Compare commits
4 Commits
feat/docke
...
feat/k3s-p
| Author | SHA1 | Date | |
|---|---|---|---|
| f4b666284a | |||
| 815ca3afa6 | |||
| e983775c04 | |||
|
bcf5cadaa0 |
@@ -13,7 +13,9 @@ None
|
||||
- ✅ **Phase 1: Foundation Setup** - Establish core NixOS configuration with flakes
|
||||
- ✅ **Phase 2: Docker Service Integration** - Integrate Docker Compose services
|
||||
- ✅ **Phase 3: AI Assistant Integration** - Enable AI-assisted infrastructure management
|
||||
- [ ] **Phase 4: Internet Access & MCP** - MCP server for web access
|
||||
- ✅ **Phase 4: Internet Access & MCP** - MCP server for web access
|
||||
- 🚨 **Security Hardening** - CRITICAL: Firewall, fail2ban, SSH hardening (PR #28)
|
||||
- [ ] **Phase 5: TAK Server** - Research, implementation, and validation
|
||||
|
||||
|
||||
## Phase Details
|
||||
@@ -133,8 +135,25 @@ Plans:
|
||||
|
||||
## Progress
|
||||
|
||||
**Merge Priority Order** (CRITICAL - merge in this order):
|
||||
|
||||
| Priority | PR | Description | Status | Notes |
|
||||
|----------|-----|-------------|--------|-------|
|
||||
| 🚨 1 | #28 | **Security hardening** (firewall, fail2ban, SSH) | Open | **MERGE FIRST** - protects all other services |
|
||||
| 2 | #22 | Matrix bridge dependency fix | Open | Blocks Hermes functionality |
|
||||
| 3 | #21 | Backup network creation fix | Open | Infrastructure fix |
|
||||
| 4 | #25 | Hermes voice GPU support | Open | Feature enhancement |
|
||||
| 5 | #24 | uConsole CM5 host | Open | New hardware support |
|
||||
| 6 | #23 | NixOS deployment infrastructure | Open | Deployment tooling |
|
||||
| 7 | #1 | AI worker restricted access | Open | Legacy PR (superseded by hardening) |
|
||||
|
||||
**Execution Order:**
|
||||
Phases execute in numeric order: 1 → 2 → 3 → 4 → 5 → 6 → 7
|
||||
Phases execute in numeric order: 1 → 2 → 3 → 4 → Security → 5 → 6 → 7
|
||||
|
||||
**Merge vs Phase Execution:**
|
||||
- PRs can merge independently (no strict phase ordering for merges)
|
||||
- **EXCEPTION:** Security hardening (#28) must merge before any new services are exposed
|
||||
- After security merge, deploy with: `nh os switch --flake .#lazyworkhorse`
|
||||
|
||||
| Phase | Milestone | Plans Complete | Status | Completed |
|
||||
|-------|-----------|----------------|--------|-----------|
|
||||
|
||||
@@ -1,203 +0,0 @@
|
||||
# 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}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -1,283 +0,0 @@
|
||||
# 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
|
||||
@@ -1 +0,0 @@
|
||||
timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
|
||||
|
@@ -1,21 +0,0 @@
|
||||
{
|
||||
"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"
