What is sage-memory?
sage-memory is a Claude Code mod by KilimcininKorOglu that keeps project and global memories in SQLite through a shared local daemon, hands the model the entries that match its file tool calls, prompts and subagent tasks, and saves new ones with a. It is listed under Context & memory and has 11 GitHub stars.
| Type | Claude code mod |
|---|---|
| Author | KilimcininKorOglu |
| Repository | KilimcininKorOglu/claude-code-mods |
| Popularity | 11 GitHub stars |
| Category | Context & memory |
| Security | High risk (48/100) |
| Rank | #491 of 5,272 Claude Code mods; #58 in Context & memory |
| License | MIT |
| Last commit | 2026-10-04 |
| Stars this week | +3 |
| Hooks | 18 events |
| Sees | /"^(Edit|Write|NotebookEdit|MultiEdit)$"/ calls, /"^(Read|Grep|Glob|LSP|Edit|Write|NotebookEdit|MultiEdit|mcp__(?!sage-memory__).+)$"/ calls, /"^mcp__sage-memory__"/ calls, Bash calls, classic hooks, compaction, every prompt, subagent spawns, the system prompt |
| Draws on | Pane |
Is sage-memory safe to install?
sage-memory scores 48/100 on the MCPMods security check: High risk. Things to review: sends data over the network; starts processes outside the sandbox; reads environment variables; watches every prompt or event. It passed 3 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| Sends data over the network | Review |
| Starts processes outside the sandbox | Review |
| Writes no files or config | Pass |
| Reads environment variables | Review |
| Watches every prompt or event | Review |
| Drives Claude (model calls, prompts) | Note |
| Passes claude plugin validate | Pass |
| Has an open-source license | Pass |
API calls in its code
| Call | What it means |
|---|---|
$.clock.after | |
$.clock.every | |
$.clock.now | |
$.command.register | |
$.env.get | reads env vars |
$.fs.read | reads files |
$.http.fetch | network requests |
$.model.complete | drives Claude |
$.process.run | runs processes |
$.session.cwd | |
$.session.id | |
$.session.usage | |
$.sidebar.set | |
$.store.get | keeps its own state |
$.store.set | keeps its own state |
$.tool.call | drives Claude |
How do I install sage-memory?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/KilimcininKorOglu/claude-code-mods claude plugin validate ./claude-code-mods/plugins/sage-memory
- Install it. Run this in your terminal, then /reload-plugins in an open session.
claude plugin marketplace add KilimcininKorOglu/claude-code-mods && claude plugin install sage-memory@kilimcininkoroglu-mods
Or ask Claude to set it up
Paste this into Claude Code and it installs sage-memory for you:
Install the "sage-memory" Claude Code mod from https://github.com/KilimcininKorOglu/claude-code-mods/tree/main/plugins/sage-memory. Run claude plugin validate on it first and show me what it can access before you enable it.
More from KilimcininKorOglu/claude-code-mods
This repository has at least 9 Claude Code mods on MCPMods.
- action-pin: After an edit that adds a GitHub Actions step pinned to a tag or a branch, names the commit SHA to write instead, from t (Review before installing)
- ask-autopick: Picks the recommended option of a question that waited unanswered for a set time, so a session you left does not stop. O (Low risk)
- bash-diet: Shrinks each Bash result before the model reads it: per-command filters for git, test runners, linters, package managers (Review before installing)
- bg-tasks: Shows the background shell tasks of the session on the status line or in the shared sidebar, with the oldest one's age, (Low risk)
- bughunt: Runs proof-driven bug hunt rounds with /bughunt: each round proves one bug with a failing command the mod runs itself, f (Review before installing)
- cache-warm: Keeps the 1-hour prompt cache warm for a window you set, or with no end in every session under always, with one cache-sh (Review before installing)
- commit-cadence: Names the uncommitted files to you at the end of each turn, and tells the model at the next prompt to commit each finish (Review before installing)
- config-parse: Parses each JSON, YAML, TOML or .env file an Edit or Write touches, notes a parse error at once instead of at the next b (Review before installing)