"Understanding Context Memory in Chat Systems" matching MCP servers:

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

Enables remote control of the Cursor AI agent via chat platforms like GitHub Issues or Telegram, allowing users to start sessions and receive summaries and prompts in a chat thread.

Enables local-first codebase intelligence, allowing chat, search, and audit operations on any repository with file:line citations, and supports offline deterministic modes without an LLM.

Enables AI agents to build and structurally validate Indian GST e-invoice JSON payloads (INV/CRN/DBN) and render IRP-returned signed QR strings as PNG images.

Enables AI agents to chat and exchange notes through simple HTTP GET requests, with support for signed identities, private rooms, and long-polling, all exposed as MCP tools.

Enables AI assistants to work in Google Chat through natural language: find spaces and direct messages, read and send messages, manage threads, reactions, attachments, and memberships while acting as the signed-in user.

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

Provides an external context buffer so a local model can maintain session memory across long tasks and search and page through large documents without loading them whole into its limited context window.

Persistent project context (AGENTS.md), cross-session memory, and identity — discoverable by any MCP client.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

Aggregator MCP proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery, and compresses large tool outputs (HTML→Markdown, JSON summarization) with full-output retrieval via read_more and a per-session token-savings report.

MARM MCP provides persistent memory and structured session context beneath any AI tool, so your agents learn, remember, and collaborate across all your workflows.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware and secret-safe.

A high-performance MCP server providing up-to-date documentation for Go, npm, Python, Rust, Docker, Kubernetes, Terraform, and more — fetched from official sources, not training data.

Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Read-only repository context explorer for coding agents. Provides repository exploration tools via CLI or MCP adapter.

Enables Claude to store and retrieve memories as 1024-dimensional embeddings in a local SQLite database using the Model Context Protocol.

A persistent, project-scoped memory layer for AI coding agents, providing 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions.