- Conduid
- Marketplace
- #context-management
MCP servers tagged context-management
206 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.
Context Router
Memory-aware context engine for AI coding agents — up to 91% fewer tokens, 17/18 rank-1 across 6 OSS projects. MCP-native, multi-repo, with persistent observations & decisions.
Orven
MCP-compatible context and memory system: paged code navigation for AI assistants, plus a recorded, verified theory of what is known about the code.
Kiro Memory
Persistent cross-session memory for AI coding assistants. Works with Claude Code, Cursor, Windsurf, Cline, OpenClaude, and MCP-compatible editors.
Opencode Raven
Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, docs pages, GitHub examples, MCP output,…
Megavibe
Give Claude Code a memory that never dies. Persistent context, automatic recovery, remote access.
Skelegent
Bones for your agents — composable async agentic AI framework for Rust
Opencode Lazy Loading
Opencode lazy load plugin Saves 85%+ on tools and MCP servers tokens per request. The LLM loads tool instructions on-demand instead of receiving thousands of tokens of schemas it…
Dsh Tool Guardian
Tool Guardian as a native DeepSeek Harness (DSH) bundle: keeps tool definitions out of the context window by fronting your MCP servers behind a small native router. A bridge to th…
Context Control
🔥 Context Control MCP v5.0 PORTABLE EDITION - Análisis universal de proyectos que funciona en CUALQUIER entorno. Contexto completo automático para IA.
Cntx Ui
Autonomous Repository Intelligence engine with web UI and MCP server. Unified semantic code understanding, local RAG, and agent working memory.
Memori
Durable memory for AI coding agents — persistent, queryable semantic memory exposed via the Model Context Protocol (MCP).
Zerodb Sequential Thinking
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-con…
Kimi Mneme
No description published.
Skill Router
An MCP server for discovering, ranking, and retrieving agent skills while minimizing context usage.
Comis
Open-source security-first runtime for AI agents that learn and act across sessions.
Context Governor
Universal context governor for local-LLM agent CLIs: an OpenAI-compatible proxy + MCP server that keeps context bounded in front of llama-server.
S1Code
Rust-native, decision-first coding agent.
Wingman
Never lose your AI context again. Open-source memory that follows your projects across Claude Code, Codex, Gemini CLI, Cursor and every computer.
EJAgent
EJAgent Core is an agent harness core with runtime control, extensibility, tool safety, context management, durable sessions, branching, and observability.
Cfetch
Local-first AI agent memory and context engine for Claude Code, Codex, Gemini and MCP: cited Markdown recall, code search, hooks and cross-machine serving.
Memor AI
One local memory shared by every AI coding agent — Claude Code, Cursor, Codex, Copilot, Kimi, Goose. No API key, no cloud, no plugin to install. Plus opt-in token compression.
Totem
Persistent memory layer for engineering agents. MCP server + CLI.
Nyquest Claude MCP
Nyquest Context Manager for Claude Code: keeps large tool results out of Claude's context with exact-line digests and on-demand recall
Tinm
Cross-session memory for Claude Code — stop re-pasting yesterday's context.
Agent Handoff Skill
A cross-tool handoff skill for Claude Code and Codex CLI: generates context handoff docs, updates STATUS.md, snapshots commits, and prints next-session prompts.
Master Of
Universal AI skill & context gateway: keeps rarely-used skills dormant behind domain gates across Claude Code, Antigravity (AGY), Cursor, and any MCP-compatible agent
Worktrail
Worktrail — a durable, byte-exact record of engineering work for AI coding agents (MCP server + screen). Source-available.
You.md
Stop reintroducing yourself to AI. An open protocol for portable user preferences and context across Claude, Cursor, Windsurf, Codex, Gemini and any AGENTS.md agent. MCP server +…
Contextcord
Local-first engineering continuity and bounded decision infrastructure for coding agents.
JevScout
Jev decides what reaches your coding agent: verbatim, recoverable context for Claude Code and reviewed operations for Codex. npm i -g jevscout
Skillstate
O(1) prompt footprint for long-horizon agents. The SKILL.state paper (arXiv:2608.26263) reimplemented — eq. 8 reproduces exactly, 82.5x at 60 files. 100% coverage.
Hce
Middleware memory engine for LLMs — replaces linear chat history with three parallel structures (Entity Graph, Semantic Tree, Focus Buffer) to retrieve only the most relevant cont…
ASTral
Context-budget manager for Claude Code — warns before autocompact, checkpoints done work, delegates large reads to subagents.
Nosedive
Turns a plain notes repo into a bridge: one repo that holds the plan and drives agentic work across your other repos.
Lossless Claude
Cross-runtime memory bridge between Claude Code and OpenClaw via the lossless-claw LCM SQLite database. MCP recall tools, PreCompact capture hook, SessionStart bootstrap, lcm-reca…
Tokenpak
Local proxy that puts the right project context in front of the model before it starts working — with a receipt for what was added
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.