- Resolves the same project read keys for search results, explicit timeline anchors, query-selected timeline anchors, and selected observation reads.
- Keeps adopted records visible while excluding unrelated or unadopted records and respecting platform-source filters.
- Preserves the Smart default three-step workflow and the optional dumbsearch alternative introduced in 15.0.0. No API or schema migration is required.
Claude Mem by Alex Newman
Memory plugin built for Claude Code: it captures what the agent does during a session, compresses it into AI-written summaries and injects the relevant context into later sessions, so work continues after a session ends. It also installs for Codex, Gemini, OpenCode, Copilot, OpenClaw and other agents. The engine runs locally for free; CMEM Pro adds a hosted observer, cloud sync across machines and a private MCP link.
Agent tooling for cost, context and memory
New · Added to AgentGid on Oct 11, 2026Memory plugin for coding agentsOpen source · Apache-2.0Free to start
Use it in: CLI MCP server Web app Works with: MCP Own API key
Price
Free + $30/mo
free tier available
Popularity
#42 in Agent tooling
Gid Score 34 / 100 · #42 of 65 ranked agent tools
Trend
Slowing down
usage down 14.9% over 30 days
Development
Actively updated
latest 15.0.1, yesterday
Community
102K GitHub stars
15.5K package downloads a week
Usage data: latest readings Oct 18 to Oct 21, 2026, last checked Oct 21, 06:34 UTC. Date of each number
What Claude Mem does
Claude Mem is a memory plugin for coding agents from Alex Newman, first released in August 2025. You use it through a command-line tool, MCP server and web app. Its documentation covers your own API key. It can run models from Anthropic, Google and OpenRouter. Paid plans start at $30 a month; there is a free tier.
Key facts
| Maker | Alex Newman |
|---|---|
| Type | Memory plugin for coding agents |
| First released | August 2025 |
| License | Apache-2.0 |
| Interfaces | CLI, MCP server, Web app |
| Main language | TypeScript |
| Open issues and PRs | 105 |
Pricing
The claude-mem engine is free and open source (Apache-2.0). CMEM Pro (hosted observation and cloud sync) is $30 a month after a 30-day free trial; Heavy ($70) and CMEM Max ($100) include more usage. Model or provider usage may cost extra.
Source: official pricing page, checked Oct 11, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itCLI, MCP server, Web app
- Model providersanthropic, google, openrouter
- Feature comparisonAll agents
- Closest alternativeOpenShell · all alternatives
What's new in Claude Mem: October 2026 so far
October brought major architectural improvements to Claude Mem's search and recall system, a new team collaboration feature, and a redesigned request dashboard. The month also saw significant performance optimizations and the introduction of version 15.0 with a new Smart-first recall workflow.
Action needed: Old memsearch guided/auto API and flashsearch calls must be replaced with the new Smart workflow or explicit dumbsearch.
- Redesigned requests dashboard with cards, lists, and agent views showing live status and readable summaries of work in progress.
- New Smart recall workflow that progressively fetches memories through search, timeline context, and detailed observations.
- TeamBrain integration allowing users to join teams, sync work state to the cloud, and see team briefs in SessionStart.
- Major performance improvements including indexed newest memories, local-first context building, and background cloud sync.
22 releases this month · summarised from the official release notes · all months
AgentGid articles about Claude Mem
Get started with Claude Mem
| npm | npm install -g claude-mem |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer.
Claude Mem alternatives
Best Claude Mem alternatives compared · All agent tooling for cost, context and memory
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
OpenShellNVIDIA |
77 | 101K | down 14.1% | up 381.4% | 16.8K+103/day | 0.1.5yesterday | Free (OSS) | |||
| 2 |
|
72 | 22.9M | up 4.3% | — | 61.7K+79/day | 1.104.5today | Free (OSS) | |||
| 3 |
NVIDIA NemoClawNVIDIA |
69 | — | — | — | 22.8K+10/day | — | Free (OSS) | |||
| 4 |
|
64 | 9.5M | down 17.1% | up 17.7% | 36.1K+48/day | 4.66.0yesterday | Free + $29/mo | |||
| 5 |
|
64 | 2M | down 19.8% | up 0.3% | 194K+350/day | 2.11.04mo ago | Free + $16/mo | |||
| 6 |
|
60 | 3.2M | down 14.5% | up 21.9% | 14.5K+21/day | 2.11.2yesterday | Free + $150/mo | |||
| No agents match that filter. | |||||||||||
Ratings from people who use Claude Mem
No ratings yet. Used Claude Mem? Rate it and say what it is good and bad at.
Claude Mem news
-
Claude Mem 15.0.1 released
Resolves the same project read keys for search results, explicit timeline anchors, query-selected timeline anchors, and selected observation reads.; Keeps adopted records visible while excluding unrelated or unadopted records and respecting platform-source…
-
Claude Mem 14.0.1 released
Cards keep the agent who did the work when new updates arrive, instead of showing Unassigned work. (+2 more releases that day)
-
Claude Mem gained 3,601 GitHub stars in a week
Now at 100K stars, against about 916 a week over the month before.
