Leonid PershinandCursor 4081890b4c Support Ollama use: chat|memory and parallel embed beside VL. ...

Pull nomic-embed-text for Assistent memory, write ollama-roles.json, CPU Modelfile, and raise MAX_LOADED_MODELS/NUM_PARALLEL to 2.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-21 22:47:03 +03:00

..

remote

Support Ollama use: chat|memory and parallel embed beside VL.

2026-08-21 22:47:03 +03:00

__init__.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

__main__.py

first commit

2026-08-21 02:42:48 +03:00

access_card.py

Enhance error handling and state management in access card and session modules

2026-08-21 20:20:49 +03:00

balance.py

Implement balance monitoring and notification for Selectel API integration

2026-08-21 06:52:51 +03:00

bootstrap.py

Enhance LLM and SwarmUI integration with improved configuration options

2026-08-21 06:44:50 +03:00

capture.py

Add capture wanted and harden Assistent wanted-queue merge.

2026-08-21 21:29:00 +03:00

civitai.py

Add file size conversion and enhance Civitai job processing

2026-08-21 10:52:44 +03:00

cli.py

Add capture wanted and harden Assistent wanted-queue merge.

2026-08-21 21:29:00 +03:00

cloud.py

Update configuration and documentation for LLM support and local watchdog

2026-08-21 05:29:23 +03:00

config.py

Update configuration and environment probing for improved flexibility and compatibility

2026-08-21 09:06:27 +03:00

doctor.py

Update documentation to clarify GPU control commands

2026-08-21 20:12:03 +03:00

errors.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

hold.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

huggingface.py

Add Hugging Face support and enhance model resolution logic

2026-08-21 07:34:15 +03:00

idle_killer.py

Enhance CLI options and idle-killer functionality

2026-08-21 11:22:14 +03:00

inventory.py

Enhance GPU flavor scanning and update documentation

2026-08-21 04:03:28 +03:00

llm_runtime.py

Support Ollama use: chat|memory and parallel embed beside VL.

2026-08-21 22:47:03 +03:00

local_watchdog.py

Update documentation to clarify GPU control commands

2026-08-21 20:12:03 +03:00

lock.py

Add package data for GPU rent and update CLI documentation

2026-08-21 03:06:51 +03:00

manifests.py

Refactor LLM configuration to remove llamacpp support

2026-08-21 08:51:36 +03:00

notify.py

Update backend status handling and improve user notifications

2026-08-21 09:53:48 +03:00

os_client.py

Update configuration and documentation for LLM support and local watchdog

2026-08-21 05:29:23 +03:00

paths.py

Add assistent-personas support and enhance model merging functionality

2026-08-21 21:21:53 +03:00

payload.py

Add package data for GPU rent and update CLI documentation

2026-08-21 03:06:51 +03:00

perf_tiers.py

Support Ollama use: chat|memory and parallel embed beside VL.

2026-08-21 22:47:03 +03:00

pools.py

Refactor CLI and LLM runtime handling for improved user experience

2026-08-21 06:31:15 +03:00

prompts.py

Refactor CLI and LLM runtime handling for improved user experience

2026-08-21 06:31:15 +03:00

provision.py

Support Ollama use: chat|memory and parallel embed beside VL.

2026-08-21 22:47:03 +03:00

ready.py

Enhance Ollama model management and performance tuning

2026-08-21 14:20:06 +03:00

resize.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

session.py

Enhance error handling and state management in access card and session modules

2026-08-21 20:20:49 +03:00

setup_wizard.py

Add assistent-personas support and enhance model merging functionality

2026-08-21 21:21:53 +03:00

snapshot.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

ssh_keys.py

Refactor environment and configuration management

2026-08-21 03:20:18 +03:00

ssh_ops.py

Refactor GPU environment verification and SSH execution for improved flexibility

2026-08-21 09:02:07 +03:00

state.py

Refactor environment and configuration management

2026-08-21 03:20:18 +03:00

sync_files.py

Enhance SwarmUI integration and GPU environment verification

2026-08-21 07:09:20 +03:00

term.py

Enhance logging and timing in CLI and session operations

2026-08-21 08:03:04 +03:00

timing.py

Enhance logging and timing in CLI and session operations

2026-08-21 08:03:04 +03:00

tunnel.py

Warm Ollama into VRAM on up and tunnel so Assistent chat is not cold.

2026-08-21 20:47:14 +03:00

ux.py

Update documentation to clarify GPU control commands

2026-08-21 20:12:03 +03:00

varsfile.py

Update LLM support for llama.cpp and enhance configuration management

2026-08-21 06:25:12 +03:00