Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), offers priority-based load balancing, optional OpenAI Chat↔Responses format conversion, and one-click setup for Claude Code / Codex.
Every file not opened. Every folder not explored. Tokens saved. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.
MCP server for token-efficient large document analysis via the use of REPL state
Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation
Token-efficient, local-first CLI tools for coding agents - compact Maven, npm/Node, and Go test output plus reusable development helpers.
Unofficial MCP server for working with Kagi *without* API access (you'll need to be a customer). Searches and summarizes. Uses Kagi session token for easy authentication. Works well with your agent.
Free Kagi Search MCP server — access search and summarizer via session tokens, no API key needed. Works with Claude Desktop, Cursor, Windsurf, Hermes and any MCP client.
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.
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
Quickly reads webpages and converts to markdown for fast, token efficient web scraping
Agent-skills marketplace for Claude Code, Codex and Cursor: RPA BDD workflow, Logika (Chelpanov formal logic), token-cost, MikroTik config generator
MCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resource Templates for client-side exploration.
AI Badger - Local-first tool that extracts focused repo context for any AI chat (Claude, ChatGPT, Grok, etc.) without wasting tokens on irrelevant files.
CTX - Context Runtime Engine for Coding Agents
Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.
C.O.N.T.EX.T is designed to compress complex, multi-domain conversations into machine-optimized "Carry-Packets." These packets achieve a crystallization point of 0.15 entity/token, ensuring that a receiving model can reconstruct the original context with near-perfect fidelity.
Save 30% token costs when using Claude Code, Codex, OpenCode for free - with open source, local semantic search. Works for small and large codebases and monorepos! Enterprise-ready and fully compliant via Ollama and SQLite-vec.
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.
Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes curate the collection. Fully local: Ollama + SQLite + optional Apple Intelligence.
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Helping coding agents never make mistakes working with public or private libraries without wasting the context window.
A third-party Perplexity MCP/REST API implementation that leverages Pro account Pool to provide unlimited quota for ask and deep search capabilities.
On-demand design systems from any URL. Five surfaces, one agent: web, API, CLI, TypeScript SDK, and a portable agent skill that runs inside Claude Code, Codex, and Cursor.