lean-ctx
Updated todayby yvgude
βββ ββββββββ ββββββ ββββ βββ βββββββββββββββββββ βββ βββ βββββββββββββββββββββ βββ βββββββββββββββββββββββββ βββ ββββββ ββββββββββββββ βββ βββ βββ ββββββ βββ ββββββ ββββββββββββββββββ βββ βββ ββββββ βββββββββββββββββββ ββββββ ββββββ ββββββββ βββ ββββ βββ βββββββββββββββββββ ββββββ βββββ βββββββ βββ βββ βββ
Control what your AI can see.
LeanCTX β Context Engineering Layer for AI Coding Agents
LeanCTX β short for Lean Context β is the context engineering layer for AI coding agents. It runs locally alongside your coding agent, helping it read repositories, run development commands, and send focused context to the model: it decides what agents read, compresses what they send (an optional local proxy shrinks every request β system prompt, history and tool results β prompt-cache-safe), remembers what they learn, guards what they touch β and proves what they save with a signed, verifiable savings ledger. The result: 60β90% fewer tokens. Zero config required. Local-first.
| Problem | With LeanCTX |
|---|---|
| Repeated file reads: ~2000 tokens each | Cached re-reads: ~13 tokens |
Raw git status: ~800 tokens | Compressed: ~120 tokens |
| Every turn re-sends the whole history | Proxy compresses each request, prompt-cache-safe |
| Context resets every chat | Session memory persists across chats |
| No visibility into context usage | Real-time dashboard + budget control |
Related servers
n8n
Updated todayby n8n-io
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
mcp-server-fetch
OfficialUpdated 14d agoA Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs
@modelcontextprotocol/server-everything
OfficialUpdated 14d agoMCP server that exercises all the features of the MCP protocol