✍️Writing & Content35🎨Image Generation43🎬Video & Animation76🎵Audio & Music67💬Chatbots & Assistants58💻Coding & Development284📈Marketing & SEO87Productivity218🎯Design & UI/UX71📊Data & Analytics69📚Education & Research30💼Business & Finance75🏥Healthcare & Wellness18🔍Search & Knowledge17🤖AI Agent Infrastructure121🛡️AI Security & Testing17🧊3D & Spatial21🔎SEO Tools34🏡Real Estate4🗃️Data Extraction32🧠ADHD & Focus Tools9
Listed in AI Agent Infrastructure with 124 other toolsPart of 1554+ curated AI tools on AISO
Neotoma logo

Neotoma

Versioned, structured memory shared across Claude, ChatGPT, Cursor, and other agents

0
freeCurrently in developer preview with install and evaluation paths published via npm and GitHub. No pricing is published on the site.View full pricing →

Visit Neotoma

https://neotoma.io

About Neotoma

Neotoma gives AI agents durable, structured memory that survives across sessions and across tools. The scenario it opens with is concrete: you tell one agent you have issued a $3,200 invoice to Acme due December 15, and it stores that as a typed entity — invoice, amount, due date, status — with a relationship to the company. Weeks later you ask a different agent for your outstanding balance and get a real total assembled from stored invoices and their relationships, not a guess from a chat transcript. It works across Claude, ChatGPT, Cursor, OpenCode, OpenClaw, and IronClaw, with facts stored privately under your control and full versioning and provenance on every retrieval. The pitch is aimed at a failure mode anyone running multiple agents will recognize: you become the human sync layer, re-explaining the same facts to each tool. The guarantees are where Neotoma differentiates. Chat memory fades, RAG drifts, and Markdown or JSON files accumulate silent conflicts — so Neotoma enforces deterministic state, versioned history so a retry cannot silently overwrite a correction, an auditable change log so you can trace what data an agent relied on when it made a bad call, silent-mutation prevention, schema constraints that reject malformed records instead of letting errors compound, and reproducible reconstruction after corruption. It installs in about five minutes, is distributed via npm and GitHub, and is currently in developer preview.

Key Features

Typed entities with relationships rather than flat chat memory
Shared across Claude, ChatGPT, Cursor, OpenCode, OpenClaw, and IronClaw
Versioned history so retries cannot silently overwrite corrections
Auditable change log tracing what data an agent relied on
Schema constraints that reject malformed records at write time
Silent-mutation prevention and tamper detection
Reproducible reconstruction after corruption
Facts stored privately under your control; installs in about five minutes

Neotoma Pros & Cons

Pros

  • +Structured entities and relationships answer aggregate questions a chat transcript cannot
  • +Versioning and provenance address the specific ways agent memory goes silently wrong
  • +Cross-tool by design, so switching agents does not mean re-explaining everything
  • +Fast to evaluate — install and try it in about five minutes

⚠️ Cons

  • Developer preview, so APIs and guarantees may still change
  • No published pricing, which makes long-term cost unknowable
  • Requires defining schemas to get the benefit over an ad-hoc notes file
  • Value is limited if you only use one agent in one tool

Who Is Neotoma Best For?

👤People running several agents who keep re-explaining the same facts to each
👤Workflows where an agent acting on a stale fact causes real damage
👤Developers who need an audit trail of what an agent knew and when

Tags

agent-memorymcpversioningprovenancedeveloper-previewnpm
🏷️

Is this your tool?

Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.

Claim Now →

ChatGPT already recommends Neotoma. Does it recommend yours?

If you're building in AI Agent Infrastructure, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.

Stay updated on AI Agent Infrastructure tools — join our weekly newsletter

One concise email with fresh launches, trending picks, and featured standouts.

Alternatives to Neotoma

View all Neotoma alternatives →

Agent connectivity: not yet verified