Context Engineering: Build Consistent, Accurate, Predictable AI Systems
#context-engineering
MCP servers, skills and plugins tagged “context-engineering” on GitHub.
112 entries · real GitHub data
- #62Cc10x
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.
Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until…
- #64Token Saver
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more)…
- #65AIGX
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file.…
- #67Docmancer
Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries…
- #69Knowl
Persistent memory for Claude Code, Cursor and Codex. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.
MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker quick start for enterprise agents.
- #73Gsd Pro
GSD Pro — The most powerful AI coding workflow for Claude Code. Free alternative to Cursor Composer, Copilot Workspace, Devin & Bolt. Multi-model routing, rollback/recovery,…
- #74Clarilayer
Memory for your AI work across projects and sessions. Save decisions, rules and lessons with source and applicability. Connect over MCP.
- #75Leantoken
Code intelligence for agents: find the code that matters and keep your context window and tokens lean.
- #76Compass
Compass is a context engine that builds a knowledge graph of your organization's metadata, capturing entities, relationships, and lineage across systems and time, making it…
Codex cli hooks - adding voice on each hook
Persistent working memory and invariant steering MCP server for AI coding agents (Claude Code, Cursor, Windsurf). Captures architectural decisions, enforces project rules with…
Introduces a comprehensive agent-based framework for guided software development (GSD)
- #80Archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
- #81Context Guru
Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time,…
AI agent skills for building, operating and troubleshooting Apache Kafka applications. Topic audit, consumer lag, schema review, security, connectors and DLQ
The repo structure for in-house marketers: give Claude Code your company's context before it writes. Folder layout, 11 context skills, a filled-in example.
- #85ox
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
- #86Skillreaper
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
- #88Aictx
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…
Outline-Driven Development - opinionated methodology between vibes and specs. AST tooling + context engineering + loop engineering on your hands. Plugins for Claude / Codex /…
AI Agent 实战手册 - 面向中文开发者的系统学习指南,从零搭建到生产部署