Compare commits

..

19 Commits

Author SHA1 Message Date
261536d74d feat: bake Matrix bridge deps into Docker image instead of volume mount
Some checks failed
Build Hermes agent / build (pull_request) Has been cancelled
Build ollama (gfx906) / build (pull_request) Has been cancelled
2026-05-22 22:15:36 -04:00
9b20dfe67f feat: honcho-only memory provider with Traefik + Authelia
- Remove OpenViking/Holographic dependencies (only Honcho stays)
- Remove httpx install from Dockerfile (was for OpenViking)
- Add Traefik routing for honcho at honcho.lazyworkhorse.net
- Add Authelia auth middleware on honcho HTTPS
- Add ai_net network to honcho for Traefik access
2026-05-22 22:15:36 -04:00
8e99fb8809 fix: restore corrupted variable names (${OPENROUTER_API_KEY}, ${OPENCLAW_GATEWAY_TOKEN}) 2026-05-22 22:15:36 -04:00
057f1b0f4e chore: remove Hermes config files from repo — lives on persistent volume 2026-05-22 22:15:36 -04:00
69e0b7383a chore: remove .env.example 2026-05-22 22:15:36 -04:00
7404e1e466 feat: keep only Honcho, remove OpenViking from memory providers 2026-05-22 22:15:36 -04:00
81a12afe39 feat: add self-hosted memory providers (OpenViking, Honcho, Holographic)
- Add OpenViking service (knowledge graph) using official GHCR image
- Add Honcho stack (user modeling): API + PostgreSQL pgvector + Redis
- Add Holographic config to Hermes (local SQLite, no server needed)
- Hermes: install httpx for OpenViking client
- Hermes: auto-generate config.yaml + honcho.json on first boot
- All data 100% local, zero cloud dependencies
2026-05-22 22:15:36 -04:00
3d90f57e7f Merge pull request 'fix: move run-multi-gateways.sh into build context, bake into image' (#50) from fix/multi-gateway-path into master
Some checks failed
Build Hermes agent / build (push) Has been cancelled
Build ollama (gfx906) / build (push) Has been cancelled
Reviewed-on: #50
2026-05-23 02:12:51 +00:00
c1cd9d31e9 fix: move run-multi-gateways.sh into ai/hermes/ and bake into image
Some checks failed
Build Hermes agent / build (pull_request) Has been cancelled
Build ollama (gfx906) / build (pull_request) Has been cancelled
2026-05-22 21:37:01 -04:00
5765dc6004 Merge remote-tracking branch 'origin/fix/hermes-build' 2026-05-22 21:13:46 -04:00
e8075fb71b fix: also clear API_SERVER_KEY for profile gateways
Line 1521 in gateway/config.py: if api_server_enabled or api_server_key:
The compose.yml sets API_SERVER_KEY=hermes_local_key, which was enough
to enable the API server even with API_SERVER_ENABLED=false.
2026-05-22 13:53:53 -04:00
645d519030 fix: use env to force API_SERVER_ENABLED=false in multi-gateway launcher
Shell prefix didn't work with nohup+gosu chain - Docker compose
env var API_SERVER_ENABLED=true leaked through. Using 'env'
command guarantees the override is in the child process env.
2026-05-22 13:52:05 -04:00
146add2a64 fix: use full hermes path and gosu in multi-gateway launcher
- Use /opt/hermes/.venv/bin/hermes (full path) — not on PATH
  before entrypoint.sh sources the venv
- Wrap with gosu hermes to avoid root guard in gateway run
- Add error check if hermes binary doesn't exist
2026-05-22 13:34:12 -04:00
eb3795d9e3 Merge remote-tracking branch 'origin/fix/hermes-build' 2026-05-22 13:26:59 -04:00
ef6e0e57b6 Merge remote-tracking branch 'origin/fix/remove-venv-mount' 2026-05-22 13:25:59 -04:00
d8a1ebcd96 fix: add missing command: gateway run to hermes service
Without this,  is empty and entrypoint.sh runs bare 'hermes'
which defaults to interactive chat mode. With a non-TTY stdin
this exits immediately with prompt_toolkit's 'Input is not a
terminal' warning, causing a container restart loop.

The profile gateways (run-multi-gateways.sh) were unaffected
because the script passes 'gateway run' explicitly.
2026-05-22 13:23:08 -04:00
45a224eb7f fix: add missing command: gateway run to hermes service
Without this,  is empty and entrypoint.sh runs bare 'hermes'
which defaults to interactive chat mode. With a non-TTY stdin
this exits immediately with prompt_toolkit's 'Input is not a
terminal' warning, causing a container restart loop.

The profile gateways (run-multi-gateways.sh) were unaffected
because the script passes 'gateway run' explicitly.
2026-05-22 13:22:58 -04:00
bce336c4fd feat: bake Matrix bridge deps into Docker image instead of volume mount
- Add libolm-dev system dep (required by mautrix[encryption])
- Add mautrix[encryption] + openai pip packages to build
- These were previously installed inline at container startup and
  persisted via the fragile venv volume mount (now removed)
2026-05-22 13:04:43 -04:00
e4117cd3d5 fix: remove venv volume mount conflicting with entrypoint.sh
The volume mount at /mnt/HoardingCow_docker_data/Hermes/venv overrides the
container's built .venv with an empty or stale host directory, causing
entrypoint.sh line 62 to fail on 'source .venv/bin/activate' (set -e).

