Prompt Compression Python Packages

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).

llm-zip

Self-hosted HTTP sidecar for LLM context compression. Reduce token costs 3–5× before calling any AI API — powered by LLMLingua-2 and MarkItDown. No proxy, no API keys, no GPU required.

latent-gate

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

agentmesh-proxy

The governance plane for AI agents — policy, budget, and audit across every framework. Istio for AI agents.

claw-compactor

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

llm-token-surgeon

Cut your LLM API bill by 30-70% with zero accuracy loss

leanctx

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

foveance

Cut your LLM token bill 60%+ without changing your code or your answers. Drop-in proxy + one-line Python API that auto-compresses agent context for Claude Code, Codex, OpenAI, Anthropic & Ollama. pip install foveance

contextcrunch

Access to the ContextCrunch Prompt Compression API from Python

supercompress

SuperCompress — learned context compression for LLMs.

context-bench

Benchmark any system that transforms LLM context: compressors, RAG rerankers, memory managers, and more.

llama-index-postprocessor-vecr

LlamaIndex postprocessor for vecr-compress: deterministic retention-guaranteed node compression.

cutia

CUTIA: compress prompts while preserving quality

vecr-compress

Auditable, deterministic context compression for LLMs — structured data survives by regex whitelist, every decision logged.

langchain-vecr-compress

Deterministic, auditable LLM context compression — regex whitelist guarantees structured facts (IDs, URLs, dates, code) survive. Two layers: retention + heuristic knapsack.

promptminify

Minify LLM prompts to save tokens — domain-aware, tiktoken-validated, zero regressions.