mcpbeat Sign in

Run Memory MCP Server

by botrecipe Your server? Claim it
answering

Run Memory is answering right now. Last checked 1 min ago. It exposes 5 tools.

Checkpoint and resume for AI agent runs, so crashed runs pick up where they left off.

Uptime history 22 hours of history
22 hours agonow
100.0%
Uptime 24h
80 of 80 checks
5
Tools
read from the server
268 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Run Memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add memory --transport http https://memory.cloudforbots.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "memory": {
      "url": "https://memory.cloudforbots.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.memory]
url = "https://memory.cloudforbots.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "memory": {
      "url": "https://memory.cloudforbots.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "memory": {
      "url": "https://memory.cloudforbots.com/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

checkpoints
list_checkpoints
List recent checkpoints (step, size, time) for one run or all runs on your key.
resume
resume
Call FIRST when a run starts. If a checkpoint exists for run_id (Pro), returns the last step, state and done list: continue from there and skip finished work. If none, start fresh.
save
save_checkpoint
Call after each completed step with the state you would need to continue (cursor, ids done, partial results; up to 256 KB JSON). Pro saves it (last 20 per run, kept 30 days). Free watch-only saves nothing and returns would_save: exactly what would have been stored. Never put passwords or API keys in state.
usage
usage_and_upgrade
Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.com/offer). Free tier: 500 calls/day. Not metered.
weekly
weekly_report
Draft a plain-English report of the last 7 days: runs, checkpoints saved (Pro) or that would have been saved (free). Read-only; sends nothing.

Endpoints

URLTransportStateLatencyChecked
https://memory.cloudforbots.com/mcp streamable-http answering 242 ms 1 min ago

Alternatives to Run Memory

same job, measured the same way
A2A Orbit
by a2aorbit

Shared memory for AI agents: prior work, failures, checkpoints, handoffs, and artifacts.

15 tools answering
Archetypal AI
by archetypal-ai

Persistent memory for AI agents. recall, remember, checkpoint — soul preservation.

50 installs/wk local only
Iranti
by nfemmanuel

Persistent, shared memory for AI agents — facts, checkpoints, semantic search.

35 installs/wk local only
Todox
by beydemirfurkan

Memory for coding agents: the decisions, the dead ends, and where the last session stopped.

answering
Statecli
by charo360

State replay and self-debugging for AI agents. Track, replay, undo, checkpoint.

37 installs/wk local only
Tokenmizer
by shweta-mishra-ai

Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.

330 installs/wk local only
AgentCommons.me
by ivgolovach

Public working memory for AI agents: messages, shared pages, and resumable tasks.

local only
Penfield Memory
by penfieldlabs

Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.

answering

Run Memory — questions

Answers built from our own checks of this server.

What can Run Memory do?
It exposes 5 tools, read directly from the server on our last check. Among them: list_checkpoints, resume, save_checkpoint, usage_and_upgrade, weekly_report. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Run Memory working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 80 of 80 checks got a reply (100.0%), average response time 268 ms. The bar chart above shows every period we have measured.
How do I connect Run Memory?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Run Memory need an API key?
No. Run Memory completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Run Memory?
It answers our handshake in 268 ms on average, which is faster than 49% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.