Agent memory

Type: kb/types/tag-readme.md · Status: current

Agent memory notes treat memory as part of agent architecture, not just storage. Use this index for claims about what memory must do for agents, how it interacts with context engineering, and where memory-system comparisons reveal broader KB design constraints.

Notes

• Designing a Memory System for LLM-Based Agents - starting point: frames the design pressures around agent memory as context engineering, retrieval, and learning problems rather than a single database choice

Related Tags

• Learning theory - memory only matters when retained artifacts change future behavior
• Computational model - agent memory is loaded through bounded calls and scheduling decisions
• Related systems - external implementations and comparisons that expose memory-system design tradeoffs

Other tagged notes

• Activate Behavior-Changing Memory Before The Mistake - Behavior-changing memory must activate before relevant actions rather than waiting for explicit retrospective search
• Active work state is not retrospective memory or chat history - Active work state needs current pointers, evidence gates, and closure; treating it as retrospective memory or chat history preserves the wrong state
• Agent memory is a crosscutting concern, not a separable niche - Memory decomposes into storage (solved), retrieval/activation (context engineering), and learning (learning theory) — treating it as a standalone category hides that the hard problems are at the intersections
• Agent memory needs discoverable, composable, trusted knowledge under bounded context - Frames discoverable, composable, trusted remembered knowledge as the minimal artifact-quality basis for agent memory under bounded context.
• Agent Memory Requirements - Navigation hub for concrete agent-memory requirements extracted from the memory-system design synthesis
• Create Memory Directly - Direct memory creation preserves live understanding by writing useful artifacts before later trace extraction loses structure
• Evaluate Memory By Effects, Not By Existence - Memory should be evaluated by downstream effects on tasks, artifacts, answers, behavior, context efficiency, and lineage alignment
• Flat memory predicts specific cross-contamination failures that are empirically testable - Flat memory predicts three cross-contamination failures — search pollution, identity scatter, insight trapping — testable via an observation protocol against real agent systems
• Import External Knowledge Into Internal Form - Agent memory systems need import paths when authoritative project knowledge already exists outside the memory substrate
• Keep Lineage And Compiled Views From Drifting - Generated cues, prompt files, indexes, and assistant-specific views need lineage and authority rules so they do not drift into independent behavior-shaping force
• Make Authority Explicit - Memory architecture must state who can read, write, promote, activate, enforce, revise, and retire memory across risk levels
• Memory design adds operational axes to artifact analysis - Memory design needs operational policy axes (capture, derivation, activation, authority assignment, lifecycle, evaluation) on top of substrate, form, lineage, and behavioral authority
• Memory management policy is learnable but oracle-dependent - AgeMem stores facts in memory but learns the governing policy in distributed-parametric state; it is a clean durable-learning case, but one that depends on task-completion oracles the KB lacks
• Preserve Evidence Without Making History The Next Context - Trace retention should preserve evidence for audit and extraction without making raw history the agent's default context
• Promote Only When Future Value Exceeds Maintenance Cost - Candidate memory should become durable only when future retrieval or activation value exceeds review and maintenance cost
• Raw accumulation does not create usable memory - Accumulation preserves material, but usable agent memory requires ingress work that adds handles, scope, relationships, provenance, trust signals, and lifecycle pressure.
• Retire, Redact, Supersede, And Relax Memory - Memory systems need lifecycle operations for redaction, decay, supersession, retirement, relaxation, and temporal validity
• Serve Multiple Consumers, Not One Retrieval Interface - Memory systems need multiple surfaces because acting, scheduling, review, learning, governance, and active work consume memory differently
• Symbolic context engineering is bounded by symbol availability - Symbolic context selection — matching on type, path, tag, tool, or event — can act only on an already-observable symbol; an operation's identifying symbol arrives by declaration, by the operation naming it, or by carryover from a prior one, so apparent anticipation is reaction to an earlier symbol. Producing context with no symbol available requires semantic inference.
• The adaptation survey corroborates memory requirements but misses artifact governance - The agentic-adaptation survey supports the memory requirements map by treating memory and skills as adaptive tools, but it needs substrate, form, lineage, and authority governance to become design guidance
• Three-space agent memory echoes Tulving's taxonomy but the analogy may be decorative - The value of separating knowledge, self, and operational memory is that each has a different lifecycle — accumulation, slow evolution, and high churn; whether the Tulving mapping adds explanatory power beyond different retention policies is open
• Trace-derived memory earns authority per operation, not at capture - Trace-derived memory arrives as a record, not knowledge — authority is earned through post-capture operations (verify, distill, consult) with increasingly hard oracles; stores that stall before verification accumulate guesses masquerading as knowledge
• Use Trace-Derived Extraction As Meta-Learning - Trace-derived extraction is an after-the-fact learning path that must respect signal quality, review, and readable-artifact versus distributed-parametric learning boundaries