Product Launch · XiaoHu Explains

LangChain Ships OpenWiki 0.1.0: Proactive Memory for AI Agents — Auto-Pulls Gmail, Notion, Git, X into a Local Wiki

No manual context-feeding — the local Markdown wiki auto-refreshes on your schedule; a Slack connector is coming soon
TL;DR
  • LangChain released OpenWiki 0.1.0, expanding the open-source CLI tool — originally built just for codebase documentation — into a general-purpose memory framework called OpenWiki Brains.
  • New Personal Brain mode: connects six source types — Gmail, Notion, Git repos, Twitter/X, Hacker News, and web search — to auto-generate a local Markdown wiki that agents can draw on.
  • Updates run via a local scheduled job (installed as a LaunchAgent on macOS), pulling new information and refreshing the wiki on a schedule you set — no server or background process required.
  • The original codebase-documentation feature is renamed Code Brain and now coexists with Personal Brain — both share the "generate and maintain a wiki" approach but serve different use cases.
  • The project is open source — install with npm install -g openwiki; the team previewed upcoming additions: a Slack connector, LangSmith traces, full-text/semantic search, and MCP support.
This article is based on LangChain's official blog release. All capability descriptions and roadmap previews reflect the official line.
1Background

What LangChain Just Shipped

LangChain recently released OpenWiki 0.1.0, extending OpenWiki — an open-source CLI tool previously used only for generating codebase documentation — into OpenWiki Brains, a "proactive memory" mode built for everyday work.

OpenWiki started out as a codebase documentation tool: run it inside a repo and it generates a wiki, then keeps that wiki updated automatically as the code changes — that's the reason LangChain built the project in the first place. With 0.1.0, the team took that same "generate and maintain a wiki" idea outside the code repo and applied it to more everyday work — writing, research, client management.

OpenWiki can now connect to six source types — Gmail, Notion, Git repos, Twitter/X, Hacker News, and web search — and organize the information into a local Markdown wiki that agents can call on anytime; the wiki also refreshes automatically on a schedule you set, with no manual upkeep needed.
The first release ships with 6 source connectors at once. The project is open source — install with npm install -g openwiki. A Slack connector is already on the roadmap, with the team saying it's coming soon.
OpenWiki Brains
Official LangChain release image, showing the overall concept of OpenWiki Brains. Source: LangChain Blog.
2Comparison

Today's Agent Memory Only Remembers What You Said

Assistants like Claude, ChatGPT, and LangSmith Fleet all come with built-in memory — they remember what you've told them and use it in later conversations. That kind of memory is useful, but it only covers what you actively say out loud, or what the agent can infer from the conversation.
Built-in Memory (Claude / ChatGPT / LangSmith Fleet, etc.)
  • Remembers facts and preferences you've explicitly told it
  • Can infer information from your conversations with it
  • Depends on you speaking up, or pasting content into the conversation
OpenWiki Brain (Proactive Memory)
  • Connects to sources like Gmail, Notion, Git, X, Hacker News, web search
  • Proactively looks for relevant information in those places based on the focus you set
  • Writes it into the local wiki automatically — no need for you to say or paste anything

Take a newly added meeting note in Notion, a useful email in your inbox, or a tweet you bookmarked on Twitter/X — even if you never paste that content into a conversation, OpenWiki Brain can still proactively pull it into the local wiki for later use.

3Mechanism

Personal Brain: Getting the Agent to Find What's Worth Remembering, on Its Own

Personal Brain is the flagship new mode in OpenWiki 0.1.0, responsible for generating this proactive-memory local wiki. When you configure it, OpenWiki starts with one question: what should this brain focus on?
Core Mechanism

The team ships a default focus prompt built for general personal-assistant use, but you can rewrite it yourself — say, to zero in on the projects you're running, an AI topic you're researching, background on a client you're working with, saved links, or recent notes in a given Notion workspace. That one sentence is what OpenWiki uses, as it ingests new information, to decide what to keep and what to skip.

Configure sources + a one-line focus prompt
Connectors ingest raw data
Agent distills it per the focus prompt
Writes into the local Markdown wiki
Agent reads the wiki when called on

Raw data first lands in the local ~/.openwiki/connectors/<connector>/raw/ directory (fill in the connector name for connector), gets distilled in this step, and is then written into ~/.openwiki/wiki/, ready for the agent to read as context in later sessions.

4Sources

Six Sources, Two Ways of Fetching

The first release opens up six connectors: Gmail, Notion, Git repos, Twitter/X, Hacker News, and web search. But they don't all fetch information the same way.
OpenWiki Brain Connector Architecture
Official LangChain release image, showing the overall architecture of OpenWiki Brain connecting six source types to generate a local wiki. Source: LangChain Blog.

Deterministic connectors have a clear answer to "give me the latest": the newest emails in your inbox, the newest tweets on your timeline, the newest commits in a repo — just pull by time. The other kind of connector isn't so simple: Notion workspaces and web search don't have a unified notion of "latest" at all, so an agent has to go looking on its own, armed with the focus you set, and judge for itself what's relevant.

Here's an analogy

The former is like pulling a list straight from "recent calls"; the latter is like handing a secretary your focus notes and having them dig through the filing cabinet for relevant material.

