- Conduid
- Marketplace
- #context-management
MCP servers tagged context-management
239 live MCP servers tagged "context-management", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with context-management.
Kosh
Kosh is a token elimination and context efficiency platform for AI agents, reducing context retransmission through leasing, batching, and reusable references.
Cairnkeep
Durable, harness-agnostic memory and context for coding agents
C31
C31 — Agent Harness System. Memory that persists. Instincts that evolve. Context that stays healthy.
Claude Context Governor
The control plane for Claude Code. Run a dozen MCP servers and a hundred skills. Pay context for only the ones doing work right now.
Project Corpus
Persistent project state and authority for AI agents — Markdown-first protocol with optional policy-enforced CLI and MCP runtime.
Containers
A portable "brain in a box" for AI coding agents: persistent file-based memory + self-reported capabilities + a machine-enforced close ritual + field-tested learning — surviving s…
Contextsynapse
The shared brain your agents are missing — open-source context engine for AI agents
Context Scribe
A Persistent Secretary for AI agents that autonomously extracts rules and preferences from chat logs and syncs them to your Memory Bank via MCP. Eliminate Agent Amnesia.
Codex Jev
Evidence selection and quota-aware recovery for Codex. Optional Jev reranking, local privacy controls, exact source reads. Keep your coding model.
Smart Router
Smart MCP router that routes tools by intent and reduces context rot for LLM hosts
Claude Memory 3tier
Auto-activating 3-tier memory for Claude Code: per-repo markdown bank that survives /compact, + optional basic-memory (Obsidian) and CodeGraph layers.
Void Memory
Three-state persistent memory for AI agents. F1=0.945 without embeddings. Patent pending.
Codex Text Control
在 Codex 中直接编辑权威上下文、Markdown 表格和版本历史。
Glom Continuity
Recaloom (formerly glom-continuity): local project checkpoints and reviewable handoffs for AI assistants. CLI + optional MCP.
Coremem
Git-diffable memory for AI agents — six-layer architecture, plain-text source of truth, Obsidian graph projection. MIT.
Contxt
Portable, privacy-first AI context layer & MCP server. Classifies personal data on-device via fine-tuned Gemma 3 & WebGPU, keeping private data offline.
Context Guardian
Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine.
CMCP TIME
Skill-first continuity for AI hosts: original words, images and timestamps, user controls, sequential handoff and optional MCP.
Cairn
Cairn - AI Context Continuity Engine. Local-private MCP server: context-zone warnings, faithful 7-bucket handoffs, and a decision/evidence ledger across sessions and models.
Context
MCP plugin focused on boosting agent context efficiency and saving tokens
Clexo
Session memory and cross-AI context for Claude Code and Codex — search, save/load, pick, tag past sessions. MCP server + CLI.
Astral
Context-budget manager for Claude Code — warns before autocompact, checkpoints done work, delegates large reads to subagents.
.github
Organization profile and community health files for Yogsoth AI.
Lore
Persistent cross-project memory for Codex — rules, decisions, and context that follow you.
Mnemex
Anchored memory MCP server for AI coding agents — binds decisions to code symbols, delivers context just-in-time. Works with Claude Code, Codex CLI, Cursor, Windsurf, Gemini CLI.…
Engram
Scope-aware memory architecture for multi-agent AI assistants. Powered by Mem0 + Qdrant + MCP.
Nbskill
MCP Server and skill for working with jupyter notebooks from codex or cursor
Nexus
Local-first, reviewable context packs for coding assistants on macOS.
Mnemo
Local-first persistent project memory for Codex, Claude Code, Gemini CLI, and MCP-compatible coding agents.
Github Actions
Control GitHub Actions workflows from your AI assistant to list runs, read logs, rerun jobs, cancel builds, and trigger deployments within your editor.
Somnia
Local-first AI agent runtime with autonomous context awareness. CLI & desktop, MCP integration, Hooks, Skills, multi-agent collaboration, and persistent sessions — purpose-built f…
Vectis CLI
AI-driven design engineering CLI for Penpot. Generate, audit and analyze UI boards from your terminal.
Fastmcp Templates
Templates and best practices for building Model Context Protocol (MCP) client and server applications with FastMCP. Includes context management patterns, modular structure, and an…
Pct MCP Server
Personal Context Technology for AI Personalization MCP server
Claude Persistent Memory
Give Claude Code persistent memory across sessions. Hybrid BM25 + vector semantic search, auto-structuring via LLM, and 4-channel retrieval (MCP + hooks). Your AI assistant finall…
Agent Context Framework
Lightweight, file-based framework for bootstrapping, preserving, and handing off project context across AI agent sessions.
Iron Mem
Persistent session memory for AI coding assistants. IronMem silently records your coding sessions, compresses them into concise memories via Claude API, and injects context into y…
Fastmcp Lro
Large Result Offloading for MCP servers. Writes oversized tool responses to JSONL files, returning compact descriptors with extraction recipes.
ShipItAndPray/mcp-memory
based, zero dependencies.
LatentContext MCP
A session-scoped memory layer for LLMs, built on the Model Context Protocol. LatentContext gives AI assistants the ability to explicitly store and retrieve notes, decisions, and c…
soolaugust/0CompactMem
os`
Claude MCP Server Gateway
MCP server gateway for Claude Code, Claude Desktop, and Cline. Loads only specific tools from your MCPs as you need them and saves thousands of tokens. Works with any Model Contex…
Dynamic Skill Loader
Universal MCP skill dispatcher for AI coding agents. Load Claude Code, OpenCode, Cursor, Gemini, command, and GitHub-hosted skills on demand.
Aethos Memory
Universal, cross-tool persistent memory bank for AI assistants (Claude Code, Cursor, Windsurf, OpenCode, Codex) powered by FastMCP, Gemini embeddings & Supabase pgvector.
One Context
One local MCP server that gives Claude, Cline, Codex, and other AI tools the same project memory.
Varve
Decision memory for AI coding agents. A local-first Go binary and MCP server: records decisions with evidence, scope, provenance and expiry, packs the relevant ones into each agen…
Qarinah
Qarinah is evidence-linked project memory for coding agents - compact enough to save context, inspectable enough to trust.
VMem
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, m…
Carrymem
Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zero-dependency, local-first, 85% PrefEval accuracy.
VecRecall
VecRecall 是一个改进版的 AI 长期记忆系统。它基于对原版 MemPalace 的深度分析重新构建，核心设计理念是将“信息检索”与“信息组织”彻底解耦。 通过纯向量检索路径和独立的 SQLite UI 层，VecRecall 在保持灵活组织的同时，将召回率（R@5）从原版的 84% 提升至 96.6%+，为 AI Agent 提供更精准、更高效…