B17z Sage
- 1 repo stars
- Updated February 17, 2026
- b17z/sage
b17z-sage is a Claude Code plugin that adds semantic memory with checkpoints, linked knowledge, and persistent failure history that auto-restores across sessions.
About
b17z-sage is a Claude Code plugin that adds semantic memory on top of normal chat context. developers install it when long threads lose decisions, repeated failures waste tokens, or they need checkpoints that actually come back on the next session. The plugin focuses on durable knowledge, linking related facts, and recording failures so the agent can treat them as first-class memory rather than buried transcript noise. That makes it useful from early research through shipping and ongoing iteration, even though the catalog lists it under build and agent-tooling. It is not a generic notes app or a vector DB you operate yourself—it is opinionated memory for Claude Code workflows. Expect to configure how checkpoints and restore behave in your environment; the value shows up when you stop re-deriving the same context every afternoon.
- Semantic memory that links context, knowledge, and past failures across sessions
- Checkpoints you can restore after compaction or new chats
- Auto-restore behavior so work resumes without re-explaining the repo
- Knowledge graph-style linking for related decisions and artifacts
- Built for Claude Code as a single-plugin bundle (pluginCount: 1)
B17z Sage by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin install b17z-sage@b17z/sageAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 1 |
|---|---|
| Last updated | February 17, 2026 |
| Repository | b17z/sage ↗ |
What it does
Give Claude Code durable semantic memory—checkpoints, knowledge, and failure history that survive session resets.
Who is it for?
Best when you're running multi-day Claude Code efforts and need memory that survives restarts without maintaining a separate doc stack.
Skip if: Skip if you only need ephemeral one-shot codegen with no continuity, or developers and already centralize memory in a dedicated external RAG system you control.
What you get
After you install sage, checkpoints and knowledge persist so the agent can restore prior context and avoid re-litigating the same failures.
- Restorable semantic checkpoints in Claude Code
- Linked knowledge and failure records that persist beyond a single chat
- Auto-restore behavior after context loss or new sessions
By the numbers
- Repository: b17z/sage
- Plugin count: 1
- Catalog keywords: checkpoints, context, knowledge, linking, memory, sage, semantic
Recommended Plugins
0pg Cc MarketplacePersonal Claude Code plugins collection
1shot Labs Squadron Comms PluginVoice communication system with ElevenLabs TTS for multi-agent coordination in Claude Code3
23blocks Os Ai MaestroAI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging.733
3commas Io Commas ClaudeThis is a repo with shared agents and skills used company-wide4
884js Agent Plugins1 plugin
A5c Ai BabysitterBabysitter enforces obedience to agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration1.6kHow it compares
Agent memory plugin for Claude Code, not an MCP server or a standalone skill file.
FAQ
Who is B17z Sage for?
Developers who rely on Claude Code for sustained product work and want semantic memory instead of copying notes between chats.
When should I use B17z Sage?
Use it when checkpoints, linked knowledge, or failure history should persist and auto-restore anytime context is trimmed or you start a fresh session.
How do I add B17z Sage to my agent?
Install the b17z/sage Claude Code plugin from the marketplace or repo, enable it in your Claude Code plugin settings, and follow the plugin README for checkpoint and restore setup.