|
||||
}
|
||||
Submodule assets/compose updated: fb0f2cbe84...a79fe9dffa
@@ -1,67 +0,0 @@
|
||||
FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
|
||||
FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
|
||||
FROM debian:13.4
|
||||
|
||||
# Disable Python stdout buffering to ensure logs are printed immediately
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
|
||||
# Store Playwright browsers outside the volume mount so the build-time
|
||||
# install survives the /opt/data volume overlay at runtime.
|
||||
ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
|
||||
|
||||
# Install system dependencies in one layer, clear APT cache
|
||||
# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
|
||||
# that would otherwise accumulate when hermes runs as PID 1. See #15012.
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
|
||||
curl poppler-utils imagemagick \
|
||||
chromium xvfb fonts-noto-color-emoji fonts-unifont fonts-liberation fonts-ipafont-gothic fonts-wqy-zenhei fonts-tlwg-loma-otf fonts-freefont-ttf \
|
||||
libasound2t64 libatk-bridge2.0-0t64 libatk1.0-0t64 libatspi2.0-0t64 libcairo2 libcups2t64 libdbus-1-3 libdrm2 libgbm1 libglib2.0-0t64 libnspr4 libnss3 libpango-1.0-0 libx11-6 libxcb1 libxcomposite1 libxdamage1 libxext6 libxfixes3 libxkbcommon0 libxrandr2 \
|
||||
texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
|
||||
RUN useradd -u 10000 -m -d /opt/data hermes
|
||||
|
||||
COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
|
||||
COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
|
||||
|
||||
WORKDIR /opt/hermes
|
||||
|
||||
# ---------- Layer-cached dependency install ----------
|
||||
# Copy only package manifests first so npm install + Playwright are cached
|
||||
# unless the lockfiles themselves change.
|
||||
COPY package.json package-lock.json ./
|
||||
COPY web/package.json web/package-lock.json web/
|
||||
|
||||
RUN npm install --prefer-offline --no-audit && \
|
||||
npx playwright install --with-deps chromium --only-shell && \
|
||||
(cd web && npm install --prefer-offline --no-audit) && \
|
||||
npm cache clean --force
|
||||
|
||||
# ---------- Source code ----------
|
||||
# .dockerignore excludes node_modules, so the installs above survive.
|
||||
COPY --chown=hermes:hermes . .
|
||||
|
||||
# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
|
||||
RUN cd web && npm run build
|
||||
|
||||
# ---------- Permissions ----------
|
||||
# Make install dir world-readable so any HERMES_UID can read it at runtime.
|
||||
# The venv needs to be traversable too.
|
||||
USER root
|
||||
RUN chmod -R a+rX /opt/hermes
|
||||
# Start as root so the entrypoint can usermod/groupmod + gosu.
|
||||
# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
|
||||
|
||||
# ---------- Python virtualenv ----------
|
||||
RUN uv venv && \
|
||||
uv pip install --no-cache-dir -e ".[all]"
|
||||
|
||||
# ---------- Runtime ----------
|
||||
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
|
||||
ENV HERMES_HOME=/opt/data
|
||||
ENV PATH="/opt/data/.local/bin:${PATH}"
|
||||
VOLUME [ "/opt/data" ]
|
||||
ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]
|
||||
@@ -1,102 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Docker/Podman entrypoint: bootstrap config files into the mounted volume, then run hermes.
|
||||
set -e
|
||||
|
||||
HERMES_HOME="${HERMES_HOME:-/opt/data}"
|
||||
INSTALL_DIR="/opt/hermes"
|
||||
|
||||
# --- Privilege dropping via gosu ---
|
||||
# When started as root (the default for Docker, or fakeroot in rootless Podman),
|
||||
# optionally remap the hermes user/group to match host-side ownership, fix volume
|
||||
# permissions, then re-exec as hermes.
|
||||
if [ "$(id -u)" = "0" ]; then
|
||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
|
||||
echo "Changing hermes UID to $HERMES_UID"
|
||||
usermod -u "$HERMES_UID" hermes
|
||||
fi
|
||||
|
||||
if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
|
||||
echo "Changing hermes GID to $HERMES_GID"
|
||||
# -o allows non-unique GID (e.g. macOS GID 20 "staff" may already exist
|
||||
# as "dialout" in the Debian-based container image)
|
||||
groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# Fix ownership of the data volume. When HERMES_UID remaps the hermes user,
|
||||
# files created by previous runs (under the old UID) become inaccessible.
|
||||
# Always chown -R when UID was remapped; otherwise only if top-level is wrong.
|
||||
actual_hermes_uid=$(id -u hermes)
|
||||
needs_chown=false
|
||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "10000" ]; then
|
||||
needs_chown=true
|
||||
elif [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
|
||||
needs_chown=true
|
||||
fi
|
||||
if [ "$needs_chown" = true ]; then
|
||||
echo "Fixing ownership of $HERMES_HOME to hermes ($actual_hermes_uid)"
