Files
AgapHost/openai/docker-compose.yml
alvis f5c14efb37 openai: add cognee-llm stateless Kimi-CLI wrapper (:8011) [Adolf P3]
Stateless one-shot wrapper for Cognee batch cognify: fresh temp dir per
request, no resume, non-streaming, text-only, bounded concurrency (3).
Per SPIKE-FINDINGS gate 5, Cognee should default its LLM to LiteLLM; this is
the optional low-volume path. New service + cognee-llm-home volume in compose.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LeqyaxJF2nbRXJtae2kNB2
2026-07-05 09:56:25 +00:00

174 lines
5.1 KiB
YAML

services:
litellm-db:
image: postgres:16-alpine
container_name: litellm-db
environment:
- POSTGRES_DB=litellm
- POSTGRES_USER=litellm
- POSTGRES_PASSWORD=litellm
volumes:
- /mnt/ssd/dbs/litellm/postgres:/var/lib/postgresql/data
restart: always
litellm:
image: ghcr.io/berriai/litellm:main-latest
container_name: litellm
ports:
- "4000:4000"
volumes:
- ./litellm-config.yaml:/app/config.yaml
environment:
- DATABASE_URL=postgresql://litellm:litellm@litellm-db:5432/litellm
- LITELLM_MASTER_KEY=sk-fjQC1BxAiGFSMs
- LANGFUSE_PUBLIC_KEY=${LANGFUSE_PUBLIC_KEY:-changeme}
- LANGFUSE_SECRET_KEY=${LANGFUSE_SECRET_KEY:-changeme}
- LANGFUSE_HOST=http://langfuse:3000
- OPENROUTER_API_KEY=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
command: ["--config", "/app/config.yaml", "--port", "4000"]
extra_hosts:
- "host.docker.internal:host-gateway"
depends_on:
- litellm-db
- langfuse
restart: always
kimi-agent:
build: ./kimi-agent
container_name: kimi-agent
volumes:
- /home/alvis/kimi-workspace:/workspace
- kimi-agent-home:/root/.kimi-code
restart: unless-stopped
langfuse-db:
image: postgres:16-alpine
container_name: langfuse-db
environment:
- POSTGRES_DB=langfuse
- POSTGRES_USER=langfuse
- POSTGRES_PASSWORD=langfuse
volumes:
- /mnt/ssd/dbs/langfuse/postgres:/var/lib/postgresql/data
restart: always
langfuse:
image: ghcr.io/langfuse/langfuse:2
container_name: langfuse
ports:
- "3200:3000"
environment:
- DATABASE_URL=postgresql://langfuse:langfuse@langfuse-db:5432/langfuse
- NEXTAUTH_URL=https://lf.alogins.net
- NEXTAUTH_SECRET=532a746b24ac40afa39f9d317031cab94d4d6881107ea3b1209b28020f1a9761
- SALT=7927b3b0092afe4542274940b557becea6418a5fed79f7acd25c3a789349fdc9
- AUTH_DISABLE_SIGNUP=true
depends_on:
- langfuse-db
restart: always
qdrant:
image: qdrant/qdrant
container_name: qdrant
ports:
- "6333:6333"
- "6334:6334"
restart: always
volumes:
- /mnt/ssd/dbs/qdrant:/qdrant/storage:z
faster-whisper:
image: fedirz/faster-whisper-server:latest-cuda
container_name: faster-whisper
runtime: nvidia
ports:
- "8880:8000"
environment:
- WHISPER__MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
- WHISPER__INFERENCE_DEVICE=cuda
- WHISPER__COMPUTE_TYPE=int8
- WHISPER__LANGUAGE=ru
- NVIDIA_VISIBLE_DEVICES=all
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
volumes:
- /mnt/ssd/ai/faster-whisper:/root/.cache/huggingface
restart: always
silero-tts:
build: ./silero-tts
container_name: silero-tts
ports:
- "8881:8881"
volumes:
- /mnt/ssd/ai/silero-tts:/cache/torch
restart: always
pipecat:
build: ./pipecat
container_name: pipecat
ports:
- "8882:8882"
environment:
- LIVEKIT_URL=ws://host.docker.internal:7880
- LIVEKIT_PUBLIC_URL=wss://lk.alogins.net
- LIVEKIT_API_KEY=devkey
- LIVEKIT_SECRET=ef3ef4b903ca8469b09b2dd7ab6af529c4d2f3c95668f53832fc351cf67777a9
- ADOLF_URL=http://host.docker.internal:8000/v1
- STT_URL=http://host.docker.internal:8880/v1
- TTS_URL=http://host.docker.internal:8881/v1
- STT_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
- TTS_VOICE=onyx
extra_hosts:
- "host.docker.internal:host-gateway"
restart: unless-stopped
# Adolf — OpenClaw fork (Matrix-first personal assistant). Skeleton only:
# real config (Matrix channel, SOUL.md, model provider -> adolf-llm:8010) is
# wired in P6. Not started until its config/keys exist. Source: /home/alvis/adolf.
adolf:
build: ../../adolf
image: adolf:local
container_name: adolf
environment:
- HOME=/home/node
- OPENCLAW_HOME=/home/node
- OPENCLAW_STATE_DIR=/home/node/.openclaw
- OPENCLAW_CONFIG_PATH=/home/node/.openclaw/openclaw.json
- OPENCLAW_CONFIG_DIR=/home/node/.openclaw
- OPENCLAW_WORKSPACE_DIR=/home/node/.openclaw/workspace
- OPENCLAW_GATEWAY_TOKEN=${ADOLF_GATEWAY_TOKEN:-}
- TZ=Europe/Riga
volumes:
- adolf-state:/home/node/.openclaw
extra_hosts:
- "host.docker.internal:host-gateway"
cap_drop:
- NET_RAW
- NET_ADMIN
security_opt:
- no-new-privileges:true
init: true
ports:
- "18789:18789"
- "18790:18790"
command:
["node", "dist/index.js", "gateway", "--bind", "lan", "--port", "18789"]
restart: unless-stopped
# cognee-llm — stateless one-shot Kimi-CLI wrapper for Cognee's batch cognify
# (P3). Opposite policy to kimi-agent: no resume, non-streaming, text-only.
# Note (SPIKE-FINDINGS gate 5): Cognee should DEFAULT its LLM to LiteLLM; this
# is the optional low-volume path. Needs `kimi login` in its own volume.
cognee-llm:
build: ./cognee-llm
container_name: cognee-llm
ports:
- "8011:8011"
volumes:
- cognee-llm-home:/root/.kimi-code
restart: unless-stopped
volumes:
kimi-agent-home:
adolf-state:
cognee-llm-home: