better-memory
Semantic memory, intelligent compression, and context management for AI agents. Prevents context limit amnesia with real embeddings, priority-based compression, and identity persistence.
Best use case
better-memory is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Semantic memory, intelligent compression, and context management for AI agents. Prevents context limit amnesia with real embeddings, priority-based compression, and identity persistence.
Teams using better-memory should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/better-memory/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How better-memory Compares
| Feature / Agent | better-memory | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Semantic memory, intelligent compression, and context management for AI agents. Prevents context limit amnesia with real embeddings, priority-based compression, and identity persistence.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Better Memory
Semantic memory, intelligent compression, and context management for AI agents.
## What It Does
- Stores memories with real vector embeddings (local, no API calls)
- Semantic search via cosine similarity
- Auto-deduplicates on store (exact + semantic)
- Priority-based compression when approaching context limits
- Identity persistence across sessions
- Token-budget-aware memory retrieval
- Configurable context limits, thresholds, and summarizer
## Quick Start
```javascript
import { createContextGuardian } from 'context-guardian';
const cg = createContextGuardian({
contextLimit: 128000,
summarizer: async (text) => myLLM.summarize(text), // optional
});
await cg.initialize();
// Store (auto-deduplicates)
await cg.store('User prefers TypeScript', { priority: 9 });
// Search
const results = await cg.search('programming preferences');
// Get memories within token budget
const { memories, tokensUsed } = await cg.getRelevantContext('query', 4000);
// Compress conversation and store important parts
const { compressed } = await cg.summarizeAndStore(messages);
```Related Skills
memory-system-v2
Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events. Use when you need persistent memory across sessions or want to recall prior work/decisions.
dory-memory
File-based memory system for AI agents that forget between sessions.
memory-setup
Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.
jpj-memory-manager
Automatic session logging and memory management for infrastructure, projects, and tools.
memory-pipeline
Complete agent memory + performance system. Extracts structured facts, builds knowledge graphs, generates briefings, and enforces execution discipline via pre-game routines, tool policies, result compression, and after-action reviews. Includes external knowledge ingestion (ChatGPT exports, etc.) into searchable memory. Use when working on memory management, briefing generation, knowledge consolidation, external data ingestion, agent consistency, or improving execution quality across sessions.
human-like-memory
This skill provides long-term memory capabilities for conversations.
enhanced-memory
Enhanced memory search with hybrid vector+keyword scoring, temporal routing, filepath scoring, adaptive weighting.
persistent-memory
Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX knowledge graph) for long-term agent.
vta-memory
Reward and motivation system for AI agents. Dopamine-like wanting, not just doing. Part of the AI Brain series.
insula-memory
Internal state awareness for AI agents. Energy, mood, and interoception. Part of the AI Brain series.
hippocampus-memory
Persistent memory system for AI agents. Automatic encoding, decay, and semantic reinforcement — just like the hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023).
basal-ganglia-memory
Habit formation and procedural learning for AI agents. Develop preferences and shortcuts through repetition. Part of the AI Brain series.