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 |
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 | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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