Context Window Python Packages

headroom-ai

The Context Optimization Layer for LLM Applications

tokenpak

Slash LLM costs with intelligent context compression, smart routing, and cost tracking

ultracontext

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

infiniloom

High-performance repository context generator for LLMs - Transform codebases into optimized formats for Claude, GPT-4/5, Gemini, and other LLMs

kopipasta

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

neuralmind

Adaptive Neural Knowledge System + PostToolUse compression hooks. Two-phase token optimization (retrieval + consumption) for Claude Code.

bellamem

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

treemapper

Export codebase structure and contents for AI/LLM context

unclog

Audit your Claude Code installation and clear context-window bloat. Local-only.

tailspin-ai

Token optimization and compression for Claude API requests

llmfs

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

claude-mem

Zero-dependency session recall for Claude Code — instant memory across compactions, ~50 tokens per prompt

memory-vault

Persistent, context-aware memory system for AI assistants

ghdigest

Fetch any GitHub repository into a single LLM-ready digest — metadata, directory tree, file contents, and built-in AI analysis.

contextcore

Unified local search and indexing for Claude and other AI tools

mansnip-kristopolous

Inject relevant documentation into your prompts: 98% savings.

deeprepo-cli

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

codeconcat

Prepare your code for AI. Concatenates your project into a clean, markdown-formatted file with file trees and granular filtering options.

reguliq-diagnostics

Diagnoses context degradation in LLM agents — beginning-anchored retrieval, cliff detection, tool burial, and more

cognitive-cache

Optimal context window selection for LLM coding tools. Treats context as a constrained optimization problem, not retrieval. Beats RAG, grep, and LLM-triage baselines on real GitHub issues.

agent-recall-ai

Your AI agent never starts over again. Framework-agnostic session checkpointing - survive context limits, cost overruns, and session death.

mansnip

Inject relevant documentation into your prompts: 98% savings.

voice-budget

The only voice agent context manager with a TTFT feedback loop

tokenpak-paid-stub

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