prompt-compression 开源项目推荐（185 个）

open-compress /claw-compactor

14-用于LLM令牌压缩的Fusion Pipeline阶段-可逆压缩、AST感知代码分析、智能内容路由。零LLM推理成本。麻省理工学院获得许可。

gglucass /headroom-desktop

MacOS和Windows上的菜单栏应用程序可将Claude Code和Codex代币成本降低约50%

jia-gao /leanctx

生产LLM应用程序的直接提示压缩。无需更改代码即可将代币账单削减40-60%。Python SDK，LLMLingua-2，麻省理工学院。

fkiene /llmtrim

本地代理会压缩你的LLM API请求，让你支付更低的费用，且答案不变。在提示、历史、工具输出和代码中修剪浪费的代币，在发送前：-31%输入 / -74% 输出，实时测量。任何供应商，没有额外的模型电话。还有MCP服务器和可嵌入库（Rust、Python、Ruby、Kotlin、Swift、JS/TS）。

pleasedodisturb /awesome-llm-token-optimization

A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

kaderkck /hewn-forge

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

swellweb /reame

CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accurate than tuning the engine. MIT, benchmarks and failures included.

Sev7eEn7 /dsh-sieve

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

baiibayu /srouter

Never hit rate limits again. One OpenAI-compatible endpoint for 60+ providers & 1,200+ models — smart auto-fallback, prompt compression, 60-language dashboard. Plug into Claude Code, Cursor, Codex & more. Free, open-source, self-hosted.

NodeNestor /claude-rolling-context

Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.

atjsh /llmlingua-2-js

JavaScript/TypeScript implementation of LLMLingua-2 (Experimental)

KathanModh259 /latent-gate

MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tokens on a mixed dev corpus, 90%+ on logs.

Thanatos9404 /llmslim

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

chappyasel /meta-kb

A self-improving knowledge base about LLM agent infrastructure

Aimaghsoodi /foveance

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line Python API for Claude Code, Codex, Cursor, OpenAI, Anthropic & Ollama. pip install foveance

centminmod /or-cli

Python command-line tool for interacting with AI models through the OpenRouter API/Cloudflare AI Gateway, or local self-hosted Ollama. Optionally support Microsoft LLMLingua prompt token compression

sriinnu /clipforge-PAKT

Lossless-first prompt compression for JSON, YAML, CSV, and Markdown. Library, CLI, MCP server, desktop app, and browser extension.

danielle34 /cavewoman

Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compression costs in dollars, accuracy, and whether the reasoning changes. Compress the output not the prompt!! 9 models, 5 benchmarks, 10 languages. EMNLP 2026 Main

lucasmartins-ai /lcc

Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claude Code plugin. MIT.

bladysh /exprompt

Reverse T9 for LLMs. Free, open-source prompt compressor for your AI prompts and agents.