steps (in order)
+```
+[32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680]
+```
+
+---
+
+## Each Run - Step by Step
+
+### 1. Read State
+```bash
+cd /opt/data/infra
+cat assets/ai-optimizer/state.json
+```
+
+### 2. Determine Next Test
+- Read `track` (gpu or ram)
+- Read `current_model` from queue at `model_index`
+- Read `current_config` for parameters to test
+- Select next context step from `context_steps` based on `phase`
+
+### 3. Pull Model (if needed)
+```bash
+docker exec ollama ollama list | grep -q "<model>" || docker exec ollama ollama pull <model>
+```
+
+### 4. Create Test Modelfile
+```bash
+docker exec ollama bash -c "cat <<EOF > /root/.ollama/test_${model}.modelfile
+FROM ${model}
+PARAMETER num_ctx ${current_config.num_ctx}
+PARAMETER num_gpu ${current_config.num_gpu}
+PARAMETER flash_attn ${current_config.flash_attn}
+PARAMETER num_predict 4096
+PARAMETER num_keep 1024
+PARAMETER repeat_penalty 1.1
+EOF"
+
+docker exec ollama ollama create test-model -f /root/.ollama/test_${model}.modelfile
+```
+
+### 5. Run Benchmark
+```bash
+# Warm up
+docker exec ollama ollama run test-model "Hello" > /dev/null
+
+# Coding prompt
+START=$(date +%s%N)
+docker exec ollama ollama run test-model "Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints."
+END=$(date +%s%N)
+
+# Calculate tokens/sec from output
+```
+
+### 6. Measure VRAM (if possible)
+```bash
+# Try host first
+rocm-smi --showmeminfo vram 2>/dev/null || \
+# Try via docker
+docker exec --privileged ollama rocm-smi --showmeminfo vram 2>/dev/null || \
+# Fallback
+echo "VRAM measurement unavailable"
+```
+
+### 7. Record Results
+- Parse tokens/sec from ollama output
+- Record VRAM/RAM usage
+- Determine if this is best config so far for this model
+- Update `best_configs` if tokens/sec improved or context increased
+
+### 8. Update State
+```python
+# Logic:
+if test_successful:
+    if context_step < max_reached:
+        phase = "context_scaling"
+        current_config.num_ctx = next_context_step
+    else:
+        # Move to next model
+        model_index += 1
+        phase = "context_scaling"
+        current_config.num_ctx = context_steps[0]
+else:
+    # OOM or error - record last good as best
+    best_configs[track][current_model] = last_good_config
+    model_index += 1
+    phase = "context_scaling"
+```
+
+### 9. Commit to Repo
+```bash
+cd /opt/data/infra
+git add assets/ai-optimizer/
+git commit -m "ai-optimizer: tested ${model} at ${num_ctx} ctx - ${status}"
+git push origin master
+```
+
+### 10. Matrix Notification (if available)
+```python
+import os
+if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"):
+    # Send notification to Matrix room
+    # Room ID from env or config
+    pass
+# Else: silent
+```
+
+---
+
+## Stop Conditions
+
+1. All models in both queues have `best_configs` recorded
+2. Manual intervention needed (error in state.json `error` field)
+3. No progress for 3 consecutive runs (stuck)
+
+---
+
+## Error Handling
+
+If any step fails:
+1. Log error to state.json: `"error": {"message": "...", "timestamp": "..."}`
+2. Do NOT increment model_index (retry next run)
+3. Commit state with error field
+4. Exit gracefully
+
+---
+
+## Important Notes
+
+- **No num_parallel**: Do not use this parameter
+- **Two tracks**: Complete GPU track first, then RAM track
+- **Backend**: Start with ollama, llama.cpp testing is optional (requires uncommenting in compose.yml)
+- **Host access**: Some commands need host - use docker exec or SSH if available
+- **Ask before deploy**: If config changes needed in NixOS modules, show diff and wait for user confirmation before `nh os switch`
+
+---
+
+## Example State Transitions
+
+**Start:**
+```json
+{"track": "gpu", "model_index": 0, "current_model": "devstral-small-2:24b", "current_config": {"num_ctx": 32768, ...}}
+```
+
+**After successful test at 32k:**
+```json
+{"track": "gpu", "model_index": 0, "current_model": "devstral-small-2:24b", "current_config": {"num_ctx": 65536, ...}}
+```
+
+**After OOM at 131k:**
+```json
+{
+  "track": "gpu",
+  "model_index": 1,
+  "current_model": "qwen2.5-coder:32b",
+  "best_configs": {
+    "gpu": {
+      "devstral-small-2:24b": {"num_ctx": 98304, "num_gpu": 99, "tokens_per_sec": 11.2}
+    }
+  }
+}
+```
--- a/assets/ai-optimizer/CRON_JOB_DRAFT.md
+++ b/assets/ai-optimizer/CRON_JOB_DRAFT.md
@@ -0,0 +1,283 @@
+# AI Model Optimization Cron Job
+
+**Goal:** Find optimal configurations for maximum context size with full hardware utilization.
