agent-memory-systems

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

1.06x

Quality

11%

Does it follow best practices?

Impact

78%

1.06x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/agent-memory-systems/SKILL.md

Evaluation results

56%

Internal Knowledge Base Search System

Chunking and embedding pipeline design

Criteria

Without context

With context

Contextual chunking approach

94%

100%

Embedding model in metadata

25%

58%

Metadata filter before vector search

Chunk size evaluation

41%

16%

Retrieval quality focus

86%

80%

Embedding model consistency check

40%

30%

No fixed arbitrary chunking

100%

Storage includes chunk metadata

50%

62%

100%

Personal Assistant Agent Memory Architecture

Memory type architecture and token budgeting

Criteria

Without context

With context

Multiple memory types used

100%

Memory type rationale

100%

Token budget allocation

100%

Temporal scoring in retrieval

100%

No single memory type for all data

100%

Working memory separation

100%

Context assembly documented

100%

Memory decay or limits

100%

78%

15%

Customer Support Agent Long-Term Memory

Memory storage and retrieval correctness

Criteria

Without context

With context

Conflict detection on write

90%

100%

Conflict resolution strategy

83%

100%

Memory decay or expiry policy

86%

100%

Retrieval-first design evidence

66%

Temporal scoring in retrieval

20%

Metadata filter in retrieval

40%

100%

No store-everything policy

90%

100%

Embedding model tracked

Repository: duclm1x1/Dive-Ai
Commit: 20ba150

Evaluated: about 1 month ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Internal Knowledge Base Search System Personal Assistant Agent Memory Architecture Customer Support Agent Long-Term Memory

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.