|
||||
# In rootless Podman the container's "root" is mapped to an unprivileged
|
||||
# host UID — chown will fail. That's fine: the volume is already owned
|
||||
# by the mapped user on the host side.
|
||||
chown -R hermes:hermes "$HERMES_HOME" 2>/dev/null || \
|
||||
echo "Warning: chown failed (rootless container?) — continuing anyway"
|
||||
fi
|
||||
|
||||
echo "Dropping root privileges"
|
||||
exec gosu hermes "$0" "$@"
|
||||
fi
|
||||
|
||||
# --- Running as hermes from here ---
|
||||
source "${INSTALL_DIR}/.venv/bin/activate"
|
||||
|
||||
# Create essential directory structure. Cache and platform directories
|
||||
# (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
|
||||
# demand by the application — don't pre-create them here so new installs
|
||||
# get the consolidated layout from get_hermes_dir().
|
||||
# The "home/" subdirectory is a per-profile HOME for subprocesses (git,
|
||||
# ssh, gh, npm …). Without it those tools write to /root which is
|
||||
# ephemeral and shared across profiles. See issue #4426.
|
||||
mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills,skins,plans,workspace,home}
|
||||
|
||||
# .env
|
||||
if [ ! -f "$HERMES_HOME/.env" ]; then
|
||||
cp "$INSTALL_DIR/.env.example" "$HERMES_HOME/.env"
|
||||
fi
|
||||
|
||||
# config.yaml
|
||||
if [ ! -f "$HERMES_HOME/config.yaml" ]; then
|
||||
cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
|
||||
fi
|
||||
|
||||
# Ensure the main config file remains accessible to the hermes runtime user
|
||||
# even if it was edited on the host after initial ownership setup.
|
||||
if [ -f "$HERMES_HOME/config.yaml" ]; then
|
||||
chown hermes:hermes "$HERMES_HOME/config.yaml"
|
||||
chmod 640 "$HERMES_HOME/config.yaml"
|
||||
fi
|
||||
|
||||
# SOUL.md
|
||||
if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
|
||||
cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"
|
||||
fi
|
||||
|
||||
# Sync bundled skills (manifest-based so user edits are preserved)
|
||||
if [ -d "$INSTALL_DIR/skills" ]; then
|
||||
python3 "$INSTALL_DIR/tools/skills_sync.py"
|
||||
fi
|
||||
|
||||
# Final exec: two supported invocation patterns.
|
||||
#
|
||||
# docker run <image> -> exec `hermes` with no args (legacy default)
|
||||
# docker run <image> chat -q "..." -> exec `hermes chat -q "..."` (legacy wrap)
|
||||
# docker run <image> sleep infinity -> exec `sleep infinity` directly
|
||||
# docker run <image> bash -> exec `bash` directly
|
||||
#
|
||||
# If the first positional arg resolves to an executable on PATH, we assume the
|
||||
# caller wants to run it directly (needed by the launcher which runs long-lived
|
||||
# `sleep infinity` sandbox containers — see tools/environments/docker.py).
|
||||
# Otherwise we treat the args as a hermes subcommand and wrap with `hermes`,
|
||||
# preserving the documented `docker run <image> <subcommand>` behavior.
|
||||
if [ $# -gt 0 ] && command -v "$1" >/dev/null 2>&1; then
|
||||
exec "$@"
|
||||
fi
|
||||
exec hermes "$@"
|
||||
@@ -61,6 +61,7 @@
|
||||
./modules/nixos/services/open_code_server.nix
|
||||
./modules/nixos/services/ollama_init_custom_models.nix
