Context Management Python Packages

acryl-datahub

The Context Platform for your Data and AI Stack

acryl-datahub-airflow-plugin

The Context Platform for your Data and AI Stack

acryl-executor

Run DataHub metadata ingestion tasks remotely via subprocess isolation with S3 log storage

acryl-datahub-dagster-plugin

The Context Platform for your Data and AI Stack

acryl-datahub-gx-plugin

The Context Platform for your Data and AI Stack

cozempic

Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning

prefect-datahub

The Context Platform for your Data and AI Stack

datahub-agent-context

The Context Platform for your Data and AI Stack

piia-engram

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

hive-vault

Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP

kindex

Knowledge index that learns from your conversations

claude-ctx

Not an Amazon-style catalog or marketplace. ctx is a recommendation layer: bring your org tools or use the shipped graph to load the right skills, agents, MCPs, and harnesses only for the current dev window, cutting token bills and local compute waste: 79,958-node LLM-wiki graph, 68,494 skills, 467 agents, 10,790 MCPs, 207 harnesses.

memor-cli

Measured memory for coding agents — Claude Code, Codex, Copilot. Fire and forget, no API keys needed.

aictx

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop onboarding your coding agents like rookies every session.

second-brain-graph

A living, always-fresh, low-token map of any project: files, code imports, doc links, areas, decisions and git sessions, queried by AI and explored by humans in an offline 2D community map. Zero runtime deps, read-only, optional MCP.

contextweaver

Budget-aware context compilation and context firewall for tool-heavy AI agents.

neural-context-protocol

Bounded, persistent context for multi-agent pipelines. MCP-native. Claude · GPT · Gemini · Ollama. 13x token reduction.

leancontext

Trim the redundant tool output your AI agent re-sends every turn. Deterministic, type-aware token reduction with a fidelity score — never breaks the agent.

precis-mcp

MCP server giving LLM agents a seven-verb API over papers, documents, code, state, patents, and cached web/Wolfram/YouTube tool calls

engrim

Local-first memory for Claude Code — remembers your decisions and the why, reloads the relevant slice every session. No API key.

aicodeprep-gui

Surgical context engineering with a nice UI, Windows, Mac, Linux, BSD, anywhere where python & Qt run

carrymem

Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zero-dependency, local-first, 85% PrefEval accuracy.

baton-pass

A tool that allows users to never lose context between sessions through a standard Baton.md file translated to each vibecoding tool such as claude code, cursor, gemini, copilot,

a2cr-mcp

MCP server for client-encrypted AI agent handoffs with WorkBaton and WorkStash