ai-memory
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Discover how ai-memory ensures thread-safe SQLite writes using a single writer actor pattern and async channels for efficient, serialized database operations. Learn about its unique approach.
Understanding Cross-Cutting Invariants in ai-memory's ArchitectureDiscover the fifteen cross-cutting invariants in ai-memory's architecture. Learn how SQLite channels and typed sanitization ensure data integrity, thread safety, and predictable behavior.
How ai-memory Ensures Atomicity in File Writes: The Temp-Rename Pattern ExplainedDiscover how ai-memory ensures atomic file writes using the temp-rename pattern. Learn how this technique prevents corrupted data even during system crashes.
What Does `project_strategy = "repo-root"` Mean in `.ai-memory.toml`?Understand project_strategy = "repo-root" in .ai-memory.toml. Learn how this setting defines your repository's top-level directory as the project root for ai-memory indexing.
How the `.ai-memory.toml` File Supports Multi-Client ConsultanciesDiscover how the .ai-memory.toml file empowers multi-client consultancies by defining workspace and project scopes for AI agents and clients. Learn about deterministic directory tree resolution.
What Is the Purpose of the `.ai-memory.toml` Marker File?Understand the purpose of the .ai-memory.toml marker file. Learn how it defines your project's logical workspace and enables the ai-memory system to discover your repository.
How Pinned Pages Are Handled in ai‑memory's Decay SystemDiscover how ai-memory's decay system protects pinned pages from eviction. Learn how the pinned flag and front-matter ensure your important content remains accessible.
How the Episodic Memory Decay Formula Works in ai-memoryUnderstand the episodic memory decay formula in ai-memory. Learn how age and access frequency combine to manage content salience and eviction.
Understanding the Four Memory Tiers in ai-memory: Working, Episodic, Semantic, and ProceduralExplore the four memory tiers in ai-memory: Working, Episodic, Semantic, and Procedural. Learn how each tier impacts retention, search, and lifecycle management for your AI content.
How ai-memory Handles Memory Decay Across TiersDiscover how ai-memory manages memory decay across tiers. Learn about its nightly retention sweep, scoring, and tier-specific rules for optimal data management.
How to Write Durable Wiki Knowledge with ai-memory: A Complete GuideLearn to write durable wiki knowledge with ai-memory. This guide details how ai-memory ensures data integrity through version control, atomic writes, and indexing for reliable knowledge management.
How the memory_query Tool Works in ai-memory: Hybrid Search Architecture ExplainedExplore the memory_query tool in ai-memory. Learn how its hybrid search architecture combines lexical, entity, and graph search for efficient historical data retrieval.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →