ctx
ctx is a context-aware recommendation engine that dynamically selects the best skills, agents, and MCPs for your current coding task using a massive knowledge graph.
What is ctx?
How to use ctx?
- 1Install with pip install claude-ctx
- 2Run ctx-init to set up hooks, graph, and model configuration
- 3Use ctx-scan-repo to scan your repository and get recommendations
- 4Install recommended skills with ctx-skill-add, agents with ctx-agent-add, etc.
- 5Optionally use ctx-monitor for a local dashboard
ctx Key Features
- 102,928-node LLM-wiki knowledge graph
- 91,464 skills, 467 agents, 10,790 MCPs, 207 harnesses
- Context budget optimization
- Skill rot detection
- Pre-built knowledge graph for fast recommendations
- Local dashboard with ctx-monitor
- Support for custom models via harness setup
ctx Use Cases
- Improving AI coding assistance efficiency
- Reducing token waste by loading only relevant skills
- Discovering new skills, agents, and MCPs relevant to current work
- Keeping installed skills up-to-date and removing stale ones
ctx Pricing & Free Credits
ctx currently operates on a Free model.
ctx Pros & Cons
Pros
- Massive curated knowledge graph of over 100K nodes
- Context-aware recommendations tailored to current task
- Integrates with Claude Code and custom models via harnesses
- Open source with active development
Cons
- Requires Python 3.11+
- Windows has some limitations with tar extraction
- May have a learning curve for initial setup
What is ctx best for?
- Developers using Claude Code
- AI coding tool users wanting smarter context
- Developers optimizing LLM context usage
ctx FAQ
Top free alternatives to ctx
A multi-agent AI runtime for Python developers with OS-inspired primitives like job scheduling, DAG orchestration, memory, and tool execution.
Command Center is an agentic coding environment that helps teams ship AI-generated code to production 2x faster.
Firecrawl is an API that enables AI systems to search, scrape, and interact with the web at scale.
Wandesk is a free AI desktop workspace for macOS that lets you build custom apps, use built-in tools like notebook and ledger, and integrate AI models—all locally.
Tempo is a code-first collaborative workspace that integrates AI agents for planning, designing, and building applications.
Zed is a fast, open-source code editor with multiplayer collaboration, integrated dev tools, and native AI-assisted editing.
Weights & Biases is an AI developer platform for tracking experiments, managing models, and collaborating on machine learning workflows.
Qoder is an agentic AI coding platform for autonomous software development across desktop, CLI, and JetBrains IDEs.
Best alternatives AI Tools to ctx
PII GUI is a local-first desktop application for detecting and redacting personal information in documents using regex and on-device ONNX models.
A multi-agent AI runtime for Python developers with OS-inspired primitives like job scheduling, DAG orchestration, memory, and tool execution.
BlitzGraph is an AI-native backend that models reality in graphs, enabling agents to compose typed JSON queries without SQL or ORMs.
fata is a mobile-first learning platform that helps developers sharpen their skills to lead coding agents across the full stack.
Claireon is an MCP server for Unreal Editor that enables AI assistants to automate game development tasks.
Free open-source desktop companion that runs a private AI backend on Mac/PC and connects MyLLM iOS app over trusted HTTPS via Tailscale.