Auto-refreshes on schedule Local Wiki Markdown · Plaintext storage Gmail Pulls recent emails Twitter / X Pulls recent activity Hacker News Pulls latest posts Git Repo Checks recent commits Web Search Searches by goal Notion Searches by goal
Deterministic connectors: pull recent data directly Agent-driven search: searches per the set goal
Deterministic Connectors · Pull Recent Data Directly
  • GmailFetched via the Gmail API using OAuth user credentialsPulls recent emails
  • Twitter / XSupports scopes like main timeline, your own tweets, mentions, bookmarks, and list tweetsPulls the recent timeline or bookmarks
  • Hacker NewsUses Hacker News's public feed and search API, no account authorization neededPulls the latest posts
  • Git RepoReads locally configured repo paths and writes out a concise summaryChecks recent commit history
Agent-Driven Search · Searches by Goal
  • NotionConnects to Notion's officially hosted MCP service via Notion OAuth login, not by pasting a token directlySearches the workspace guided by your focus
  • Web SearchUnder the hood it calls Tavily via LangChain, requiring a configured TAVILY_API_KEYSearches the web guided by your focus
5Freshness

How the Memory Stays Fresh

OpenWiki keeps the wiki fresh through a local scheduled job, not a persistent server process. Since the wiki lives right on your own machine, refreshing it works like any other local tool: run it on schedule, pull in the new information, and exit when done.

On macOS, this scheduled job installs as a built-in LaunchAgent: no extra server to install, no process sitting around in the background — it just runs the fetch-and-refresh script on schedule, exits when finished, and logs locally. The whole flow only needs the sources configured once; the rest is maintained automatically in the background on schedule.

Triggers on schedule
Iterates over configured connectors
Fetches new data
Refreshes the local wiki
Once this run finishes, the job exits and waits for the next scheduled time to start again — a cycle that never needs a persistent server.
6Positioning

How Does This Relate to the Original Code-Documentation Feature?

OpenWiki's original codebase-documentation feature is still there — it's now called Code Brain, and it sits alongside the new Personal Brain. Neither replaces the other.
Code Brain (Existing)
  • Runs inside a git repo
  • Focuses on code structure, commit history, file relationships, coding conventions
  • Generates docs into the repo's openwiki directory and inserts reference blocks into AGENTS.md and CLAUDE.md
Personal Brain (New)
  • Connects to multiple source types — Gmail, Notion, Git, X, Hacker News, web search
  • Focuses on cross-tool work context — projects, research topics, client background
  • The generated wiki lives locally in the ~/.openwiki/wiki/ directory

The two use different connectors, prompts, and update methods, but the underlying idea is the same: generate and maintain a body of context the agent can call on anytime.

7Current State

What You Can Get Right Now

Here's what the team lists as actually available right now.
  • The generated wiki is plaintext Markdown — you can view, search, and version-control it right through the file system, with nothing locked into some dedicated interface.
  • The same connector can be configured with multiple instances — say, two web-search sources on different topics — each fetching and updating independently.
  • For developers already using AGENTS.md or CLAUDE.md as agent instruction files, Code Brain automatically inserts reference blocks pointing to the wiki right into those files — a low-cost setup.
  • You choose the model that runs the wiki: OpenAI (defaulting to gpt-5.6-terra), Anthropic, OpenRouter, Fireworks, Baseten, and any OpenAI-compatible endpoint are all supported out of the box; if you have a ChatGPT subscription, you can log in via the browser and run on your subscription quota instead of buying separate API access.
  • Code Brain comes with ready-made GitHub Actions / GitLab CI workflows: docs update automatically when code changes, with a PR or merge request opened automatically.
Install and Initialize Personal Brain
npm install -g openwiki@latest
openwiki personal --init
8Outlook

What's Still Missing — the Team Says So Themselves

The team itself is upfront about where this stands today.
6
Source connectors supported in the first release: Gmail, Notion, Git repos, Twitter/X, Hacker News, web search
0.1.0
The OpenWiki version number in this release, marking its formal expansion from a pure code-documentation tool into the general-purpose Personal Brain memory mode
6
Model providers supported out of the box: OpenAI (default), Anthropic, OpenRouter, Fireworks, Baseten, and any OpenAI-compatible endpoint
Slack
The next connector the team has previewed — not live yet
  • More connectors: Slack is coming soon, with LangSmith run traces and local Claude/Codex sessions also planned as future sources.
  • Better retrieval: right now a brain is just a wiki sitting in the file system. Directions the team plans to try next include full-text search, MCP, semantic search, and letting the agent do its own retrieval across all of these.
  • Better formats: Markdown is just the starting point — cross-page linking and richer knowledge formats (including directions like Google's proposed Open Knowledge Format) are all under consideration.
Built-in memory helps an agent remember what you've told it. OpenWiki Brain helps it remember what's happening in the places you already use.LangChain Blog, "Introducing OpenWiki Brains," 2026-07-10
This article is compiled from the LangChain official blog post "Introducing OpenWiki Brains: Proactive Memory for AI Agents" (published 2026-07-10) and the README of the langchain-ai/openwiki GitHub repo. The source is a vendor release, and all capability descriptions and roadmap previews reflect the official line.