prompt-compression

Open repos and models their makers tagged prompt-compression, most starred first. The same for everyone.

AI on my own machineRepo

llmtrim

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

  • 276
  • Rust
  • MPL-2.0
  • 8 d ago
fkieneTake it
AI agentsRepo

9routerx

9RouterX (9R Next Go Generation): Single-binary Go AI router, LLM gateway & 20-40% token saver. Route Claude Code, Cursor & Codex across 155 providers, 28 OAuth & 248 free models (24 keyless) — OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama & MCP.

  • 255
  • Go
  • 2 d ago
yanstd888Take it
AI on my own machineRepo

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。

  • 113
  • TypeScript
  • MIT
  • 3 wk ago
Sev7eEn7Take it
Developer toolsRepo

flint

Help AI agents use fewer tokens and keep more useful context. Reversible code, JSON and text compression, persistent memory, focused reads and version-aware edits.

  • 15
  • Python
  • Apache-2.0
  • 4 wk ago
JustVuggTake it
Search GitHub and Hugging Face for prompt-compression

Get , open it once and sign in. Then come back here and press the button again.