loading…
Search for a command to run...
loading…
A high-performance control plane for Ollama-based local LLM sessions with background memory consolidation, hybrid cloud planning, and real-time fleet monitoring
A high-performance control plane for Ollama-based local LLM sessions with background memory consolidation, hybrid cloud planning, and real-time fleet monitoring.
📖 Installation Guide — quick start, manual setup, and troubleshooting
A high-performance control plane for Ollama-based local LLM sessions, with background memory consolidation (KAIROS), hybrid cloud planning (ULTRAPLAN), and real-time fleet monitoring. Optimized for RTX 4090 environments.
MEMORY.md using asynchronous background cycles. Configurable poll interval and consolidation budget. State persists across restarts.send_multimodal tool. Works with any vision-capable Ollama model.git clone https://github.com/sandraschi/openclaude-mcp
cd openclaude-mcp
just
This opens an interactive dashboard showing all available commands. Run just bootstrap to install dependencies, then just serve or just dev to start.
If you don't have just installed:
.\setup.ps1
.\start.ps1
http://localhost:10932/ssehttp://localhost:10933http://localhost:10932/api/events (SSE push)http://localhost:10932/api/health
Or with Docker:
docker compose up| Tool | Action |
|---|---|
start_session |
Initialize a new Ollama session |
send_prompt |
Execute a prompt in an active session |
send_multimodal |
Send text + images to a session (png, jpeg, webp, gif) |
session_status |
Get output/status/usage/elapsed of a session |
list_sessions |
List all active sessions |
stop_session |
Stop and clean up a session |
kairos_enable |
Activate background memory consolidation |
kairos_disable |
Halt background memory consolidation |
kairos_log |
Retrieve KAIROS consolidation log |
list_models |
Inventory of available Ollama models |
set_default_model |
Set default model for new sessions |
model_status |
Check VRAM and load status |
ultraplan |
Hybrid cloud/local planning cycle |
fleet_dashboard |
Prefab UI fleet status overview |
fleet_status |
Raw fleet status JSON |
caregiver_alert |
[KID-SAFE] Notify caregivers of high-risk interaction |
┌─────────────────┐
│ Claude Desktop │── SSE ──────┐
│ Cursor / VSCode │ │
└─────────────────┘ │
▼
┌──────────────┐ REST ┌────────────────────────────┐ stdio (NDJSON) ┌──────────────────┐
│ React Webapp│───────►│ server.py (FastMCP 3.2) │◄────────────────│ OpenClaude CLI │
│ (SSE push) │◄───────│ + SessionStore │ subprocess │ (Node.js/Bun) │
└──────────────┘ │ + ModelRouter │◄───────────────►│ + Ollama :11434 │
│ + KairosController │ └──────────────────┘
│ + SessionPersistence │
│ + SSE Event Bus │
└────────────────────────────┘
| Variable | Default | Description |
|---|---|---|
OPENCLAUDE_MCP_PORT |
10932 |
Backend port |
OPENCLAUDE_MCP_TOKEN |
— | REST auth token (disable if unset) |
OPENCLAUDE_DIR |
D:\Dev\repos\external\openclaude |
OpenClaude source path |
OPENCLAUDE_ULTRAPLAN_MODEL |
claude-sonnet-4-6 |
Anthropic model for ULTRAPLAN |
OPENCLAUDE_CONFIG_DIR |
~/.config/openclaude |
Persistence directory |
KAIROS_POLL_SECONDS |
30 |
KAIROS daemon poll interval |
KAIROS_MAX_CONSOLIDATIONS |
100 |
Max consolidations per session |
CAREGIVER_WEBHOOK_URL |
— | Webhook for caregiver alerts |
uvgemma4:26b, qwen3.5:35b-a3b)uv run pytest # 79 tests (unit + smoke + integration + e2e)
uv run pytest tests/unit/ # fast, no external deps
uv run pytest tests/e2e/ # Anthropic API mocked via respx
MIT
Выполни в терминале:
claude mcp add openclaude-mcp-server -- npx Безопасность
Низкий рискАвтоматическая эвристика по публичным данным — не гарантия безопасности.