whereismyai
TenseMem
TenseMem: State memory engine for AI agents that keeps one current truth per slot in a local SQLite file.
TenseMem is an embedded, deterministic state memory system designed for AI agents. It uses a single SQLite file with no server required to store factual data and maintain chronological state. The model proposes typed facts while the engine applies deterministic rules to decide what is current and report read freshness. It supports integrations such as OpenAI, Anthropic, Ollama, LiteLLM, Gemini, LangGraph, and LlamaIndex. Designed for developers building AI agents, it prevents self-echo and handles corrections that survive database rebuilds.
TenseMem at a glance
- Best for: Software engineer
- Runs on: Python, CLI, REST, MCP, Web, self-hosted
- Pricing: Free
- Released: October 2026
- Category: AI agent tool
- Website: github.com/tensemem/tensemem
Key features
- Stores memory in a single SQLite file
- Resolves current facts via deterministic rules
- Reports freshness for every read
- Prevents learning from its own output
- Supports OpenAI, Anthropic, Ollama, and Gemini
- Provides a local Next.js inspector studio
- Integrates with LangGraph and LlamaIndex
Use it for
- Managing persistent state for AI agents
- Tracking current user facts over conversation history
- Inspecting agent memory states locally
- Building applications with LangGraph or LlamaIndex
Alternatives to TenseMem
- MemPalace — Achieves high recall with local-first storage and zero API calls.
- memU — It gives every connected agent a shared and inspectable memory layer.
- ReMe — It enables local-first, file-native long-term memory sharing across multiple AI agents.
- MuscleMemory — It cuts input tokens, tool calls, and execution time while maintaining task success.
- Mnemosyne — It provides sub-millisecond memory access with no external service costs.
- Mem0 — It provides drop-in persistent memory for AI agents without changing pipelines.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- MemMachine — Provides long-term persistent memory for LLM-based agents.
- Agentmemoryrepo — Enables agents to navigate memories like a wiki and share knowledge across sessions.
- LongMemory — Provides immutable, temporal, and governed recall instead of simple vector retrieval.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- MemOS — It delivers ultra-persistent memory, hybrid-retrieval, and token savings.
All TenseMem alternatives