A super light-weight embedded code search engine CLI (AST based) that just works - saves 70% token and improves speed for coding agent 🌟 Star if you like it!

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local.

A unified CLI to install and update token-saving plugins — RTK, Caveman, CodeGraph, and Context-Mode — for Claude Code, OpenCode, Codex, and Antigravity. Minimal setup. Any OS.

Verified code context for agents

Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.

Context compiler for TypeScript/JavaScript AI agents. Automatically compiles agent state into optimized LLM payloads with history compression, tool pruning, multi-provider support, and more.

Code HUD uses Tree-sitter to show the shape of your codebase: signatures, types, and structure without the noise. Structural search, symbol-aware editing, and git diffs. Installs as a skill or agent for Claude Code, Cursor, Codex, Aider, and OpenClaw.

reShapr website

🧠 Claude Code plugin marketplace featuring Second Brain - an agentic workflow system with persistent memory and tribal knowledge. Transform Claude from goldfish to elephant with cross-session learning.

Helm Charts for installing reShapr components on Kubernetes

reShapr Community repo

[Experiment] Achieve 30% to 60x token savings via the V3U protocol. Use a free/local Translator Agent to communicate with Executor Agents natively in V3U data (0-English). Read How_to_Start.md to begin.

A TUI for scraping and inspecting Claude Code's context built with Bubbletea + Lipgloss

A system architecture proposal for infinite AI conversation continuity, solving the context window limit through a five-component memory framework: sliding hot window, conversation graph, state document, memory manager, and pre-fetch engine

Real-time context window monitoring for Claude Code users. Avoid the silent context ceiling with intelligent alerts, predictive warnings, and actionable optimization suggestions.

A formally-grounded governance framework for Kilo Code. Establishes explicit policy foundations and experimental guardrails across Kilo’s Architect and Code modes to eliminate model hallucination, unauthorized scope creep, and unverified architecture drift.

Field projection layer for MCP tools — let AI agents request only the fields they need, reducing context window usage by up to 95%

Stop burning AI session limits. One click compresses your AI conversations and continues it in a fresh session instantly.

MultiArch Utility that converts entire project directories into a single, context-optimized XML file for Large Language Models.