+
+**Hardware:**
+- 2× AMD MI50 GPUs (32GB VRAM each, 64GB total)
+- 128GB system RAM
+- ROCm: HSA_OVERRIDE_GFX_VERSION=9.0.6, HIP_VISIBLE_DEVICES=0,1
+
+---
+
+## Model Queue
+
+### GPU-Optimized (Coding - prioritize speed + context on GPU)
+1. `devstral-small-2:24b` - Best coding model
+2. `qwen2.5-coder:32b` - Strong coder, fits on GPU+offload
+3. `codellama:34b-instruct` - Legacy but solid
+
+### RAM-Optimized (Knowledge - prioritize max context, accept slower)
+1. `qwen2.5:72b` - Best knowledge, needs heavy offload
+2. `nemotron-3-nano:30b` - Good general knowledge
+3. `mixtral:8x7b-instruct` - MoE, efficient for knowledge
+
+---
+
+## Optimization Strategy
+
+**Two separate tracks:**
+
+### Track A: GPU-Focused (Coding)
+```
+Baseline: num_ctx=32768, num_gpu=99, flash_attn=true
+Steps:
+1. Increase context: 32k → 65k → 98k → 131k → 163k
+2. At each step, verify VRAM usage < 60GB (leave headroom)
+3. If OOM: reduce num_gpu until stable, record best
+4. Measure tokens/sec - if < 5 tok/s, consider context too high
+```
+
+### Track B: RAM-Focused (Knowledge)
+```
+Baseline: num_ctx=65536, num_gpu=50, flash_attn=true
+Steps:
+1. Increase context: 65k → 131k → 200k → 262k → 327k
+2. Allow heavy RAM offload (system RAM up to 100GB)
+3. If OOM: reduce context or num_gpu
+4. Speed less critical - focus on max stable context
+```
+
+---
+
+## Backend-Specific Configs
+
+### Ollama (Modelfile parameters)
+```
+PARAMETER num_ctx <value>
+PARAMETER num_gpu <layers>
+PARAMETER flash_attn true/false
+PARAMETER num_predict 4096
+PARAMETER num_keep 1024
+PARAMETER repeat_penalty 1.1
+```
+
+### Llama.cpp (CLI flags)
+```
+--ctx-size <value>
+--n-gpu-layers <layers>
+--flash-attn on/off
+--n-predict 4096
+--batch-size 4096
+--ubatch-size 512
+--cache-type-k f16
+--cache-type-v f16
+--split-mode layer
+--no-mmap
+```
+
+---
+
+## Host Test Instructions
+
+**The cron runs inside the hermes container. Some tests require host access:**
+
+### 1. VRAM Monitoring (HOST)
+```bash
+# Run on host to check VRAM usage during/after benchmark
+sudo rocm-smi --showmeminfo vram
+
+# Or via docker exec if rocm-smi available in container
+docker exec --privileged ollama rocm-smi --showmeminfo vram
+```
+
+### 2. Running Ollama Benchmarks (CONTAINER)
+```bash
+# Pull model
+docker exec ollama ollama pull <model>
+
+# Create custom modelfile
+docker exec ollama bash -c 'cat <<EOF > /root/.ollama/test.modelfile
+FROM <model>
+PARAMETER num_ctx 65536
+PARAMETER num_gpu 99
+PARAMETER flash_attn true
+EOF'
+
+# Create model from modelfile
+docker exec ollama ollama create test-model -f /root/.ollama/test.modelfile
+
+# Run benchmark (warm model first)
+docker exec ollama ollama run test-model "Write a Python async context manager with exponential backoff"
+
+# Cleanup
+docker exec ollama ollama rm test-model
+```
+
+### 3. Running Llama.cpp Benchmarks (CONTAINER - needs llama.cpp container)
+```bash
+# Uncomment llama_cpp_devstral in compose.yml first
+# Then rebuild: sudo nh os switch --flake .#lazyworkhorse
+
+# Test via HTTP API
+curl http://localhost:8300/v1/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "devstral-2-small-llama_cpp",
+    "prompt": "Write a Python function",
+    "max_tokens": 100
+  }'
+```
+
+### 4. Deploying Changes (HOST via ai-worker)
