kimi-memory
by cbuntingde
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIMI_MEMORY_DREAM | No | Set to off to skip staged consolidation. Existing queued jobs stay queryable. | on |
| KIMI_MEMORY_EMBEDDINGS | No | Set to off to skip the embedding encoder. Recall falls back to keyword search only. | on |
| KIMI_MEMORY_CONSOLIDATE | No | Set to off to skip the inline synthesis and merge pass at session start. | on |
| KIMI_MEMORY_AUTO_EXTRACT | No | Set to off to disable the assistant-driven memory extraction at the end of each turn. | on |
| KIMI_MEMORY_LEGACY_SUBSYSTEMS | No | Set to off to hide the deprecated tool groups (access control, tier and persona, code graph). | on |
| KIMI_MEMORY_AUTO_RESET_ON_RECLONE | No | Auto-wipe per-project rows when SessionStart detects a re-clone. Set to off to keep a manual hint instead. | on |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues