Mindcore Memory
by woshilaoheicommunityv0.1.11
1
3
An MCP memory server that stores persistent agent memories locally and supports retrieval with hybrid BM25 + FAISS search. It also exposes resilience and observability features such as circuit breaker behavior, retry/backoff, SLO tracking, and Prometheus metrics.
From the registry: AI long-term memory MCP server with importance scoring and confidence calibration
Install & configure
Prerequisites
- requiredInstall Python packageInstall the published MindCore Memory package from PyPI. Optionally install extras for semantic search or encryption support if needed.
https://pypi.org/project/mindcore-memory/$ pip install mindcore-memory
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `mindcore-memory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python package** — Install the published MindCore Memory package from PyPI. Optionally install extras for semantic search or encryption support if needed. Run: `pip install mindcore-memory` (https://pypi.org/project/mindcore-memory/)
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","mindcore_memory.server"]
- optional environment variables:
- `MINDCORE_MEMORY_PATH`: Path where MindCore stores persistent memory data. The README example sets this to a local directory for cross-session persistence. (example: `<your-memory-directory>`)
Note: The README's Quick Start also shows launching via the installed CLI command `mindcore-memory`, but the explicit MCP config example uses `python -m mindcore_memory.server`, which is the canonical stdio shape extracted here. The server README mentions support for HTTP transport, but provides no usable HTTP configuration details, so only stdio config is included. Optional package extras mentioned: `mindcore-memory[semantic]` for FAISS-based semantic search and `mindcore-memory[encrypt]` for encryption at rest.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: The README's Quick Start also shows launching via the installed CLI command `mindcore-memory`, but the explicit MCP config example uses `python -m mindcore_memory.server`, which is the canonical stdio shape extracted here. The server README mentions support for HTTP transport, but provides no usable HTTP configuration details, so only stdio config is included. Optional package extras mentioned: `mindcore-memory[semantic]` for FAISS-based semantic search and `mindcore-memory[encrypt]` for encryption at rest.
Tools (9)
memory_store
Persist a memory with automatic BND evaluation.
memory_recall
Search memories using hybrid BM25+FAISS search.
memory_context
Build an LLM context window from stored memories.
memory_update_confidence
Adjust the confidence value of a memory.
memory_delete
Remove a memory by ID.
memory_stats
Return system statistics.
bnd_check
Evaluate content with the 4D boundary scoring system and anti-chain checks.
bnd_stats
Return BND manager statistics such as acceptance rate and score metrics.
deduce
Extract patterns or deductions from high-quality memories.
Environment variables
MINDCORE_MEMORY_PATHrequiredDirectory path where the server stores its local memory data.Packages
mindcore-memory
pypiv0.1.11transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Jun 14, 2026
- Last commit
- Jun 16, 2026
- Registry name
- io.github.woshilaohei/mindcore-memory
Categories
Related Servers
Claude Flow
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
68.0k
Codebase Memory Mcp
Persistent codebase knowledge graph. Survives session restarts and context compaction.
39.2k
Serena
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
28.1k