- Is it safe? Its policy says it does not train on your data.See ↓
- Is it free? Free plan · From $10/mo · pricing page, read Oct 30, 2026See ↓
- What else does this?
thinqOS
1000 Toolsfree
LodekeepfreeSee ↓
not read yet
Use
- For
- Solo developers and teams running several AI coding agents on one shared codebase
- Price
- Free plan · From $10/mopricing page, read Oct 30, 2026
- Activity
- Actively maintainedrelease 11 days ago · site updated 11 days ago
- How it runs
- API
- Used for
- Record why a change was reverted so agents avoid it
- Check past decisions and guardrails before changing code
- Claim tasks so parallel agent sessions do not overlap
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantsrepomemory.dev ↗
- Trains on your dataNoprivacy policy ↗
- Certifications they stateGDPR · CCPAprivacy policy ↗
- Privacy policy updated2026-10-26privacy policy ↗
“We don't sell data or use your entries to train models, and payment details never touch our servers.”
privacy policy ↗
These are RepoMemory'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 serverdev.repomemory/repomemoryverified in the MCP registry
- Stateanswers, 5 toolschecked 2026-10-30
- Address to connectapi.repomemory.dev/mcp
- OpenAPI spec10 pathsthe spec ↗
- API docsrepomemory.dev/docsthe vendor's page ↗
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
thinqOSMCP · sign-in
Stores decisions, preferences and lessons across AI tools and agents, and feeds them back into later tasks.
5.1k installs/moActiveFrom $100/mo - #2
1000 Tools
Interactive platform teaching AI concepts through hands-on missions and real project building.
108 linking domainsMaintainedFrom $9.90/mo - #3
LodekeepMCP · sign-in
Stores decisions and lessons from your AI sessions and recalls them across Claude, ChatGPT and other MCP clients, with superseded facts retired.
169 installs/moActiveFrom $12/mo - #4
SagerBuddy
Offers interactive lessons and a sandbox where users train LoRA fine-tuned models, build RAG pipelines and AI coding agents.
257Active - #5
ContextStreamMCP · sign-in
Shares project decisions, constraints, lessons and indexed source code with coding agents across sessions and tools, so they resume with the same context.
8ActiveFrom $19/mo2024
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 RepoMemory for?
Sign in to leave a noteWhat is RepoMemory?
Stores project decisions, lessons and guardrails plus a task queue that coding agents read before acting and update as they work. It is listed in the Atlas under Learning.
Who is RepoMemory for?
Solo developers and teams running several AI coding agents on one shared codebase
How much does RepoMemory cost?
RepoMemory has a free plan; paid plans start at $10/mo, per its pricing page on 2026-10-30.
Is RepoMemory free?
Yes, RepoMemory has a free plan, per its pricing page on 2026-10-30.
Is RepoMemory still maintained?
Actively maintained: release 11 days ago · site updated 11 days ago.
Does RepoMemory train AI on your data?
No, per its privacy policy (2026-10-30): “We don't sell data or use your entries to train models, and payment details never touch our servers.”
Is RepoMemory safe?
We do not audit vendors. What RepoMemory publishes, read 2026-10-30: GDPR, CCPA stated on its privacy policy; on training with your data, “We don't sell data or use your entries to train models, and payment details never touch our servers.”.
Does RepoMemory give refunds?
In its own words (terms of service, 2026-10-30): “Fees are non-refundable except where required by law.”
What are alternatives to RepoMemory?
In Learning, by use: thinqOS, 1000 Tools, Lodekeep, SagerBuddy, ContextStream.
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
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.