+```bash
+# After optimization, commit results
+cd /home/ai-worker/infra
+git add assets/ai-optimizer/
+git commit -m "ai-optimizer: new best config for <model>"
+git push
+
+# If config changes needed in ollama_init_custom_models.nix:
+# 1. Edit the file
+# 2. nixpkgs-fmt .
+# 3. Show diff to user
+# 4. Wait for confirmation
+# 5. sudo nh os switch --flake .#lazyworkhorse
+```
+
+### 5. Accessing Host from Hermes Container
+```bash
+# SSH to host as ai-worker (key should be mounted)
+ssh -i /path/to/key ai-worker@host.docker.internal
+
+# Or via docker socket if mounted
+# (not recommended for security)
+```
+
+---
+
+## Benchmark Prompts
+
+### Coding (Track A)
+```
+"Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints and error handling."
+```
+
+### Knowledge (Track B)
+```
+"Explain the complete memory hierarchy in modern GPUs, from registers through L1/L2 caches to VRAM, and how data moves between them during matrix multiplication. Include bandwidth considerations for each level."
+```
+
+### Measurement
+- Tokens per second (generation speed)
+- Time to first token (latency)
+- VRAM usage (via rocm-smi)
+- System RAM usage (via free -h)
+- Context success (did it complete without OOM?)
+
+---
+
+## State File Structure
+
+`/opt/data/infra/assets/ai-optimizer/state.json`
+
+```json
+{
+  "track": "gpu",
+  "current_model": "devstral-small-2:24b",
+  "model_index": 0,
+  "phase": "context_scaling",
+  "backend": "ollama",
+  "current_config": {
+    "num_ctx": 65536,
+    "num_gpu": 99,
+    "flash_attn": true
+  },
+  "best_configs": {
+    "gpu": {
+      "devstral-small-2:24b": {
+        "backend": "ollama",
+        "num_ctx": 131072,
+        "num_gpu": 99,
+        "flash_attn": true,
+        "tokens_per_sec": 12.5,
+        "vram_used_gb": 58.2,
+        "tested_at": "2026-04-28T17:00:00Z"
+      }
+    },
+    "ram": {}
+  },
+  "completed_models": [],
+  "gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
+  "ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"]
+}
+```
+
+---
+
+## Results CSV
+
+`/opt/data/infra/assets/ai-optimizer/results.csv`
+
+```csv
+timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
+2026-04-28T17:00:00Z,gpu,devstral-small-2:24b,ollama,context_scaling,65536,99,true,15.2,52.1,18.4,success,false
+```
+
+---
+
+## Cron Job Flow
+
+```
+1. Read state.json
+2. If both queues empty → STOP (all models tested)
+3. Select next model from current track queue
+4. Pull model if needed (docker exec ollama ollama pull)
+5. Create Modelfile / llama.cpp config with current test params
+6. Run benchmark (both prompts)
+7. Measure: tokens/sec, VRAM (rocm-smi), RAM (free -h)
+8. If successful:
+   - Increase context (next step)
+   - Update current_config in state
+9. If OOM/error:
+   - Record last good config as best_configs[track][model]
+   - Move to next model in queue
+10. Update state.json
+11. Append to results.csv
+12. Git commit + push to /opt/data/infra
+13. Send Matrix notification if available, else silent
+```
+
+---
+
+## Matrix Notification (Optional)
+
+```python
+# If matrix credentials available in environment
+if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"):
+    # Send completion notification
+    # Room: !ai-optimizer:lazyworkhorse.net (or similar)
+    pass
