tiered-memory Skill
Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn Published by microsoft in frontier-agentic-devops-rvas.
What is tiered-memory Skill?
Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn Published by microsoft in frontier-agentic-devops-rvas. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Developers using frontier-agentic-devops-rvas
Technical details
- Install or run with Copy skill directory
When to use tiered-memory Skill
- Use it for developers using frontier-agentic-devops-rvas.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/frontier-agentic-devops-rvas
- Skill file: .squad/templates/skills/tiered-memory/SKILL.md
What it does
Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn
Skill instructions
Skill: Tiered Agent Memory Overview Squad agents currently load their full context history on every spawn, resulting in 34–74KB payloads per agent (8,800–18,500 tokens). Measurement shows 82–96% of that context is "old noise" — information that is no longer relevant to the current task. The Tiered Agent Memory skill introduces a three-tier memory model that eliminates this bloat, achieving 20–55% context reduction per spawn in production. --- Memory Tiers 🔥 Hot Tier — Current Session Context - Size target: ~2–4KB - Load policy: Always loaded. Every spawn includes hot memory by default. - Contents: Current task description, active decisions made this session, immediate blockers, last 3–5 actions taken, who you are talking to right now. - Lifetime: Current session only. Discarded after session ends (Scribe promotes relevant parts to Cold). - Purpose: Provide immediate task context without any latency or load decision. ❄️ Cold Tier — Summarized Cross-Session History - Size target: ~8–12K
Explore related resources
Frequently asked questions
What is tiered-memory?
tiered-memory is a open-source AI agent skill with Copy skill directory. Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn
Who is tiered-memory best for?
tiered-memory is best for reusing agent instructions, scripts, and references.
How do I install tiered-memory?
Install or run tiered-memory using Copy skill directory. Check tiered-memory for the latest setup command.
Is tiered-memory actively maintained?
tiered-memory may need a closer maintenance check before production use.
Auto-fetched from GitHub.
