ClawMem
by yoloshii
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAWMEM_BIN | No | Path to clawmem binary (used by Hermes plugin). | |
| CLAWMEM_VAULTS | No | JSON object mapping vault names to paths for multi-vault setup. | |
| CLAWMEM_LLM_URL | No | LLM server URL for intent/query/A-MEM. Without it, falls to node-llama-cpp (if allowed). | http://localhost:8089 |
| CLAWMEM_PROFILE | No | Retrieval profile: speed, balanced, or deep. | balanced |
| CLAWMEM_API_TOKEN | No | Bearer token for HTTP REST API authentication. If unset, access is open (localhost-only by default). | |
| CLAWMEM_EMBED_URL | No | Embedding server URL. Uses llama-server (GPU or CPU) or cloud API. Falls back to in-process node-llama-cpp if unset. | http://localhost:8088 |
| CLAWMEM_LLM_MODEL | No | Model name sent to the configured LLM endpoint. Override for OpenAI-compatible proxies such as gpt-5.4-mini. | qwen3 |
| CLAWMEM_HEAVY_LANE | No | Enable the v0.8.2 background maintenance lane for consolidation + deductive synthesis. | false |
| CLAWMEM_RERANK_URL | No | Reranker server URL. Without it, falls to node-llama-cpp (if allowed). | http://localhost:8090 |
| CLAWMEM_EMBED_MODEL | No | Model name for embedding requests. Override for cloud providers (e.g. jina-embeddings-v5-text-small). | embedding |
| CLAWMEM_ENABLE_AMEM | No | A-MEM note construction + link generation during indexing. | enabled |
| CLAWMEM_LLM_NO_THINK | No | Append /no_think to remote LLM prompts. Set to false for standard OpenAI models and other endpoints that reject or treat the Qwen-style suffix as literal prompt text. | true |
| CLAWMEM_EMBED_API_KEY | No | API key for cloud embedding. Enables cloud mode: batch embedding, provider-specific params, TPM-aware pacing. | |
| CLAWMEM_EMBED_MAX_CHARS | No | Maximum characters per document for local embedding truncation. | 6000 |
| CLAWMEM_EMBED_TPM_LIMIT | No | Tokens-per-minute limit for cloud embedding pacing. Match to your provider tier. | 100000 |
| CLAWMEM_NO_LOCAL_MODELS | No | Block node-llama-cpp from auto-downloading GGUF models. Set true for remote-only setups where you want fail-fast on unreachable endpoints. | false |
| CLAWMEM_EMBED_DIMENSIONS | No | Output dimensions for OpenAI text-embedding-3-* Matryoshka models (e.g. 512, 1024). | |
| CLAWMEM_MERGE_SCORE_NORMAL | No | Phase 2 consolidation merge-safety threshold when candidate and existing anchors align. Merges above this normalized 3-gram cosine score are allowed. | 0.93 |
| CLAWMEM_MERGE_SCORE_STRICT | No | Strictest merge-safety threshold — fallback when anchor sets are ambiguous. | 0.98 |
| CLAWMEM_MERGE_GUARD_DRY_RUN | No | When true, Phase 2 merge-safety rejections are logged but not enforced — use for calibration before enabling the gate. | false |
| CLAWMEM_CONTRADICTION_POLICY | No | Merge-time contradiction gate policy. link inserts a new row + contradicts edge (default). supersede marks the old row status='inactive'. | link |
| CLAWMEM_ENABLE_CONSOLIDATION | No | Background worker for backlog A-MEM enrichment. | disabled |
| CLAWMEM_LLM_REASONING_EFFORT | No | Optional top-level reasoning_effort field for Chat Completions endpoints that support it (for example OpenAI reasoning models). Leave unset for llama-server/vLLM unless your serving stack explicitly accepts that field. | |
| CLAWMEM_CONSOLIDATION_INTERVAL | No | Worker interval in ms (min 15000). | 300000 |
| CLAWMEM_CONTRADICTION_MIN_CONFIDENCE | No | Minimum combined heuristic + LLM confidence required before the contradiction gate blocks a merge. | 0.5 |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yoloshii/ClawMem'
If you have feedback or need assistance with the MCP directory API, please join our Discord server