Agent Context Python Packages

basemind

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

engram-connect

Engineering memory for AI coding agents

loghop

Stop losing context when switching AI coding assistants. Persistent sessions, automatic handoffs, shared timeline between Claude Code and Codex.

agent-context-cli

Navigation contract for AI coding agents in large repos. Templates, validation scripts, and a Python CLI for authoring three-layer context packs. Companion to the agent-recall research.

trellis-ai

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

universal-agent-context

Universal context system for AI agents: discover, translate, and manage agent skills across formats. Includes MCP server, CLI, and Python library.

crewai-prediction-markets

CrewAI tools for prediction market data. Give your AI crew real-time world awareness from 30,000+ markets.

neural-ledger

A lightweight memory engine that helps systems remember useful things, recall what matters, and learn from feedback.

scs-tools

CLI tools for Structured Context Specification (SCS) project scaffolding

gitmind

AI powered Git repository analysis and reporting