|
||||
./modules/nixos/services/openclaw_node.nix
|
||||
./modules/nixos/services/hyperspace.nix
|
||||
./users/gortium.nix
|
||||
./users/ai-worker.nix
|
||||
];
|
||||
|
||||
@@ -277,6 +277,16 @@
|
||||
displayName = "lazyworkhorse-host";
|
||||
};
|
||||
|
||||
# Hyperspace Pods — P2P mesh AI cluster (combine GPUs across machines)
|
||||
services.hyperspace = {
|
||||
enable = true;
|
||||
user = "ai-worker";
|
||||
apiPort = 8080;
|
||||
profile = "auto";
|
||||
openFirewall = true;
|
||||
extraArgs = [ "--verbose" ];
|
||||
};
|
||||
|
||||
# Public host ssh key (kept in sync with the private one)
|
||||
environment.etc."ssh/ssh_host_ed25519_key.pub".text =
|
||||
"${keys.hosts.lazyworkhorse.main}";
|
||||
|
||||
235
modules/nixos/services/hyperspace.nix
Normal file
235
modules/nixos/services/hyperspace.nix
Normal file
@@ -0,0 +1,235 @@
|
||||
{ config, lib, pkgs, ... }:
|
||||
|
||||
with lib;
|
||||
|
||||
let
|
||||
cfg = config.services.hyperspace;
|
||||
|
||||
# Hyperspace CLI release from github.com/hyperspaceai/aios-cli
|
||||
# The binary bundles Node.js runtime + llama.cpp + sidecars (~914MB)
|
||||
# It auto-updates via `hyperspace update` post-install
|
||||
hyperspacePkg = pkgs.stdenv.mkDerivation rec {
|
||||
pname = "hyperspace";
|
||||
version = cfg.release;
|
||||
|
||||
src = pkgs.fetchurl {
|
||||
url = "https://github.com/hyperspaceai/aios-cli/releases/download/v${version}/aios-cli-x86_64-unknown-linux-gnu.tar.gz";
|
||||
hash = "sha256-f6fJ8t3exqtYwUD5j+WvD+Hm0oN/Eef0X+R9Rj23dE0=";
|
||||
};
|
||||
|
||||
sourceRoot = ".";
|
||||
|
||||
installPhase = ''
|
||||
mkdir -p $out/bin $out/lib/hyperspace
|
||||
|
||||
# Main CLI binary
|
||||
cp aios-cli $out/bin/hyperspace
|
||||
chmod +x $out/bin/hyperspace
|
||||
|
||||
# Sidecar binaries
|
||||
for f in _aios-cli pod-raft hyperspace-*; do
|
||||
[ -f "$f" ] && install -m755 "$f" $out/lib/hyperspace/ || true
|
||||
done
|
||||
|
||||
# WASM, native modules, Python shards
|
||||
cp -r *.wasm $out/lib/hyperspace/ 2>/dev/null || true
|
||||
cp -r *.node $out/lib/hyperspace/ 2>/dev/null || true
|
||||
mkdir -p $out/lib/hyperspace/python
|
||||
cp -r python/* $out/lib/hyperspace/python/ 2>/dev/null || true
|
||||
|
||||
# Skills directory
|
||||
mkdir -p $out/share/hyperspace
|
||||
cp -r skills $out/share/hyperspace/ 2>/dev/null || true
|
||||
|
||||
# Set HYPERSPACE_PATH so the binary finds sidecars
|
||||
wrapProgram $out/bin/hyperspace \
|
||||
--set HYPERSPACE_PATH "$out/lib/hyperspace" \
|
||||
--set HYPERSPACE_SKILLS_DIR "$out/share/hyperspace/skills"
|
||||
'';
|
||||
|
||||
nativeBuildInputs = with pkgs; [ makeWrapper ];
|
||||
|
||||
meta = {
|
||||
description = "Hyperspace CLI — P2P mesh AI inference network (Pods)";
|
||||
longDescription = ''
|
||||
Hyperspace Pods let multiple machines pool their GPUs into one private
|
||||
AI cluster. Install the CLI, create a pod, share an invite link — your
|
||||
machines form a P2P mesh and can run models split across all connected
|
||||
GPUs. Exposes an OpenAI-compatible API for use with Cursor, Claude Code,
|
||||
Aider, etc.