+# Else: silent, just commit
+```
+
+---
+
+## Files to Create
+
+```
+/opt/data/infra/assets/ai-optimizer/
+├── state.json           # Current progress
+├── results.csv          # All test results
+├── best_configs.json    # Final best configs (human-readable)
+└── CRON_JOB_DRAFT.md    # This file
+```
+
+---
+
+## Notes
+
+- **No num_parallel**: Removed to avoid limiting other settings
+- **Two tracks**: GPU (coding/speed) vs RAM (knowledge/context)
+- **Both backends**: Test ollama first, then llama.cpp if available
+- **Host tests**: rocm-smi must run on host or privileged container
+- **Deploy**: ai-worker has sudo for nh/nixos-rebuild, must ask user first
--- a/assets/ai-optimizer/results.csv
+++ b/assets/ai-optimizer/results.csv
@@ -0,0 +1 @@
+timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
--- a/assets/ai-optimizer/state.json
+++ b/assets/ai-optimizer/state.json
@@ -0,0 +1,21 @@
+{
+  "track": "gpu",
+  "current_model": "devstral-small-2:24b",
+  "model_index": 0,
+  "phase": "context_scaling",
+  "backend": "ollama",
+  "current_config": {
+    "num_ctx": 32768,
+    "num_gpu": 99,
+    "flash_attn": true
+  },
+  "best_configs": {
+    "gpu": {},
+    "ram": {}
+  },
+  "completed_models": [],
+  "gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
+  "ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"],
+  "context_steps": [32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680],
+  "last_updated": "2026-04-28T17:00:00Z"
+}
--- a/flake.lock
+++ b/flake.lock
@@ -23,6 +23,38 @@
        "type": "github"
      }
    },
+    "argononed": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1729566243,
+        "narHash": "sha256-DPNI0Dpk5aym3Baf5UbEe5GENDrSmmXVdriRSWE+rgk=",
+        "owner": "nvmd",
+        "repo": "argononed",
+        "rev": "16dbee54d49b66d5654d228d1061246b440ef7cf",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nvmd",
+        "repo": "argononed",
+        "type": "github"
+      }
+    },
+    "argononed_2": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1729566243,
+        "narHash": "sha256-DPNI0Dpk5aym3Baf5UbEe5GENDrSmmXVdriRSWE+rgk=",
+        "owner": "nvmd",
+        "repo": "argononed",
+        "rev": "16dbee54d49b66d5654d228d1061246b440ef7cf",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nvmd",
+        "repo": "argononed",
+        "type": "github"
+      }
+    },
    "flake-compat": {
      "flake": false,
      "locked": {
@@ -37,6 +69,36 @@
        "url": "https://git.lix.systems/lix-project/flake-compat/archive/main.tar.gz"
      }
    },
+    "flake-compat_2": {
+      "locked": {
+        "lastModified": 1767039857,
+        "narHash": "sha256-vNpUSpF5Nuw8xvDLj2KCwwksIbjua2LZCqhV1LNRDns=",
+        "owner": "edolstra",
+        "repo": "flake-compat",
+        "rev": "5edf11c44bc78a0d334f6334cdaf7d60d732daab",
+        "type": "github"
+      },
+      "original": {
+        "owner": "edolstra",
+        "repo": "flake-compat",
+        "type": "github"
+      }
+    },
+    "flake-compat_3": {
+      "locked": {
+        "lastModified": 1767039857,
+        "narHash": "sha256-vNpUSpF5Nuw8xvDLj2KCwwksIbjua2LZCqhV1LNRDns=",
+        "owner": "edolstra",
+        "repo": "flake-compat",
+        "rev": "5edf11c44bc78a0d334f6334cdaf7d60d732daab",
