167 packages found
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c
Local-first MCP server + CLI giving terminal AI agents an endless, low-token memory via Anchored Compacting
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs acr
The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learn
Session continuity for AI coding agents — your agent picks up where it left off. Persistent memory for Claude Code, Open
MCP server for spreadsheet analysis and editing. Slim, token-efficient tool surface designed for LLM agents.
Lightweight Long-Term Memory for LLM Agents.
Standalone enforcement system for indexed rules, validators, Codex skills, MCP, hooks, and CI adapters.
MCP that allows you to use top-tier LLM's, such as GPT-5.6 and Fable 5, in any IDE via Notion provider
GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools: scene management, GDScript LSP, DAP debugger, sc
Todo and task management
🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access.
Zero-key MCP web search for AI agents: native Chinese sources, multi-engine aggregation, optional commercial backends, n
Local MCP broker that exposes one compact MCP entry for MCP clients while routing to many configured upstream servers.
CLI and MCP server that reads Tokens Studio applied tokens from a Figma URL. Compact tree, grouped dictionary, or Figma-
Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.
enrichr-mcp-server
The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
A MCP server for datetime formatting and file name generation.
o9k — token-efficiency meta-framework for AI coding agents (Claude Code, Cursor, Codex, OpenCode, Hermes): seven pillars
TokToken is a fast, single-binary C codebase indexer for AI coding agents. Powered by universal-ctags and SQLite FTS5, i
Token-saving code search for AI coding agents — TypeScript, JavaScript & Python (zero setup), C#, C++, Go & 30+ more, vi
CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assista
Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count. An MCP server.
An MCP server that lets Claude Code recall past conversations from any project, as clean compact Markdown.
Trello integration for Claude Desktop via Model Context Protocol (MCP) - 19 tools for comprehensive board, card, and lis
MCP proxy that condenses verbose JSON and YAML tool responses into compact TOON text, dramatically reducing token usage
MCP server for Microsoft To Do via Microsoft Graph API. Manage task lists, create, update, complete and delete tasks fro
CLI for the ClickUp API, optimized for AI agents
MCP server for Google Sheets - Read, write and manipulate spreadsheets through Claude Desktop
AI Distiller is ultra‑fast, open‑source tool for intelligently extracting only the essential public APIs, types, and str
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementatio
Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence com
Local, evidence-linked project memory and cited context compiler for coding agents - 98.71% less estimated repeated cont
Let Claude manage your tastytrade portfolio.
SerpApi MCP Server for Google and other search engine results
Zero-dependency agent memory + MCP server. Value-ranked recall, consolidation, and a first-class correction & erasure ch
Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM
Persistent memory for AI coding agents
让 Codex 秒级、低 token、安全地读写 macOS 微信 | Fast, token-efficient WeChat bridge for Codex
memory-mcp-1file
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-dr
Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrit
@tathagat22Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternati
MCP server that exposes Google News RSS feeds as MCP Tools
Context-First-MCP
NBA MCP server to get nba stats and data