|
||||
'';
|
||||
homepage = "https://hyperspace.sh";
|
||||
sourceProvenance = with lib; [ sourceTypes.binaryNativeCode ];
|
||||
license = lib.licenses.unfree;
|
||||
platforms = [ "x86_64-linux" ];
|
||||
maintainers = [ ];
|
||||
};
|
||||
};
|
||||
|
||||
in {
|
||||
options.services.hyperspace = {
|
||||
enable = mkEnableOption "Hyperspace P2P AI agent (Pods)";
|
||||
|
||||
release = mkOption {
|
||||
type = types.str;
|
||||
default = "5.45.30";
|
||||
description = "Hyperspace CLI release version (from GitHub releases).";
|
||||
};
|
||||
|
||||
user = mkOption {
|
||||
type = types.str;
|
||||
default = "ai-worker";
|
||||
description = "System user to run the Hyperspace agent.";
|
||||
};
|
||||
|
||||
apiPort = mkOption {
|
||||
type = types.port;
|
||||
default = 8080;
|
||||
description = "Port for the OpenAI-compatible API server.";
|
||||
};
|
||||
|
||||
autoStart = mkOption {
|
||||
type = types.bool;
|
||||
default = true;
|
||||
description = "Auto-start the Hyperspace agent on boot.";
|
||||
};
|
||||
|
||||
openFirewall = mkOption {
|
||||
type = types.bool;
|
||||
default = true;
|
||||
description = "Open firewall ports for P2P traffic (libp2p 4001, chain 30301, API).";
|
||||
};
|
||||
|
||||
profile = mkOption {
|
||||
type = types.enum [ "auto" "full" "inference" "embedding" "relay" "storage" ];
|
||||
default = "auto";
|
||||
description = ''
|
||||
Agent profile:
|
||||
- auto: auto-detect hardware
|
||||
- full: all 9 capabilities
|
||||
- inference: GPU inference only
|
||||
- embedding: CPU embedding only
|
||||
- relay: lightweight relay
|
||||
- storage: storage + memory
|
||||
'';
|
||||
};
|
||||
|
||||
extraArgs = mkOption {
|
||||
type = types.listOf types.str;
|
||||
default = [ ];
|
||||
description = "Extra arguments passed to `hyperspace start`.";
|
||||
};
|
||||
|
||||
dataDir = mkOption {
|
||||
type = types.str;
|
||||
default = "/var/lib/hyperspace";
|
||||
description = "Data directory for agent state (models, config, logs).";
|
||||
};
|
||||
};
|
||||
|
||||
config = mkIf cfg.enable {
|
||||
# Ensure the service user exists
|
||||
users.users.${cfg.user} = {
|
||||
isSystemUser = true;
|
||||
group = cfg.user;
|
||||
home = "/home/${cfg.user}";
|
||||
createHome = true;
|
||||
shell = pkgs.bash;
|
||||
};
|
||||
users.groups.${cfg.user} = { };
|
||||
|
||||
# Install the hyperspace binary
|
||||
environment.systemPackages = [ hyperspacePkg ];
|
||||
|
||||
# Data directories
|
||||
systemd.tmpfiles.rules = [
|
||||
"d ${cfg.dataDir} 0755 ${cfg.user} ${cfg.user} -"
|
||||
"d ${cfg.dataDir}/models 0755 ${cfg.user} ${cfg.user} -"
|
||||
"d ${cfg.dataDir}/data 0755 ${cfg.user} ${cfg.user} -"
|
||||
];
|
||||
|
||||
# Systemd service: runs the Hyperspace agent as a system daemon
|
||||
systemd.services.hyperspace = {
|
||||
description = "Hyperspace P2P AI Agent — Pods mesh cluster";
|
||||
documentation = [ "https://hyperspace.sh" "https://github.com/hyperspaceai/aios-cli" ];
|
||||
after = [ "network-online.target" ];
|
||||
wants = [ "network-online.target" ];
|
||||
wantedBy = mkIf cfg.autoStart [ "multi-user.target" ];
|
||||
|
||||
environment = {
|
||||
HYPERSPACE_HOME = cfg.dataDir;
|
||||
HYPERSPACE_API_PORT = toString cfg.apiPort;
|
||||
HYPERSPACE_PATH = "${hyperspacePkg}/lib/hyperspace";
|
||||
};
|
||||
|
||||
path = with pkgs; [ bash curl nodejs ];
|
||||
|
||||
script = ''
|
||||
# Wait for network connectivity before starting
|
||||
${pkgs.bash}/bin/bash -c '
|
