markmhendrickson/neotoma
Deterministic state layer for AI agents
Enforces schema-bound, versioned state with full provenance through a four-stage pipeline (observations → entity resolution → snapshots → memory graph), preventing silent mutations and conflicting facts common in production agents. Exposes state through three equivalent interfaces—REST API, MCP protocol (Claude/Cursor/Codex), and CLI—all backed by the same deterministic contract, enabling reproducible state inspection and replay across any session or tool.
Available on npm.
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.
Higher-rated alternatives
ComposioHQ/composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed...
langwatch/better-agents
Standards for building agents, better
AgentDock/AgentDock
Build Anything with AI Agents
AIGNE-io/aigne-framework
The functional, composable, and typescript-first AI Agent framework for real-world LLM Apps.
vercel-labs/knowledge-agent-template
Open source file-system and knowledge based agent template. Build AI agents that stay up to date...