+        "type": "github"
+      },
+      "original": {
+        "owner": "edolstra",
+        "repo": "flake-compat",
+        "type": "github"
+      }
+    },
    "home-manager": {
      "inputs": {
        "nixpkgs": [
@@ -70,11 +132,11 @@
        "pre-commit-hooks": "pre-commit-hooks"
      },
      "locked": {
-        "lastModified": 1774721317,
-        "narHash": "sha256-KS0ElyhZKdUFcfaxfwid3yi2Id3EP9i+dGL16/wx1T8=",
+        "lastModified": 1777373577,
+        "narHash": "sha256-K0sXr8tRA9L1FGE8Khl42NR+DmZOY9gNYCP8ljX7TAo=",
        "ref": "main",
-        "rev": "d0190cff6f2314cc1c727ff113aea20e086f4bcc",
-        "revCount": 19103,
+        "rev": "faaa14a303dabc6309a52cc8e5eba86f9e29ccaf",
+        "revCount": 19152,
        "type": "git",
        "url": "https://git.lix.systems/lix-project/lix"
      },
@@ -144,6 +206,130 @@
        "type": "github"
      }
    },
+    "nixos-images": {
+      "inputs": {
+        "nixos-stable": [
+          "nixos-raspberrypi",
+          "nixpkgs"
+        ],
+        "nixos-unstable": [
+          "nixos-raspberrypi",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1747747741,
+        "narHash": "sha256-LUOH27unNWbGTvZFitHonraNx0JF/55h30r9WxqrznM=",
+        "owner": "nvmd",
+        "repo": "nixos-images",
+        "rev": "cbbd6db325775096680b65e2a32fb6187c09bbb4",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nvmd",
+        "ref": "sdimage-installer",
+        "repo": "nixos-images",
+        "type": "github"
+      }
+    },
+    "nixos-images_2": {
+      "inputs": {
+        "nixos-stable": [
+          "nixos-uconsole",
+          "nixos-raspberrypi",
+          "nixpkgs"
+        ],
+        "nixos-unstable": [
+          "nixos-uconsole",
+          "nixos-raspberrypi",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1747747741,
+        "narHash": "sha256-LUOH27unNWbGTvZFitHonraNx0JF/55h30r9WxqrznM=",
+        "owner": "nvmd",
+        "repo": "nixos-images",
+        "rev": "cbbd6db325775096680b65e2a32fb6187c09bbb4",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nvmd",
+        "ref": "sdimage-installer",
+        "repo": "nixos-images",
+        "type": "github"
+      }
+    },
+    "nixos-raspberrypi": {
+      "inputs": {
+        "argononed": "argononed",
+        "flake-compat": "flake-compat_2",
+        "nixos-images": "nixos-images",
+        "nixpkgs": [
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1773704510,
+        "narHash": "sha256-Kq0WPitNekYzouyd8ROlZb63cpSg/+Ep2XxkV0YlABU=",
+        "owner": "nvmd",
+        "repo": "nixos-raspberrypi",
+        "rev": "b5c77d506bed55250a4642ce6c8b395dd29ef06b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nvmd",
+        "ref": "v1.20260317.0",
+        "repo": "nixos-raspberrypi",
+        "type": "github"
+      }
+    },
+    "nixos-raspberrypi_2": {
+      "inputs": {
+        "argononed": "argononed_2",
+        "flake-compat": "flake-compat_3",
+        "nixos-images": "nixos-images_2",
+        "nixpkgs": [
+          "nixos-uconsole",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1773704510,
+        "narHash": "sha256-Kq0WPitNekYzouyd8ROlZb63cpSg/+Ep2XxkV0YlABU=",
+        "owner": "nvmd",
+        "repo": "nixos-raspberrypi",
