lean-ctx
LeanCTX is a cognitive context layer for AI coding agents that optimizes token usage between code and models.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 2.5k
- Source
- GitHub
- Added
- 2026-06-07
- Last verified
- 2026-06-07

Overview
LeanCTX is a cognitive context layer for AI coding agents, designed to optimize token usage between code and models. It enhances efficiency by compressing, remembering, routing, and validating each token, addressing issues such as repeated file reading, parsing lengthy shell outputs, and loss of context across sessions. Users can start using it by installing a local binary file with no additional configuration required. Ideal for developers who need to efficiently leverage AI for programming tasks.
Key features
- ▪Compress AI-read content
- ▪Cross-session memory of important information
- ▪Intelligent routing of read requests
- ▪Validation of returned data accuracy
- ▪Up to 99% token savings
Use cases
Pros
- +Significantly reduces token consumption
- +Enhances context continuity
- +Supports multiple AI tools
- +Zero-configuration quick setup
Limitations / notes
- -Dependent on specific AI tools
- -May have a learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Which AI tools does LeanCTX support?
Supports Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini, and more.
How do I get started with LeanCTX?
Download and install the local binary file—no additional configuration needed to start using it.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.