Context Window Python Packages

headroom-ai

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

tokenpak

Drop-in HTTP proxy that compresses LLM context, optimizes cache hits, routes smart, and tracks every dollar. Zero SDK changes required.

ultracontext

Open Source Context infrastructure for AI agents. Auto-capture and share your agents' context everywhere.

mnemara

Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.

neuralmind

🧠 Adaptive Neural Knowledge System - 40-70x token reduction for AI code understanding

reducethemtokens

Compress any code repo into a compact skeleton to reduce LLM token usage. 90%+ reduction with full structural retention.

gemma-mnemara

Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.

infiniloom

Python bindings for Infiniloom - AST-aware code context engine for RAG and vector databases. Tree-sitter parsing, PageRank ranking, BLAKE3 content-addressable chunks, 27+ tokenizers.

llmfs

Filesystem-based persistent memory for LLMs and AI agents -- unlimited context windows without lossy summarization

treemapper

Smart git diff context for LLMs - selects the minimal code fragments needed to understand a change. Also exports full codebase in YAML/JSON/MD.

claude-mem

Persistent session memory for Claude Code. Indexes your session history locally and injects context automatically. Zero dependencies.

kopipasta

`cat project | LLM | patch`. Transparent context control and interactive patching for terminal-centric LLM workflows.

tailspin-ai

Token optimization and compression for Claude API requests

unclog

Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

cognitive-cache

Optimal context orchestration for LLMs

bellamem

Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact.

agentfit-py

Python port of @mukundakatta/agentfit: fit your messages into the LLM context window

codeconcat

A tool to concatenate folders into a single text file, respecting .gitignore and using optional config.

agent-recall-ai

Structured session checkpointing for AI agents — survive context limits, cost overruns, and session death

reguliq-diagnostics

Diagnose context degradation in LLM agents — find where memory breaks and how to fix it

deeprepo-cli

AI project memory for coding tools. Eliminates the cold start tax in every AI session.

tokenpak-paid-stub

Drop-in HTTP proxy that compresses LLM context, optimizes cache hits, routes smart, and tracks every dollar. Zero SDK changes required.

context-bench

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

contextcore

ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)