+        "rev": "b5c77d506bed55250a4642ce6c8b395dd29ef06b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nvmd",
+        "ref": "v1.20260317.0",
+        "repo": "nixos-raspberrypi",
+        "type": "github"
+      }
+    },
+    "nixos-uconsole": {
+      "inputs": {
+        "nixos-raspberrypi": "nixos-raspberrypi_2",
+        "nixpkgs": [
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1775854552,
+        "narHash": "sha256-hBlNh2eFWg0qlxM1gFpjp2JBdB82Zw4Y5otd+hwEvpQ=",
+        "owner": "nixos-uconsole",
+        "repo": "nixos-uconsole",
+        "rev": "cf4cb3b7996bd2cbc88964f90af8929e4d76987b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nixos-uconsole",
+        "repo": "nixos-uconsole",
+        "type": "github"
+      }
+    },
    "nixpkgs": {
      "locked": {
        "lastModified": 1705033721,
@@ -178,11 +364,11 @@
    },
    "nixpkgs_2": {
      "locked": {
-        "lastModified": 1774386573,
-        "narHash": "sha256-4hAV26quOxdC6iyG7kYaZcM3VOskcPUrdCQd/nx8obc=",
+        "lastModified": 1777268161,
+        "narHash": "sha256-bxrdOn8SCOv8tN4JbTF/TXq7kjo9ag4M+C8yzzIRYbE=",
        "owner": "nixos",
        "repo": "nixpkgs",
-        "rev": "46db2e09e1d3f113a13c0d7b81e2f221c63b8ce9",
+        "rev": "1c3fe55ad329cbcb28471bb30f05c9827f724c76",
        "type": "github"
      },
      "original": {
@@ -212,6 +398,8 @@
      "inputs": {
        "agenix": "agenix",
        "lix": "lix",
+        "nixos-raspberrypi": "nixos-raspberrypi",
+        "nixos-uconsole": "nixos-uconsole",
        "nixpkgs": "nixpkgs_2"
      }
    },
--- a/flake.nix
+++ b/flake.nix
@@ -12,10 +12,20 @@
      url = "git+https://git.lix.systems/lix-project/lix?ref=main";
      inputs.nixpkgs.follows = "nixpkgs";
    };
+    # uConsole CM5 hardware support
+    nixos-uconsole = {
+      url = "github:nixos-uconsole/nixos-uconsole";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
+    # nixos-raspberrypi provides hardware.raspberry-pi options required by uconsole-cm5
+    nixos-raspberrypi = {
+      url = "github:nvmd/nixos-raspberrypi/v1.20260317.0";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
    self.submodules = true;
  };

-  outputs = { self, nixpkgs, agenix, lix, ... }@inputs:
+  outputs = { self, nixpkgs, agenix, lix, nixos-uconsole, nixos-raspberrypi, ... }@inputs:
    let
      system = "x86_64-linux";
      keys = import ./lib/keys.nix;
@@ -79,6 +89,25 @@
              ./hosts/cyt-pi/hardware-configuration.nix
            ];
          };
+
+          uConsole = nixpkgs.lib.nixosSystem {
+            system = "aarch64-linux";
+            specialArgs = { inherit self keys paths inputs nixos-raspberrypi; };
+            modules = [
+              {
+                nixpkgs.config.allowUnfree = true;
+                nixpkgs.hostPlatform = "aarch64-linux";
+                nixpkgs.overlays = [ nixos-raspberrypi.overlays.vendor-pkgs ];
+                nix.package = lix.packages."aarch64-linux".default;
+              }
+              # Raspberry Pi 5 base (provides hardware.raspberry-pi options)
+              nixos-raspberrypi.nixosModules.raspberry-pi-5.base
+              # uConsole CM5 hardware support (display, kernel, config)
+              nixos-uconsole.nixosModules.uconsole-cm5
+              ./hosts/uconsole/configuration.nix
