No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by lna-lab · MCP Server · ★ 53
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is distill-kura safe to install? View the security audit →
蒸留蔵 — 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. Why this exists 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
| Stars | 53 |
| Forks | 7 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 67.4864488538126/100 |
| Last Updated | 2026-09-30 |
| Created | 2026-08-21 |
| Platforms | mcp, python |
| Est. Tokens | ~22k |
Looking for a distill-kura alternative? If you're comparing distill-kura with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn fro
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited n
The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.
Explore other popular mcp server tools:
distill-kura is 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.. It is categorized as a MCP Server with 53 GitHub stars.
distill-kura is primarily written in Python. It covers topics such as agent-memory, dsh-plugin, llm-memory.
You can find installation instructions and usage details in the distill-kura GitHub repository at github.com/lna-lab/distill-kura. The project has 53 stars and 7 forks, indicating an active community.
distill-kura is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to distill-kura on Agent Skills Hub include claude-mem-lite, YourMemory, mengram. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: