
not read yet
Use
- For
- Teams running client projects who want shared memory across their members' Claude agents.
- Price
- Free plan · From $9.99/mopricing page, read Oct 24, 2026
- Activity
- Actively maintainedrelease 4 weeks ago
- Used for
- Onboard new teammates with project context before client calls
- Record client decisions with dates and alternatives considered
- Share one project memory across a team's Claude connections
- Has an MCP server (1 in the registry)public registry →
Free plan · From $9.99/mo
- Privacy policy updated2026-09-05privacy policy ↗
These are agent-wiki's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.
- MCP servercom.getagentwiki/agent-wikiverified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-24
- Address to connectgetagentwiki.com/mcp
- MCP docsgetagentwiki.com/mcp-knowledge-basethe vendor's page ↗
- Status pagelinked from the homepagegetagentwiki.com/health ↗
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1

MDflowMCP · sign-in
Stores markdown files in shared workspaces with a browser editor, tasks from checkboxes, public knowledgebase links, and API and MCP access.
182ActiveFrom ≈ $5.59/mo - #2

NeverWrite
Stores markdown notes and files locally, with AI agents that draft and restructure content as reviewable changes.
106ActiveFree - #3

StashrMCP · sign-in
Saves bookmarks from any platform, tags them with AI, and makes them searchable for you or your agents.
68ActiveFrom $6/mo - #4

HjarniMCP · sign-in
Stores plans, decisions and preferences as markdown notes that ChatGPT and Claude can search and edit across chats.
35ActiveFrom $12/mo2026 - #5

emdlyMCP · open
Hosts markdown skill playbooks that agents install into Claude over MCP or with a single CLI command, plus browse, upvote and publish.
18Active - #6

Wuniq Studio
Stores and syncs structured project knowledge for AI assistants to access across sessions.
17Active2026
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use agent-wiki for?
Sign in to leave a noteWhat is agent-wiki?
Gives a team one shared wiki per client project that Claude and other MCP-connected agents read and write. It is listed in the Atlas under Knowledge.
Who is agent-wiki for?
Teams running client projects who want shared memory across their members' Claude agents.
How much does agent-wiki cost?
agent-wiki has a free plan; paid plans start at $9.99/mo, per its pricing page on 2026-10-24.
Is agent-wiki free?
Yes, agent-wiki has a free plan, per its pricing page on 2026-10-24.
Do people use agent-wiki?
Little sign of use.
Is agent-wiki still maintained?
Actively maintained: release 4 weeks ago.
How do I cancel agent-wiki?
In its own words (terms of service, 2026-10-24): “If we believe your use is abusive, unsafe, unlawful, creates security risk, degrades the service, or attempts to evade limits, we may throttle activity, disable assistant connections, remove access to specific content, suspend your account, cancel your subscription, or terminate service.”
What are alternatives to agent-wiki?
In Knowledge, by use: MDflow, NeverWrite, Stashr, Hjarni, emdly, Wuniq Studio.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.