+              ./hosts/uconsole/hardware-configuration.nix
+            ];
+          };
        };
        devShells.${system}.default = devShell;
      };
--- a/hosts/uconsole/configuration.nix
+++ b/hosts/uconsole/configuration.nix
@@ -0,0 +1,153 @@
+{ config, lib, pkgs, paths, self, keys, inputs, nixos-raspberrypi, ... }:
+
+let
+  # Reticulum Network Stack - build from PyPI
+  reticulum = pkgs.python3Packages.buildPythonPackage {
+    pname = "reticulum";
+    version = "0.7.0";
+    format = "pyproject";
+    src = pkgs.python3Packages.fetchPypi {
+      pname = "reticulum";
+      version = "0.7.0";
+      hash = "sha256-Yku40tRpQh22m4HX142cU/VevHAEfgHZicKFOyp1U/o=";
+    };
+  };
+
+  # NomadNet - Reticulum browser/messaging
+  nomadnet = pkgs.python3Packages.buildPythonPackage {
+    pname = "nomadnet";
+    version = "0.5.2";
+    format = "pyproject";
+    src = pkgs.python3Packages.fetchPypi {
+      pname = "nomadnet";
+      version = "0.5.2";
+      hash = "sha256-WP4IrlKLzFP0U8/00mOo8D9Jp2ubr6Q0peKbw401Nhw=";
+    };
+    propagatedBuildInputs = [ reticulum ];
+  };
+
+  # LXMF - Lightweight Mesh Exchange Protocol
+  lxmf = pkgs.python3Packages.buildPythonPackage {
+    pname = "lxmf";
+    version = "0.5.1";
+    format = "pyproject";
+    src = pkgs.python3Packages.fetchPypi {
+      pname = "lxmf";
+      version = "0.5.1";
+      hash = "sha256-2zwTgG283qx1Bt6TKaGJtcwPr2tCNOOIASu8RXC/QLE=";
+    };
+    propagatedBuildInputs = [ reticulum ];
+  };
+in
+{
+  # --- CORE HARDWARE (CM5 / RPi5) ---
+  # nixos-raspberrypi.nixosModules.raspberry-pi-5.base + nixos-uconsole.nixosModules.uconsole-cm5 imported in flake.nix
+
+  # --- BASIC HOST INFO ---
+  networking.hostName = "uConsole";
+  networking.networkmanager.enable = true;
+  time.timeZone = "America/Montreal";
+  i18n.defaultLocale = "en_CA.UTF-8";
+
+  # --- GPS DAEMON ---
+  services.gpsd = {
+    enable = true;
+    devices = [ "/dev/ttyAMA0" ]; # Default port for RPi5/CM5 GPS
+    nowait = true;
+  };
+
+  # --- USER CONFIGURATION ---
+  users.users.thierry = {
+    isNormalUser = true;
+    description = "Thierry";
+    extraGroups = [ 
+      "wheel"      # Sudo
+      "dialout"    # Access to serial/HAM rigs
+      "plugdev"    # Access to USB SDRs
+      "wireshark"  # Packet capture without root
+      "video"      # Hardware acceleration access
+      "networkmanager"
+    ];
+    openssh.authorizedKeys.keys = [
+      keys.users.gortium.main
+      keys.users.gortium.gitea
+    ];
+  };
+
+  # --- INTERFACE (WAYLAND/SWAY) ---
+  # Sway is recommended for the uConsole's low resources
+  programs.sway = {
+    enable = true;
+    extraOptions = [ "--unsupported-gpu" ]; # Often needed for RPi
+  };
+
+  # --- SOFTWARE TOOLKITS ---
+  environment.systemPackages = with pkgs; [
+    # Base Tools (for your Doom Emacs environment)
+    emacs-pgtk      # Emacs with Wayland support
+    git             # Required for Doom Emacs / Flakes
+    ripgrep         # Fast searching for Emacs/CLI
+    fd              # Better find for Emacs
+    htop            # Resource monitor
+    tmux            # Terminal multiplexer
+    neovim          # Alternative editor
+
+    # HAM RADIO (Digital Modes)
+    js8call         # Weak-signal keyboard messaging
+    wsjtx           # FT8, JT65, etc.
