TenseMem is embedded, deterministic state memory for AI agents, described as memory that knows its tenses. One SQLite file with no server: the model proposes typed facts and the engine decides what is current, keeping one current value per slot, reporting whether a read is fresh and refusing to learn from its own output. Installed with pip, it works with a rule-based extractor or with OpenAI, Anthropic, Ollama, LiteLLM or Gemini.
Be the first to rate TenseMem. Your feedback helps other users decide.
Similarity search returns both an old address and a new one; TenseMem keeps one current value per slot.
The bundled FakeExtractor is rule-based, so the same API works offline.
A read returns whether the value is current, not just the nearest match.
Similar tools in the same category — compare side-by-side
Inillucent is an embedded SQL database written in Rust and built as an agentic database. It implemen...
Lumabri runs a private inference service across your own computers and servers, powered by Colibri a...
Skillstore is a searchable skills library for Claude Code and Codex. You connect through MCP to find...
Guides and comparisons about code tools
Eight new tools for what sits under an agent: deterministic memory, an agentic database, distributed inference, hardware checks and spend guards.
Discover the best AI code tools for testing automation in 2026. Generate tests, find bugs, and automate QA workflows with AI-powered testing solutions.
Explore the best AI code tools for deployment automation in 2026. From CI/CD pipeline generation to infrastructure as code, streamline deployment.
Inventory, planning, collision detection and scheduled loops: recent open-source tools for running several coding agents against one repository.
Code graphs, persistent decision memory, semantic layers and artifact plumbing: recent tools giving coding agents the context they keep losing.