📡 MCP Radar

lna-lab/distill-kura

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.

9 stars
0 forks
Python
momentum ▲ 18.0
created 2026-08-21
on radar since 2026-08-22
star trend 3 → 9 since 2026-08-22
agent-memorydsh-pluginllm-memorylong-term-memorymcp-serverrag
View on GitHub ↗

About distill-kura

A long-term memory for agents that is distilled, not accumulated. Recall works by meaning, writing is gated by evidence, and one server can hold several separate memories — one per agent mode — so switching mode switches what the agent remembers.

Ships as a DeepSeek Harness plugin, an MCP server for any other host, an HTTP service, and a Python library. Standard library only; no vector database, no embeddings, no framework.

Two failures kill an agent's long-term memory, and they kill it from opposite sides.

Retrieval by keyword misses the thing you needed. A question about "SSD inference chips" shares no word with a memory titled "running the 2.6T model off an SSD tier" — yet they are the same subject. Word search returns nothing; the agent answers from nowhere. The fix here is not embeddings but recognition: the entire index (one line per memory, written as a recognition trigger) goes into one prompt, and a small model names what bears on the question. An index of ~500 memories is around 6k tokens — a few percent of a modern context window, and it sits in the prefix cache.

Writing everything poisons the store. An agent asserts something; a naive distiller records the assertion as a fact; the next agent reads it back as ground truth and repeats it with more confidence. That loop is self-reinforcing, and prompt instructions do not stop it — measured, not assumed. So the write path is gated by deterministic Python: every candidate memory must carry quotes that exist character-for-character in the raw material, tagged with where they came from.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/lna-lab--distill-kura.html)

Related MCP servers

2672243194/agentbrain

Local-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.

⭐ 5Python
DanceNitra/mnemo

Zero-dependency agent memory + MCP server. Value-ranked recall, consolidation, and a first-class correction & erasure channel (revert, lineage-aware retraction, tamper-evident receipts). Measured inte

⭐ 4Python
Pseudogiant-xr/Pseudolife-MCP

Persistent long-term memory for Claude — an MCP server with an associative memory bank, a canonical-fact cortex, sleep-like dream consolidation, and a web console. Not quite alive.

⭐ 4Python
mienetic/mnema

🧠 Mnema — Long-term memory for AI via MCP × Vector DB. Pluggable backends, hybrid search, Auto Dream consolidation, CLI + REST API + SDK.

⭐ 3Python
17861102832/wanyimem

为了服务于大众

⭐ 3Python
rwnalds/engram

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, n

⭐ 4TypeScript

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.