PromptThrift MCP

PromptThrift MCP: Smart Token Compression for LLM Apps

Cut 70-90% of your LLM API costs with intelligent conversation compression. Now withGemma 4 local compression: smarter summaries, zero API cost.

⭐If this saves you money, star this repo!⭐

Every LLM API call resends yourentire conversation history. A 20-turn chat costs 6x more per call than a 3-turn one, so you're paying for the same old messages over and over.

Turn 1: ████ 700 tokens ($0.002) Turn 5: ████████████████ 4,300 tokens ($0.013) Turn 20: ████████████████████████████████████████ 12,500 tokens ($0.038) ↑ You're paying for THIS every call

PromptThrift is an MCP server with 4 tools to slash your API costs:

pip install git+https://github.com/woling-dev/promptthrift-mcp.git

git clone https://github.com/woling-dev/promptthrift-mcp.git cd promptthrift-mcp pip install -e .

For smarter AI-powered compression (free, runs locally):

# Install Ollama: https://ollama.com ollama pull gemma4:e4b

PromptThrift auto-detects Ollama. If running → uses Gemma 4 for compression. If not → falls back to fast heuristic compression. Zero config needed.

{ "mcpServers": { "promptthrift": { "command": "python", "args": ["/path/to/promptthrift-mcp/server.py"] } } }

{ "mcpServers": { "promptthrift": { "command": "python", "args": ["/path/to/promptthrift-mcp/server.py"] } } }

An AI coding assistant debugging a complex issue over 30+ turns:

Before compression (sent every API call):

User: My Next.js app throws a hydration error on the /dashboard page. Asst: That usually means server and client HTML don't match. Can you share the component? User: [pastes 50 lines of DashboardLayout.tsx] Asst: I see the issue, you're using new Date() directly in render, which differs between server and client. Let me also check your data fetching... User: I also get a warning about useEffect running twice. Asst: That's React 18 Strict Mode. Not related to hydration. Let me trace the real bug... User: Wait, there's also a flash of unstyled content on first load. Asst: That's a separate CSS loading order issue. Let me address both... [... 25 more turns of debugging, trying fixes, checking logs ...] User: OK it's fixed now! But I want to add dark mode next. Asst: Great! For dark mode with Next.js + Tailwind, here are three approaches...

~8,500 tokens after 30 turns,and growing every single API call

[Compressed history] Resolved Next.js hydration error in DashboardLayout.tsx caused by Date() in render (fixed with useEffect). Unrelated: React 18 Strict Mode double-fire (expected), CSS flash (fixed via loading order). User now wants to add dark mode to Next.js + Tailwind app. [End compressed history] [Recent turns preserved, last 4 turns intact]

~1,200 tokens.86% saved on every subsequent call

Cost impact at scale (Claude Sonnet @ $3/MTok):

Some facts mustneverbe lost during compression: user names, critical preferences, key decisions. Pin them:

You: "Pin the fact that this customer is allergic to nuts" → promptthrift_pin_facts(action="add", facts=["Customer is allergic to nuts"]) → This fact will appear in ALL future compressed summaries, guaranteed.

Before (every API call sends ALL of this): ┌──────────────────────────────────┐ │ System prompt (500 tokens) │ │ Turn 1: user+asst (600 tokens) │ ← Repeated every call │ Turn 2: user+asst (600 tokens) │ ← Repeated every call │ ... │ │ Turn 8: user+asst (600 tokens) │ ← Repeated every call │ Turn 9: user+asst (new) │ │ Turn 10: user (new) │ └──────────────────────────────────┘ Total: ~6,500 tokens per call After PromptThrift compression: ┌──────────────────────────────────┐ │ System prompt (500 tokens) │ │ [Pinned facts] (50 tokens) │ ← Always preserved │ Compressed summary │ ← Turns 1-8 in 200 tokens! │ Turn 9: user+asst (kept) │ │ Turn 10: user (kept) │ └──────────────────────────────────┘ Total: ~1,750 tokens per call (73% saved!)

PromptThrift automatically uses the best available method. Install Ollama + Gemma 4 for maximum compression quality.

Compression effectiveness scales with conversation length and redundancy:

Why?Short, dense conversations have little filler to remove. Longer conversations accumulate greetings, repeated context, exploratory dead-ends, and verbose explanations, and those are exactly what the compressor strips away. A 30-turn debugging session with code snippets, back-and-forth troubleshooting, and final resolution compresses dramatically because only the conclusion and key decisions matter for future context.

Rule of thumb:Start compressing after 8-10 turns for best results.

- All data processedlocallyby default. Nothing leaves your machine
- Ollama compression runs 100% on your hardware
- Post-compression sanitizerstrips prompt injection patterns from summaries
- API keys read from environment variables only, never hardcoded
- No persistent storage, no telemetry, no third-party calls

- Heuristic conversation compression
- Multi-model token counting (14 models)
- Intelligent model routing
- Gemma 4 local LLM compression via Ollama
- Pinned facts (Never-Compress List)
- Post-compression security sanitizer
- Cloud-based compression (Anthropic/OpenAI API fallback)
- Prompt caching optimization advisor
- Web dashboard for usage analytics
- VS Code extension

PRs welcome! This project uses MIT license. Fork it, improve it, ship it.

BrandDefender.aiis the product line ofWolin Global Media (沃嶺國際媒體), a Taiwan-based AI infrastructure studio helping brands get discovered, understood, and recommended by AI systems.

🔍AEO Consulting (Answer Engine Optimization)Get your brand correctly cited by ChatGPT, Gemini, Perplexity, and Claude. We implement JSON-LD schema, optimize content structure, and monitor AI search presence for Taiwan food, tea, beauty, and lifestyle brands.

- Website:https://aibranddefender.com/
- Free AI brand scan:https://app.aibranddefender.com/

- This repois one of them.
- Sibling tools:promptforge·promptthrift-mcp

- 📧Email:service@wolinglobal.com
- 💬LINE:@886upktf
- 🌐Website:https://aibranddefender.com/
- 🐙GitHub:https://github.com/woling-dev

台灣品牌想做 AEO audit：我們提供 ChatGPT / Gemini / Perplexity 全面掃描 + JSON-LD 修補 + 月度監測。Email或LINE直接找我們聊。

MIT License. Free for personal and commercial use.

Anchor Browser (https://anchorbrowser.io) is secure infrastructure for computer-use agents — stealth cloud browsers, authentication, captcha bypass, and a hosted MCP server for Cursor, Claude, and Windsurf.