localmind
A fully local AI stack that provides OpenAI/Anthropic-compatible LLM API, embeddings, mem0 memory, and second-brain RAG via MCP tools, all running independently with no cloud dependencies.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
shaul1991
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
BASE_URLBRAIN_BATCH/ BRAIN_CONCURRENCY / BRAIN_CHUNK_SIZE 32 / 4 / 2000 인덱싱 튜닝BRAIN_CHUNK_SIZEBRAIN_BATCH / BRAIN_CONCURRENCY / 32 / 4 / 2000 인덱싱 튜닝BRAIN_CONCURRENCYBRAIN_BATCH / / BRAIN_CHUNK_SIZE 32 / 4 / 2000 인덱싱 튜닝BRAIN_INDEXNOTES_DIR>/.brain-index.json 임베딩 인덱스 위치. git/싱크 볼트를 안 더럽히려면 밖으로CLAUDE_JOB_DIREMBEDDINGS_KEYEMBEDDINGS_MODELtext-embedding-3-small (게이트웨이가 bge-m3로 매핑)EMBEDDINGS_URLbge-m3 그대로 + GPU/전용 임베딩 서버(TEI/Infinity) 로 교체 (한국어 품질 유지하며 가속, 권장)EMBED_RETRIESEMBED_TIMEOUT_MSLITELLM_MASTER_KEYOPENAI_API_KEY=sk-local # 값LOCALMIND_API_KEY(없음) localmind 인증 시LOCALMIND_URLMCP_DEFAULT_MODELsonnet ask / ask_brain 기본 모델MCP_HTTP_ALLOW_NOAUTHMCP_HTTP_HOSTMCP_HTTP_PORT / 8788 / 0.0.0.0 원격 MCP 바인딩MCP_HTTP_PORT/ MCP_HTTP_HOST 8788 / 0.0.0.0 원격 MCP 바인딩MCP_HTTP_TOKEN.env에 설정 후 make up-mcp → 노트북에서 서버별 원격 MCP로 접속 (아래 디바이스/서버별 관리)MCP_HTTP_URLMCP_INSTANCE서버마다 =서버명으로 독립 인스턴스 → 그 서버의 자원/메모리/노트를 로컬에서 관리MEMORY_BACKUP_FILEMODELsonnet npm run smoke # claude 백엔드NOTES_DIR"env": { "": "/내/노트/폴더", "OPENMEMORY_USER": "내이름" }OPENMEMORY_URLOPENMEMORY_USER"env": { "NOTES_DIR": "/내/노트/폴더", "": "내이름" }Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
7/7 tools missing one or more hints — whoami (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ask (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); remember (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +4 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
6/7 tool handlers declare input schemas (86%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
6/7 tool handlers wrap calls in try/catch (86%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/shaul1991/localmind)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check