markmhendrickson/neotoma
Deterministic state layer for AI agents
This project helps AI agents remember key information and decisions across different AI tools and sessions. It takes unstructured inputs like files, messages, or API data, and processes them into structured, versioned records such as contacts, tasks, or transactions. The output is a reliable, consistent memory graph that AI agents can use and update, preventing them from forgetting or creating conflicting information. This tool is for anyone who uses multiple AI agents for tasks and needs their agents to have a shared, accurate, and persistent understanding of ongoing work.
Available on npm.
Use this if your AI agents often forget context, provide conflicting information, or make decisions without a clear, reproducible history across different tools like Claude, ChatGPT, or Cursor.
Not ideal if you only need basic semantic retrieval or simple document storage without the need for strict data integrity, versioning, or cross-platform consistency for AI agents.
Stars
9
Forks
2
Language
TypeScript
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
56
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/markmhendrickson/neotoma"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
ComposioHQ/composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed...
langwatch/better-agents
Standards for building agents, better
AIGNE-io/aigne-framework
The functional, composable, and typescript-first AI Agent framework for real-world LLM Apps.
Peiiii/AgentVerse
Multi-Agent Collaboration Platformâ¨
agentscope-ai/agentscope-studio
A development-oriented visualization toolkit