ai-memory
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Discover the 19 MCP tools in ai-memory server for agents. Learn about read-only queries, hand-off coordination, and write/maintenance operations for stable long-term memory access.
How `[auto_improve] require_approval = true` Enables Human-in-the-Loop Review for AI-MemoryLearn how `require_approval = true` in AI-Memory enables human-in-the-loop review for AI-Memory auto-improvement. Approve changes manually via CLI.
ai-memory ignore_paths Configuration: How to Exclude Files from CaptureLearn how to use ai-memory ignore_paths to exclude specific files from capture. Prevent sensitive data from entering your LLM pipeline with custom glob patterns.
ai-memory Configuration: Using TOML Files and Environment VariablesLearn how ai-memory configures itself using TOML files and environment variables. Discover how the AI_MEMORY_ prefix and Figment library manage settings for robust runtime configuration.
What is the ai-memory-consolidate Crate? Karpathy-Style LLM Ingest Pipeline ExplainedDiscover the ai-memory-consolidate crate, implementing Karpathy-style LLM ingest for structured wiki pages. Learn about automated consolidation, embedding backfill, and iterative improvement.
How ai-memory Handles Fallback Search When Compiled Wiki Pages MissDiscover how ai-memory uses raw observation fallback search to ensure users always get relevant data when compiled wiki pages miss.
What Is AI_MEMORY_RERANKER=llm? Optional LLM Relevance Reranking in ai-memoryDiscover the purpose of AI_MEMORY_RERANKER=llm. This optional pass uses LLM relevance reranking to reorder search results for improved accuracy in ai-memory.
How ai-memory Adjusts Search Relevance Using Frontmatter Tags and Page KindDiscover how ai-memory enhances search relevance using frontmatter tags and page kind. Learn about configurable multipliers and the retrieval tuning layer for optimized results.
How ai-memory's Retrieval Architecture Combines FTS5, Entity Matching, and Vector EmbeddingsDiscover how ai-memory's retrieval architecture integrates FTS5, entity matching, and vector embeddings with RRF for powerful semantic search. Learn about its robust design.
How ai-memory's Auto-Improvement Feature Works with LLM Providers: A Technical Deep DiveExplore how ai-memory's auto-improvement feature automatically refines LLM provider performance. Learn about the deterministic pipeline, wiki edits, and optional human approval for enhanced AI.
What Is the Purpose of memory_consolidate in ai-memory?Discover how memory_consolidate in ai-memory transforms raw data into searchable knowledge using an LLM pipeline for project auto-improvement.
How SessionEnd Events Are Synthesized and Drive Agent Handoffs in ai-memoryLearn how SessionEnd events synthesize summaries and drive agent handoffs in ai-memory with atomic SQLite transactions for zero-duplication context transfer. Read now!
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 →