The Docker image already builds a complete venv — no need to persist it.
2026-05-22 13:04:08 -04:00
4 changed files with 63 additions and 18 deletions

View File

@@ -32,7 +32,7 @@ services:
- default
container_name: hermes
entrypoint: ["/bin/bash", "-c",
"bash /opt/data/hermes-tools/install.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
"bash /opt/data/hermes-tools/install.sh && bash /usr/local/bin/run-multi-gateways.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
"hermes-entrypoint"]
restart: always
# Gateway run enables the internal API server on port 8642
@@ -40,6 +40,10 @@ services:
environment:
- OLLAMA_HOST=http://ollama:11434
- HERMES_DASHBOARD=1
# Multi-profile: comma-separated list of profiles to run as gateways.
# The entrypoint reads this and starts one gateway per profile.
# Add profiles here when they exist on disk (e.g. default,researcher,writer)
- HERMES_PROFILES=ashley,claire,finn,matt,paul
- API_SERVER_ENABLED=true
- API_SERVER_PORT=8642
- API_SERVER_HOST=0.0.0.0
@@ -123,6 +127,7 @@ services:
- "traefik.http.routers.syncthing-https.tls.certresolver=njalla"
- "traefik.http.services.syncthing.loadbalancer.server.port=8384"
ollama:
build:
context: ./ollama

View File

@@ -43,6 +43,12 @@ RUN apt-get update && \
# ---------- UV ----------
COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/
# ---------- Matrix bridge + extra pip deps ----------
# Previously installed inline at container startup and persisted via volume mount.
# Now baked into the image so the fragile venv volume mount can be removed.
RUN . /opt/hermes/.venv/bin/activate && \
uv pip install --no-cache-dir 'mautrix[encryption]' openai
WORKDIR /opt/hermes
# ---------- Matrix bridge + extra pip deps ----------
@@ -78,6 +84,10 @@ os.remove(tgz)
print('himalaya v1.2.0 installed')
PYEOF
# ---------- Install multi-gateway launcher ----------
# Launches one gateway process per profile (HERMES_PROFILES env var)
COPY --chmod=0755 run-multi-gateways.sh /usr/local/bin/run-multi-gateways.sh
# ---------- Runtime ----------
USER hermes
ENV HERMES_HOME=/opt/data

32
ai/hermes/run-multi-gateways.sh Executable file
View File

@@ -0,0 +1,32 @@
#!/bin/bash
# Multi-gateway launcher for HERMES_PROFILES env var.
# Reads comma-separated profile names, spawns one gateway per profile.
# Designed to run before the main entrypoint — gateways run in background.
set -e
if [ -z "${HERMES_PROFILES}" ]; then
echo "HERMES_PROFILES not set — skipping multi-gateway launch"
exit 0
fi
# Source venv to make 'hermes' available (entrypoint.sh sources it later,
# but we need it NOW for the background gateways)
HERMES_BIN="/opt/hermes/.venv/bin/hermes"
if [ ! -x "$HERMES_BIN" ]; then
echo "ERROR: hermes binary not found at $HERMES_BIN"
exit 1
fi
mkdir -p /opt/data/logs
IFS=',' read -ra PROFILES <<< "${HERMES_PROFILES}"
for profile in "${PROFILES[@]}"; do
profile="$(echo "${profile}" | xargs)" # trim whitespace
[ -z "${profile}" ] && continue
echo "Starting gateway for profile: ${profile}"
nohup env API_SERVER_ENABLED=false API_SERVER_KEY= gosu hermes "$HERMES_BIN" --profile "${profile}" gateway run \
>> "/opt/data/logs/gateway-${profile}.log" 2>&1 &
done
echo "All gateways launched: ${HERMES_PROFILES}"

View File

@@ -29,7 +29,7 @@ URL = "redis://honcho-redis:6379/0"
[llm]
DEFAULT_MAX_TOKENS = 4096
# Embeddings via Ollama local (nomic-embed-text)
# Embeddings via Ollama (nomic-embed-text recommended on this system)
[embedding]
VECTOR_DIMENSIONS = 768
MAX_INPUT_TOKENS = 8192
@@ -40,7 +40,6 @@ model = "nomic-embed-text"
base_url = "http://ollama:11434/v1"
# --- Deriver (user representation builder) ---
# Uses DeepSeek V3 Flash via OpenCode Go
[deriver]
ENABLED = true
WORKERS = 1
@@ -49,11 +48,10 @@ FLUSH_ENABLED = true
[deriver.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
# --- Dialectic ---
# All levels use DeepSeek V3 Flash via OpenCode Go
[dialectic]
MAX_INPUT_TOKENS = 4096
SESSION_HISTORY_MAX_TOKENS = 8192
@@ -63,36 +61,36 @@ MAX_TOOL_ITERATIONS = 1
MAX_OUTPUT_TOKENS = 512
[dialectic.levels.minimal.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
[dialectic.levels.low]
MAX_TOOL_ITERATIONS = 3
[dialectic.levels.low.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
[dialectic.levels.medium]
MAX_TOOL_ITERATIONS = 2
[dialectic.levels.medium.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
[dialectic.levels.high]
MAX_TOOL_ITERATIONS = 4
[dialectic.levels.high.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
[dialectic.levels.max]
MAX_TOOL_ITERATIONS = 10
[dialectic.levels.max.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
# --- Summary ---
[summary]
@@ -102,8 +100,8 @@ MESSAGES_PER_LONG_SUMMARY = 60
[summary.model_config]
transport = "openai"
model = "deepseek/deepseek-v3-flash"
base_url = "https://opencode.ai/zen/go/v1"
model = "hermes-3"
base_url = "http://ollama:11434/v1"
# --- Dream ---
[dream]