“Agent memory”

Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, session-headed…

Read and write the project's Git-stored memory shared by every agent.

Global team and org memory powered by Activeloop.

Gradient descent for agent memory and instructions.

Load context from the shared agent memory before continuing work on a project - latest sessions, pending items, open checkpoints.

Shared team graph memory — record and recall lessons, patterns, gotchas, and decisions across runs.

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and…

Review every conversation Rami has ever had with his agents - Claude Code transcripts across all projects, agent memory, voice note transcriptions, journals -…

Router for the memory-boost CLI (markdown wiki for agents + drift reports + session digests).

Expert guidance for LangChain and LangGraph development with Python, covering chain composition, agents, memory, and RAG implementations.

Persistent memory for Claude Code with two-tier architecture: hot cache for instant recall (0ms) and semantic search for everything else (~50ms).

How to use your wiki, conversation history, and passive-recall block.

Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory…

Agent-agnostic long-term project memory through `.memory-bank/` + RULES (TDD/SOLID/Clean Architecture/FSD/Mobile) + dev-toolkit commands.

Creative-writing domain knowledge for durable story state.

Store concise, durable, non-secret notes for future agent context.

Designs, debugs, evaluates, and hardens AI agents — the loop, tools, memory, context budget, cost, and escalation — independent of any framework.

Weekly synthesis of accumulated notes and memory optimization

Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.

Write the human-facing prose about a change — PR body · changelog entry · release note · postmortem — and put it in the right file.

Search memory files and agent docs for a query.

Agent memory system with memory graph, context profiles, checkpoint/recover, structured storage, semantic search, observational memory, task tracking, canvas…

Store and retrieve durable learnings about how brayness actually works - success patterns, failure modes, corrections, and next-time hints.