A CLI tool to build context files to attach to Large Language Models (LLMs).

Compress LLM context. Save tokens. Fit more into every request.

Optimize token allocation within LLM context windows

LLM Context Manager MCP Server & CLI wrapper using npx

Recursive Language Model - Process documents larger than LLM context windows

Liminal — transparent LLM context compression proxy

Emit an llms.txt-style, token-efficient digest of the cssdoc model for LLM context windows.

Universal context intelligence layer — compresses LLM context across CLI, MCP, browser, and IDE

Profile and optimize LLM context windows. See what's eating your tokens and fix it — works with Claude, GPT, Gemini, and any MCP-capable AI app.

Lossless, provable, composable LLM context compression

Pi extension: inspect the system prompt and full LLM context in scrollable overlay popups

Persistent structured memory for AI agent systems — pluggable SQLite or Postgres backend, LLM context bridge

In-process content + symbol cache for LLM context windows. Keyed (source, version, item). Tree-sitter symbol extraction + grep + cached-read bridge as subpath imports.

Pi extension for bounded Brave web search and LLM context retrieval

Intercept Kitty Graphics Protocol images from CLI output and inject them into LLM context. A spec and OpenCode plugin for agent-CLI image passing.

Rehydra plugin for OpenCode — anonymizes secrets in LLM context using native plugin hooks

Sovereign, portable LLM context layer

Live local session and LLM context viewer for pi

OpenCode plugin that redacts secrets from LLM context and restores them for tool execution

A DSL for explicit, scoped, auditable LLM context