||||
for i in $(seq 1 30); do
|
||||
ping -c 1 -W 1 8.8.8.8 >/dev/null 2>&1 && break
|
||||
sleep 2
|
||||
done
|
||||
' || true
|
||||
|
||||
exec ${hyperspacePkg}/bin/hyperspace start \
|
||||
--profile ${cfg.profile} \
|
||||
--api-port ${toString cfg.apiPort} \
|
||||
${lib.escapeShellArgs cfg.extraArgs}
|
||||
'';
|
||||
|
||||
serviceConfig = {
|
||||
Type = "exec";
|
||||
User = cfg.user;
|
||||
Group = cfg.user;
|
||||
WorkingDirectory = cfg.dataDir;
|
||||
Restart = "always";
|
||||
RestartSec = 10;
|
||||
TimeoutStartSec = 180;
|
||||
TimeoutStopSec = 30;
|
||||
KillMode = "mixed";
|
||||
|
||||
# File limits for network-heavy P2P agent
|
||||
LimitNOFILE = 65536;
|
||||
LimitNPROC = 4096;
|
||||
|
||||
# GPU access — AMD MI50 (ROCm) through /dev/kfd and /dev/dri
|
||||
DeviceAllow = [
|
||||
"/dev/kfd" "rw"
|
||||
"/dev/dri" "rw"
|
||||
];
|
||||
SupplementaryGroups = [ "video" "render" ];
|
||||
|
||||
# Security hardening
|
||||
NoNewPrivileges = true;
|
||||
ProtectSystem = "strict";
|
||||
ProtectHome = true;
|
||||
PrivateTmp = true;
|
||||
PrivateDevices = false; # needs GPU access
|
||||
ReadWritePaths = [
|
||||
cfg.dataDir
|
||||
"/tmp"
|
||||
];
|
||||
BindPaths = [
|
||||
# GPU devices for AMD MI50
|
||||
"/dev/kfd"
|
||||
"/dev/dri"
|
||||
];
|
||||
};
|
||||
};
|
||||
|
||||
# Firewall: open P2P ports for the mesh network
|
||||
networking.firewall = mkIf cfg.openFirewall {
|
||||
allowedTCPPorts = [
|
||||
4001 # libp2p P2P (agent gossip, DHT, circuits)
|
||||
30301 # Chain P2P (blockchain consensus)
|
||||
cfg.apiPort # OpenAI-compatible API
|
||||
];
|
||||
allowedUDPPorts = [
|
||||
4001 # libp2p QUIC transport
|
||||
30301 # Chain UDP discovery
|
||||
];
|
||||
};
|
||||
};
|
||||
}
|
||||
@@ -14,8 +14,25 @@
|
||||
local base_model=$2
|
||||
if ! ${pkgs.docker}/bin/docker exec ollama ollama list | grep -q "$model_name"; then
|
||||
echo "$model_name not found, creating from $base_model..."
|
||||
|
||||
# We use a custom TEMPLATE block to strip the 'currentDate' function
|
||||
# which is unsupported in Ollama 0.5.7 but present in Devstral's default manifest.
|
||||
${pkgs.docker}/bin/docker exec ollama sh -c "cat <<EOF > /root/.ollama/$model_name.modelfile
|
||||
FROM $base_model
|
||||
TEMPLATE \"\"\"{{- if .System }}
|
||||
[SYSTEM_PROMPT]
|
||||
{{ .System }}
|
||||
[/SYSTEM_PROMPT]
|
||||
{{- end }}
|
||||
{{- range .Messages }}
|
||||
{{- if eq .Role \"user\" }}
|
||||
[INST]
|
||||
{{ .Content }}
|
||||
[/INST]
|
||||
{{- else if eq .Role \"assistant\" }}
|
||||
{{ .Content }}
|
||||
{{- end }}
|
||||
{{- end }}\"\"\"
|
||||
PARAMETER num_ctx 131072
|
||||
PARAMETER num_predict 4096
|
||||
PARAMETER num_keep 1024
|
||||
@@ -26,6 +43,7 @@ PARAMETER stop \"[/INST]\"
|
||||
PARAMETER stop \"</s>\"
|
||||
EOF"
|
||||
${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f "/root/.ollama/$model_name.modelfile"
|
||||
${pkgs.docker}/bin/docker exec ollama rm "/root/.ollama/$model_name.modelfile"
|
||||
else
|
||||
echo "$model_name already exists, skipping."
|
||||
fi
|
||||
@@ -36,6 +54,10 @@ EOF"
|
||||
|
||||
# Create Devstral
|
||||
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
|
||||
|
||||
# create_model_if_missing "qwen2.5-coder:32b-128k" "qwen2.5-coder:32b"
|
||||
|
||||
# create_model_if_missing "mistral-large-planner:123b" "mistral-large:123b-instruct-v2407-q4_K_S"
|
||||
'';
|
||||
serviceConfig = {
|
||||
Type = "oneshot";
|
||||
|
||||
Reference in New Issue
Block a user