Sandbox
23 repos for tokenization · Any agent · DocsClear
mxyhi/
token_proxy

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.

92
styler-ai/
ProjectAtlas

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%.

407
yogthos/
Matryoshka

MCP server for token-efficient large document analysis via the use of REPL state

148
skibidiskib/
ai-codex

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

391

Token-efficient, local-first CLI tools for coding agents - compact Maven, npm/Node, and Go test output plus reusable development helpers.

184
czottmann/
kagi-ken-mcp

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.

41
KSroido/
Kagi-Session2API-MCP

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.

83
lucasrosati/
claude-code-memory-setup

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.

973

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

125
just-every/
mcp-read-website-fast

Quickly reads webpages and converts to markdown for fast, token efficient web scraping

161
EvilFreelancer/
rpa-skills

Agent-skills marketplace for Claude Code, Codex and Cursor: RPA BDD workflow, Logika (Chelpanov formal logic), token-cost, MikroTik config generator

35
kadykov/
mcp-openapi-schema-explorer

MCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resource Templates for client-side exploration.

76

AI Badger - Local-first tool that extracts focused repo context for any AI chat (Claude, ChatGPT, Grok, etc.) without wasting tokens on irrelevant files.

35
Alegau03/
CTX

CTX - Context Runtime Engine for Coding Agents

143
EtienneChollet/
ontomics

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.

41

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.

32
ory/
lumen
ory/lumenConnectors

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.

255
firish/
webfetch
firish/webfetchConnectors

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.

55

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.

41
okf-memory/
okf-agent-memory

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.

547
ref-tools/
ref-tools-mcp

Helping coding agents never make mistakes working with public or private libraries without wasting the context window.

1.2k

A third-party Perplexity MCP/REST API implementation that leverages Pro account Pool to provide unlimited quota for ask and deep search capabilities.

165
MohtashamMurshid/
getdesign

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.

49