+    fldigi          # Digital modem (PSK, RTTY)
+    pat             # Winlink client (Use 'pat configure' after install)
+    direwolf        # Software TNC for APRS
+    chirp           # Radio programming
+    hamlib          # Rig control (rigctl)
+    trustedqsl      # LotW log signing
+
+    # SDR + RF ANALYSIS
+    sdrpp           # Modern SDR GUI (Best for uConsole)
+    gqrx            # Classic SDR receiver
+    rtl-sdr         # Drivers for RTL2832U
+    inspectrum      # Offline signal analysis
+    soapysdr-with-plugins # Hardware abstraction layer
+
+    # LORA, MESH & RETICULUM
+    reticulum   # The RNS stack (rnsd, rnsh)
+    nomadnet    # Reticulum browser/messaging
+    lxmf        # Lightweight Mesh Exchange Protocol
+    # sidechannel - not available on PyPI, would need to build from source
+
+    # HACKING & SECURITY (Kali-like suite)
+    nmap            # Port scanning
+    metasploit      # Exploitation framework
+    aircrack-ng     # Wi-Fi auditing
+    kismet          # Wireless sniffer (Essential for your Pi Zero project)
+    bettercap       # MITM and network attack tool
+    wireshark       # Protocol analyzer
+    burpsuite       # Web vulnerability scanner
+    hashcat         # Password recovery
+    john            # John the Ripper (password cracking)
+    sqlmap          # Automated SQL injection
+
+    # GPS & OFFLINE MAPPING
+    foxtrotgps      # Lightweight map viewer (Perfect for small screens)
+    viking          # GPS data editor and map viewer
+    gpsbabel        # GPS data conversion
+    # marble - not available in this nixpkgs version
+  ];
+
+  # Udev rules for SDR and Radio hardware access
+  services.udev.packages = [ 
+    pkgs.rtl-sdr
+  ];
+
+  # Enable Wireshark privilege separation
+  programs.wireshark.enable = true;
+
+  # Enable OpenSSH
+  services.openssh = {
+    enable = true;
+    settings.PermitRootLogin = lib.mkForce "prohibit-password";
+  };
+
+  # System state version
+  system.stateVersion = "25.11";
+}
--- a/hosts/uconsole/hardware-configuration.nix
+++ b/hosts/uconsole/hardware-configuration.nix
@@ -0,0 +1,30 @@
+{ config, lib, pkgs, modulesPath, ... }:
+
+{
+  imports =
+    [ (modulesPath + "/installer/scan/not-detected.nix")
+    ];
+
+  boot.initrd.availableKernelModules = [ "xhci_pci" "usbhid" "sdhci_pci" ];
+  boot.initrd.kernelModules = [ ];
+  boot.kernelModules = [ ];
+  boot.extraModulePackages = [ ];
+
+  # uConsole CM5 specific filesystem (eMMC boot)
+  fileSystems."/" =
+    { device = "/dev/disk/by-label/NIXOS_SD";
+      fsType = "ext4";
+      options = [ "noatime" ];
+    };
+
+  fileSystems."/boot" =
+    { device = "/dev/disk/by-label/FIRMWARE";
+      fsType = "vfat";
+    };
+
+  swapDevices = [ ];
+
+  # uConsole CM5 is ARM64
+  nixpkgs.hostPlatform = lib.mkDefault "aarch64-linux";
+  hardware.enableRedistributableFirmware = true;
+}
				`@@ -0,0 +1 @@`
				`timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best`