kiranklabs

kiranklabs / hermes-memory-wiki

Public

A browsable, searchable memory layer for Hermes AI agent conversations — automatically captured, summarized, and injected as context into every new session.

github.comkiranklabshermes-memory-wiki
11
1
89% credibility
Found May 30, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Hermes Memory Wiki is a persistent memory layer for an AI assistant that automatically captures, summarizes, and organizes conversations into a browsable web wiki, then injects relevant context into new sessions so users never have to repeat themselves.

How It Works

1
📥 Install with one command

You run a single install command and everything sets up automatically — the wiki, the scanner, and the automatic backups.

2
🔍 It quietly watches your conversations

The tool automatically scans your AI conversations every hour, reading through what you discussed and worked on.

3
✨ Your conversations become searchable

The tool creates summaries of each conversation and organizes everything into a beautiful web page you can browse anytime.

4
📋 Browse your memory wiki

Open the wiki in your browser to see all your past projects, decisions, and facts organized neatly by day and topic.

5
Start a new AI session
✅
It finds a match

Your AI sees you were working on a portfolio site and jumps right in with context about your project, your tools, and where you left off.

💬
No match found

Your AI starts fresh without any injected context, keeping your conversation clean and focused.

🎉 Never repeat yourself again

Your AI remembers your projects, your preferences, and your decisions — so you can pick up right where you left off without explaining everything from scratch.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is hermes-memory-wiki?

Hermes Memory Wiki is a persistent memory layer for the Hermes AI agent that automatically captures, summarizes, and injects your conversation history into every new session. Built with TypeScript and Next.js on the frontend, Python scripts handle the scanning and summarization pipeline from your local SQLite database. The result is a local web wiki at localhost:9876 where you can browse past sessions, see extracted facts and decisions, and query a timeline of your work — without re-explaining context to your AI each time.

Why is it gaining traction?

The killer feature is the three-layer memory architecture: narrative summaries, deduplicated facts, and a decisions trail with supersedence tracking. When you switch from PostgreSQL to SQLite, the old decision is marked superseded rather than deleted — your agent never forgets you already rejected something. The context injection is selective: only relevant history gets injected, keeping token costs predictable. Auto-scanning runs hourly via cron jobs, daily backups keep your data safe, and the `memory-wiki` CLI makes manual operations trivial.

Who should use this?

Developers heavily invested in the Hermes agent who want continuity across sessions. If you spend significant time re-explaining project context, your stack, or your preferences to a fresh agent, this eliminates that friction. Teams working on long-running projects where decisions compound — architecture choices, tool selections, workflow preferences — will get the most value from the decisions layer. Not suitable for Windows or Linux users; requires macOS for the launch agent and cron job integration.

Verdict

At 11 stars and early maturity, this is a passionate personal tool with a well-thought-out design. The supersedence model for facts and decisions is genuinely clever, and the auto-injection approach respects token budgets. Credibility score sits at roughly 90%. The docs are thorough and the CLI is polished, but test coverage is unknown and the community footprint is minimal. Worth installing if you use Hermes daily; otherwise, watch the project and revisit when it gains traction.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.