5 items
AI research assistant with persistent memory, powered by soul.py SoulSearch adds a persistent, memory-aware AI assistant to every webpage you visit. Unlike other AI browser tools, your memory lives in a private Git repo you own — not on Google's servers. HOW IT WORKS Open SoulSearch on any page and ask questions. It reads the page text and answers in context. Your personal notes and research accumulate in a MEMORY.md file in your private repo, synced whenever you choose. FEATURES • Page-aware answers — reads any webpage, SPA, or web app • Git-backed memory — GitHub, GitLab, Gitea, or self-hosted • Named sessions — create, switch, clear independent conversation histories • Memory version history — restore MEMORY.md to any previous commit • Agent mode — automate browser tasks via natural language (click, type, scroll, navigate) • Right-click context menu — save any selected text to memory instantly • Works with Anthropic (Claude), OpenAI (GPT), or Google (Gemini) • Freeform model selector — use any model name your API key supports • 100% open source (MIT) — no subscriptions, no telemetry YOUR DATA • API keys stored locally only — never synced through Chrome Sync • Page content sent directly to your LLM provider, never to SoulSearch servers (we have none) • Memory stored in your own private Git repository GETTING STARTED 1. Add your LLM API key in Settings 2. Create a private Git repo (use menonpg/soulsearch-memory as a template) 3. Add your Git repo details + Personal Access Token 4. Click Save & Sync — your memory loads instantly PRIVACY: https://menonpg.github.io/soulsearch/privacy.html SOURCE: https://github.com/menonpg/soulsearch
Mar 19, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.