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

Optimize token allocation within LLM context windows

Recursive Language Model - Process documents larger than LLM context windows

Liminal — transparent LLM context compression proxy

Extract video frames for LLM context injection

Transparent LLM context compression for Pi using Headroom

Pi extension for bounded Brave web search and LLM context retrieval

Full featured Project Structure Analyzer & LLM Context Builder

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

Live local session and LLM context viewer for pi

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

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

CLI + MCP server for managing shared LLM context stores

Sovereign, portable LLM context layer

Pi extension: inspect the system prompt, active tools, messages, token breakdown and full LLM context in a tabbed overlay

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

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

LLM Context Manager MCP Server & CLI wrapper using npx

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

Preview and export handoffs, then require confirmed import of a strictly validated, bounded package into the active LLM context with duplicate protection.