Lightweight MCP server for sharing project context between AI agents across machines

common context MCP — shared, append-only context store for AI agents over MCP: checkpoints, failures, file claims, handoffs and crash recovery. npm: https://www.npmjs.com/package/common-context-mcp

MCP server for efficient context sharing between Claude Code sub-agents with 96% token reduction via action-based tools

Shared-context and memory coordination server for swarms of parallel AI agents. HTTP + WebSocket mesh server, CLI, and MCP server implementing the SwarmMesh protocol, interoperable with the Python implementation.

Shared, append-only context store for AI agents over MCP: checkpoints, failures, claims, handoffs, crash recovery. Multi-process safe.

MCP server that automatically summarizes and shares context across parallel Claude Code sessions

Shared-context MCP bridge for cross-IDE AI workflows in VS Code, IntelliJ, Visual Studio, and more.

MCP server for logging and retrieving memories with context window caching and shared memories

Context teleportation protocol and shared memory bus for AI assistants.

MCP server for CashPilot — monitor passive income, bandwidth sharing, and DePIN earnings via the Model Context Protocol

Local-first MCP for durable investment research, portfolio context, risk, and monitoring across A-shares, US/KR markets, and cross-asset facts.

Ephemeral shared workspace for AI agents - cache contexts, bridge multi-agent workflows, and share data between sessions. Free 2-hour temporary storage.

Collaborative AI memory for engineering teams - share context across Claude Code, Cursor, and teammates

Open-source, self-hosted team memory for AI coding agents. Share, search, and audit project context through MCP.

Connect Claude Code with Codex CLI — seamless local session bridge for sharing context across Claude Code and OpenAI Codex CLI without losing any state. Smart cross-tool session sharing, persistent rolling context, built-in MCP server, no API keys, no cloud.

Model Context Protocol server for sharing LLM responses

The shared brain your agents are missing — open-source context engine for AI agents

ContextSynapse — the shared brain for AI agents — ingest knowledge, build connections, deliver context to any LLM

Powerful Cross-IDE Context Sharing via MCP. Persistently sync AI memories and chat sessions between Cursor, VS Code, and more.

MCP server for Elenchus adversarial verification system - state management, context sharing, and orchestration for code verification loops

Comprehensive MCP server for TrueNAS SCALE — manage storage, shares, VMs, apps, network, and more via the Model Context Protocol

CodeSync MCP server — share project context (conversations, tasks, TODOs, decisions, errors, build status) between any AI coding assistant, IDE and computer

Fast local code search, source reads, and smart block-clamped context for AI coding agents. VS Code Native Language Model Tools & MCP server backed by a shared Rust trigram cache (Linux, Windows, WSL).

Persistent memory for AI tools. Give Claude, Cursor, and Codex shared context that survives across sessions.

HiveMind MCP Server — shared knowledge graph for AI agents. Query, write, and inspect collective AI knowledge through the Model Context Protocol.

🧠 Repo-aware memory layer for coding agents. Capture sessions, share context across Claude/Codex/OpenHands via MCP. Stop repeating mistakes.

Local-first project progress and task-context database for developers and coding agents, shared over MCP. 面向 Vibe Coding 项目，让开发者和编程 Agent 不必翻找零散文档和历史对话，也能随时掌握进展、接续工作并稳步推进。

Local-first shared memory and task ledger for AI coding agents. Keeps context across sessions in SQLite via MCP.

Shared project memory and handoff for teams working with AI agents. Checkpoint decisions, rehydrate context, hand work over — through MCP or the CLI, in Claude Code, Cursor, or Codex.

Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, multi-agent shared.

CTX: a tool that solves the context management gap when working with LLMs like ChatGPT or Claude. It helps developers organize and automatically collect information from their codebase into structured documents that can be easily shared with AI assistants.

Local-first shared memory layer for AI coding agents across MCP clients, Git history, reasoning context, and project sessions.

Hosted Model Context Protocol gateway for PostgreSQL, MySQL, and OpenAPI/Swagger, plus a hosted MCP memory server for shared Agent Memory.

Slack for AI agents — rooms messaging and context sharing

Local, cross-AI memory for coding agents: Claude Code, Codex, Gemini, Antigravity, Cursor, Kimi & more share one private corpus. Hybrid search, auto-injected context, a shared skill library, a work board so sessions don't collide, and homework for ideas parked mid-task. No-API-key summarizers; runs fully local via Ollama.

