Context Engineering 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.

honcho-ai

Memory library for building stateful agents

summarization-pydantic-ai

Context Management processor for Pydantic AI agents, providing LLM-powered summarization or zero-cost sliding window trimming to handle infinite/long-running conversations without context overflow. Supports flexible triggers, safe cutoffs, and custom prompts for efficient AI apps.

lamindb

Open-source data framework for biology. Query, trace & validate with a lineage-native lakehouse that supports bio-formats, registries & ontologies. 🍊YC S22

cognee

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

pageindex

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

stashai

Shared memory for your team's coding agents

vincio

The context engineering platform for AI applications — compile prompts, memory, retrieval, tools, schemas & policies into optimized, validated, observable context packets.

lamindb-core

Open-source data framework for biology. Query, trace & validate with a lineage-native lakehouse that supports bio-formats, registries & ontologies. 🍊YC S22

cocoindex-code

A super light-weight embedded code search engine CLI (AST based) that just works - saves 70% token and improves speed for coding agent 🌟 Star if you like it!

gcf-proxy

MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.

rapidfireai

RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning

ims-mcp

Meta-prompting, context engineering, and centralized instructions management for AI coding agents - by Grid Dynamics

dummyindex

Persistent context engine for Claude Code — turn any codebase into a .context/ folder Claude navigates instead of grepping. Deterministic AST backbone (tree, symbols, graph, conventions) + a multi-agent council that fills in the judgment.

wren-core-py

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

omega-memory

Cross-model memory for AI agents. Local-first, works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client

docpull

Convert the public web into AI-ready Markdown with a local Python CLI/SDK/MCP crawler.

powermem

PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.

synalinks

From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

ace-framework

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

agentbundle

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

acontext

Agent Skills as a Memory Layer

mloda

mloda.ai - Open Data Access for AI and ML. Plugin-based. Traceable. Framework-agnostic.

wrenai

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.