Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents, and automatic verification

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

Pith is the hook that makes Claude Code sessions last 3x longer.

Stop Claude Code from burning through your quota in 20 minutes. Auto-rotates oversized sessions and preserves context.

Working memory for Claude Code - persistent context and multi-instance coordination

Config-driven CLI tool that compresses command output before it reaches an LLM context

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

LeanCTX — Context Intelligence for AI systems.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, then reversibly disables the dead weight. No proxy, no compression.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.

CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the context window. Supports 52+ commands — git, docker, kubectl, npm, terraform, and more.

Make your AI coding tools work as one team. Route jobs across Claude, Codex, Cursor, Devin, Gemini, OpenRouter, and local models, carry your setup with them, and track every cost.

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

🤫 Claude shuts up until it's done. A Claude Code plugin: one short answer at the end, the file to open, and no log dumps in your chat.

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.