distil
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
具有质量契约的压缩——面向代理运行时的缓存感知、因果剪枝LLM上下文压缩，在7个领域内经认证不劣于原版。兼容任何SDK。
How to install
git clone https://github.com/dshakes/distil ~/.claude/skills/distil Recommendation signals
Meta
- License
- NOASSERTION
- Language
- Python
- GitHub stars
- 16
- mo. downloads
- –
- Last push
- 2026-09-24
- Created
- 2026-06-21
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:punkpeye/awesome-mcp-servers
- Topics
- agents, ai-infrastructure, anthropic, claude-code, conformal-prediction, context-compression, cost-optimization, llm, llmops, mcp, openai, prompt-caching, token-optimization
Related plugins
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
dsh-mnemon
omdsh-dev/dsh-mnemon
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
get-shit-done
gsd-build/get-shit-done
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.