Back to directory

TrueMemory

A local, automatic memory system for AI coding agents that captures relevant facts from conversations, resolves contradictions over time, and injects the right memories into later sessions, storing everything in a single local SQLite file.

TrueMemory

TrueMemory automatically captures memories from an AI agent's conversations and injects the relevant ones into later sessions, without manual tagging or prompt engineering. It resolves contradictions when a user changes their mind, updates facts that have gone stale, and consolidates what it knows over time rather than acting as a static database.

Everything is stored in a single local SQLite file with no cloud dependency and no API keys required; the only telemetry is anonymous usage data that never includes memory content, and it can be disabled with an environment variable. It reports internal benchmark scores on long-context memory retrieval tasks, comparing a free and a paid tier against other memory systems.

It installs with a shell script and integrates with Claude Code, Claude CLI, Cursor, Codex CLI, and Gemini CLI, downloading local embedding models on first setup. It is written in Python under the AGPL-3.0 license.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.