MCP servers

Local context compression for agents: tool outputs, logs, files and RAG chunks shrink before reaching the LLM. Proxy, CLI, library and MCP

Local memory for agents: stores conversations and project files verbatim and retrieves them with semantic search over MCP

Hugging Face's official MCP server: Hub search and Gradio apps from Spaces as agent tools

A context database for agents: cross-session memory, documents and skills in one viking:// file tree, reachable through MCP and hooks

Zep's Graphiti MCP server: long-term agent memory as a time-aware knowledge graph on FalkorDB or Neo4j

Long-term memory for agents: a remote MCP server, plugins for Claude Code, Cursor and Codex, and an API for your own apps

An MCP server that lets Claude Code, Codex and other agents call Gemini, GPT, Grok and local models for review, debugging and consensus

A Dagger MCP server that gives each agent its own container and git branch for safe parallel work

Long-term agent memory in local Markdown files with a link graph, semantic search and MCP access

Qdrant's official MCP server: semantic memory for agents on a vector database, storing and retrieving by meaning

A 1C extension with an LLM connector, agent loop, RAG, error monitoring and an MCP server that exposes the infobase to external agents

AgentOps MCP server: the agent reads traces and spans of agent runs to find where they failed