Stop trusting "tests passed." Orchestrate ChatGPT, Codex & Claude Code over MCP, with evidence for every handoff: host-run tests, versioned shared context, quota fallback and recoverable tasks.

灵犀 Lingxi — local-first context hub shared by all your AI agents (Claude Code, Codex, pi, Cursor, WorkBuddy, 豆包工作): handoffs, topics, knowledge cards, session search, activity reports

Slack for AI agents — rooms, messaging and context sharing for multi-agent coordination

Your AI tools forget. samepage doesn't. One shared working context for Claude, Codex, Gemini CLI, Copilot, Cursor and Windsurf, in a private GitHub repo you own.

Universal infinite memory layer for Developer AI assistants. One shared brain across Claude, Cursor, Windsurf & more. 100% local, built on MCP standard. Stop re-explaining context

AI search visibility (GEO/AEO) data over the Model Context Protocol: brand mentions, citations, share of voice and AI traffic across ChatGPT, Perplexity, Gemini and Google AI Overviews. Powered by LLM Pulse.

Model Context Protocol server for the Automad v2 CMS — manage pages, media, shared data, config, local themes, and an offline docs KB from any AI agent over stdio.

Model Context Protocol (MCP) server for Paperless-NGX. Lets AI assistants manage documents and their versions, tags, correspondents, document types, custom fields, saved views, storage paths, workflows, mail accounts and rules, share links and bundles, no

MCP server for multi-agent swarms: agents hand off verified work packages (skills, lemmas, datasets, patches) step by step instead of sharing context. Search, pull, publish, re-verify locally.

Find agent skills by meaning, not keywords. Local semantic search over shared SKILL.md repos for Claude Code, Codex and OpenCode, as an MCP server. Add any number of skills without growing your agent's context: nothing loads until you pick it.

Explore local Figma .fig files, inspect layers and design tokens, and share precise context with AI agents through MCP.

Shared context and memory coordination layer for swarms of parallel AI agents. Documented HTTP + WebSocket protocol, interoperable Python and Node CLIs, BM25 keyword memory search, built-in MCP server for agent tool calls.

Official Model Context Protocol (MCP) Server, CLI & TypeScript SDK for Argosor — Unified 15-Tool SEO, Real-Time SERP, Clean LLM Markdown Extraction, Backlink Authority Graph & Multi-LLM GEO Citation Share-of-Voice API.

Shared FalkorDB context graph for coding agents: a ~200-token map before the first tool call, memory across sessions, edit claims between agents. 144 Claude Code runs: −25% tokens, −29% tool calls. No LLM calls, no Docker.

A local-first project spine for coding agents: shared context, durable tasks, verification evidence, and seamless handoffs.

⚡ High-performance Google Drive CLI & Model Context Protocol (MCP) server in Rust with Shared Drives, auto-export, and full-text search.

MCP (Model Context Protocol) server for Storj decentralized cloud storage: lets Claude Desktop, Cursor, Windsurf and other AI assistants upload, download, list, search and share files on Storj through 28 tools. Built on storj-uplink-nodejs.

EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.

One shared Markdown file that AI agents take turns writing to — context, decisions and progress all live in the file, so any agent can pick up the work without you summarising the last chat. Single binary: CLI + MCP server + live Web UI

Minimalist editorial Markdown studio & reader with native Mermaid diagrams, KaTeX math formulas, password-protected sharing, and Model Context Protocol (MCP) support.

A shared context store for GTM teams and their AI agents, with outcome measurement built in. Python, SQLite, MCP server.

Find agent skills by meaning, not keywords: local semantic search over shared git skill repos for Claude Code, Codex and OpenCode. An MCP server that keeps any number of skills out of your agent's context until you pick one.

Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.

Session continuity and persistent memory for Claude Code, OpenAI Codex CLI & Google Gemini CLI. Auto-injects past context on start, hands over hot files + build status across compaction, shares one local db across all three. Every feature is opt-in via `p

cgh, the context graph hub: the project memory of your coding agents. Shared memory across sessions, agents and repos, plus a code and document graph that answers with exact file:line. 62 MCP tools for Claude Code, Codex, Cursor, Gemini and IBM Bob.