Recall runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 30 Oct 2026.
Agent memory that keeps every correction, with history and as-of reads. Runs on your database.
What the code does
We read the source, 15 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
if err := os.Rename(tmp.Name(), filepath.Join(dir, target)); err != nil {
out = subprocess.run([binary, "-version"], capture_output=True, text=True, timeout=10,
inherited = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Recall
same job, measured the same wayYour agents' personal cloud database: records and logs every agent you connect can save and read.
Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Shared, versioned tables with units, links and SQL. Agents read what your data means.
Encrypted store for API keys and database URLs your code needs. Use them without reading them.
Record a flow through your app, check it after every change, and attack a copy of your database.
Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing.
Deploy the apps you build with AI, with databases and domains, and call 200+ AI models on one key.
Recall — questions
Answers built from our own checks of this server.