memstate-ai/memstate-mcp
Versioned memory for AI agents. Store facts, detect conflicts, and track how decisions change over time — exposed as a hosted MCP server. Other memory systems dump everything into your context window and hope for the best. Memstate gives your agent a structured, versioned knowledge base it navigates precisely — load only what you need, know what changed, know when facts conflict. We built an open-source benchmark suite that tests what actually matters for agent memory: can your system store facts, recall them accurately across sessions, detect conflicts when things change, and maintain context as a project evolves?
Ads
Overview
Versioned memory for AI agents. Store facts, detect conflicts, and track how decisions change over time — exposed as a hosted MCP server. Other memory systems dump everything into your context window and hope for the best. Memstate gives your agent a structured, versioned knowledge base it navigates precisely — load only what you need, know what changed, know when facts conflict. We built an open-source benchmark suite that tests what actually matters for agent memory: can your system store facts, recall them accurately across sessions, detect conflicts when things change, and maintain context as a project evolves?
Capabilities
- memstate_remember
Store task summaries and decisions — Save markdown notes, decisions, or task results with `memstate_remember` and let the server extract keypaths and detect conflicts automatically.
- memstate_set
Set individual configuration values — Write a short value to a specific keypath (e.g., `config.port = 8080`) using `memstate_set`.
- memstate_get
Browse project memory before starting work — Retrieve all memories for a project or subtree with `memstate_get` to understand current context.
- memstate_search
Find memories by meaning — Use `memstate_search` for semantic lookup when you don't know the exact keypath.
- memstate_history
Audit how knowledge changed over time — View the full version chain of any keypath with `memstate_history` to see what changed and when.
- memstate_delete
Remove outdated memories safely — Soft-delete a keypath or entire project with `memstate_delete` or `memstate_delete_project` while preserving full history.
Installation
npx -y @memstate/mcp
Configuration
{
"mcpServers": {
"memstate-ai": {
"command": "npx",
"args": [
"@memstate/mcp",
"-e",
"MEMSTATE_API_KEY=YOUR_API_KEY_HERE"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Tags
- memory
- version-control
- ai-agent
- knowledge-retrieval
- database
- awesome-list
Related MCP servers
Knowledge & Memory
Memory MCP Server
Persist assistant memory as a lightweight knowledge graph across sessions.
2 tools · create_entities, search_nodes
Knowledge & Memory
OpenLore
Sponsored by <a href="https://oiya.ai/?utm_source=github&utm_medium=referral&utm_campaign=openlore&utm_content=sponsor_logo"><img src="assets/oiya-logo.svg" alt="Oiya" height="24" align="absmiddle"></a> OpenLore is a minimal, extensible, agent-native knowledge base that keeps shared context current and inspectable. AI coding agents already know how to explore files with ls, cat, grep, find, pipes, and shell loops. OpenLore gives them that same interface over SSH, backed by your documentation instead of a real machine.
5 tools · Manage identity-scoped access, publish
Knowledge & Memory
liza-studio/skillmem
Self-improving skill memory for coding agents: skills that help get reinforced, unused ones fade on an Ebbinghaus decay curve. $0 write path (SQLite FTS5 + local ONNX embeddings, no LLM calls), bilingual EN/RU hybrid search, SHA256 tamper-evident history, deterministic LongMemEval benchmark in-repo (hit@5 0.871). 8 mem_* tools; deep Claude Code hook integration optional. `pip install skillmem`
Knowledge & Memory
yubinkim444/repo-memory
Shared, git-tracked memory for AI agents on the same codebase. Stores facts/decisions/gotchas in a `.ai-memory/` directory you commit to the repo — sync is git, no DB, no daemon. What one Claude/Cursor/Cline learns, the next one picks up automatically across users and machines. 5 MCP tools (`get_repo_memory`, `add_fact`, `list_facts`, `add_decision`, `add_gotcha`). Install: `uvx repo-memory-mcp --repo /path/to/repo`.
Knowledge & Memory
Mnemosyne-OS/Mnemosyne-Neural-OS
Memory the human governs: vaults separated by domain (code, notes, journal) on your own machine, hybrid retrieval (BM25 fused with vectors by RRF), and a declared vault list, so a vault left out cannot be read by mistake. Also reads what the OTHER coding agents on this machine wrote to disk, and flags when two are live in the same git worktree. Needs the Mnemosyne OS desktop app running. `npx -y @mnemosyne_os/mcp`
Knowledge & Memory
kunickiaj/codemem
Persistent coding memory across sessions, machines, and teammates. Provides MCP tools for searching and managing memories, optional cross-machine sync, and project sharing. OpenCode, Claude Code, and Codex integrations add automatic capture and context injection.
Knowledge & Memory
kskurtveit/echocache
Cache expensive LLM results — HTTP-style freshness (TTL / stale-while-revalidate) plus semantic recall of related past answers
Knowledge & Memory
pipeshub-ai/mcp-server
Permission-aware enterprise search and RAG that gives agents context from your business apps (Google Workspace, Microsoft 365, Slack, Jira, and others). Streamable HTTP or local stdio (`npx @pipeshub-ai/mcp`). Official registry: `io.github.pipeshub-ai/mcp`.