-
Claude Mem passes 100K GitHub stars
-
10 agents added to AgentGid
Paperclip, Graphify, Agent-Reach, ECC, OpenMontage, Ruflo, OmniRoute, Claude Mem, Ragflow, Openhuman
What changed: recent Claude Mem releases
73 stable releases in the last 90 days · Monthly summary · Full changelog
- Use the mem-search skill for default Smart recall. Local tools are search → timeline → getobservations; Cloud/Pro starts with memorysearch and can fetch selected summaries with getsummaries.
- Replace calls to the old memsearch guided/auto API and flashsearch with the Smart workflow, or explicitly choose dumbsearch for a shallow lookup. Auto/guided modes and continuation cursors are…
- Refresh existing MCP connections so clients load the new tool catalog and descriptions.
- Cloud timeline supports context anchored to a selected search result.
- Standalone-server recall stays scoped to its configured server project rather than reading a local worker's memory.
- Selected-detail output reports its bounds honestly and preserves selected record identities when long content must be shortened.
Earlier releases
- Cards keep the agent who did the work when new updates arrive, instead of showing Unassigned work.
- Cards, List and Agents views. Full-width request cards with the title, a plain-language summary, who worked on it and the project. Switch to a sortable list or a view by agent. "Attention first"…
- Readable summaries. Each request gets a short everyday-language summary of what happened and the next step, written by the model you've already configured. The last good summary stays visible…
- Live status. In progress, Needs you, No recent update, Ready to check and Checked update as work is recorded, without the page jumping while you read.
- Review. Mark a result as checked yourself, so an agent reporting "done" is never mistaken for a person confirming it.
- Drill down. Open any request to see the work behind it: workstreams, recorded evidence and the original request.
- Codex: skips next-message suggestion and rollout-consolidation helper prompts (#4812).
- build delegates a coding session through make-plan, do, and babysit.
- release delegates publication through version-bump and childhood.
- build-and-release runs both, merging the ready PR before continuing from updated main.
- Restores the existing childhood skill so post-release verification is included.
- npx claude-mem teambrain join <invite-link> connects this install to a TeamBrain team using the same device-code sign-in as install. You approve the device in the browser, then choose which…
- Members who join with a team seat keep their own local observer — joining never switches your observer provider.
- When an install belongs to a team, SessionStart adds a short team brief: open collisions in this project, recent plans and decisions, who else is active, and items delegated to you. Agents also…
- The agent's work-state tracker (workstatewrite / workstateread) now syncs to the cloud as a workstate content kind, for accounts where the sync server enables it. Until then rows wait locally —…
- The Claude observer can batch queued events (opt-in).
- Viewer: the NOTES summary section has its own icon (#4776); long prompts clamp behind a "Show more" disclosure (#4765).
Claude Mem prices over time
Anthropic OpusAnthropic SonnetAnthropic Haiku
Claude Mem popularity and usage data
Claude Mem was downloaded 15.5K times from npm in the week ending Oct 18, 2026, down 16.7% on the week before and down 14.9% over the last 30 days compared with the 30 before. The GitHub repository has 102K stars, 8,111 of them added in the last 30 days. The latest stable release is 15.0.1, published Oct 20, 2026; there were 28 stable releases in the past 30 days. It was mentioned in 1 Hacker News posts and comments over the last 30 days.
Download the raw daily series: claude-mem.csv
Gid Score breakdown
Adoption27
Community84
Attention0
Momentum35
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Oct 18, 2026 | Oct 21, 06:25 UTC |
| GitHub stars | Oct 21, 2026 | Oct 21, 06:32 UTC |
| Website rank (Tranco) | Oct 20, 2026 | Oct 21, 06:34 UTC |
| Hacker News mentions | Oct 20, 2026 | Oct 21, 06:33 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Claude Mem FAQ
How much does Claude Mem cost?
The claude-mem engine is free and open source (Apache-2.0). CMEM Pro (hosted observation and cloud sync) is $30 a month after a 30-day free trial; Heavy ($70) and CMEM Max ($100) include more usage. Model or provider usage may cost extra.
Is Claude Mem open source?
Yes. Claude Mem is open source, released under the Apache-2.0 license.
How popular is Claude Mem?
Claude Mem was downloaded 15.5K times from npm in the week ending Oct 18, 2026, down 16.7% on the week before and down 14.9% over the last 30 days compared with the 30 before. The GitHub repository has 102K stars, 8,111 of them added in the last 30 days. The latest stable release is 15.0.1, published Oct 20, 2026; there were 28 stable releases in the past 30 days.
What is the latest version of Claude Mem?
The latest stable release we track is 15.0.1, published on Oct 20, 2026.
What are the alternatives to Claude Mem?
The closest alternatives in the same category by Gid Score are OpenShell, LiteLLM, NVIDIA NemoClaw, Langfuse.
For the makers of Claude Mem badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/claude-mem/)[](https://agentgid.com/agents/claude-mem/)[](https://agentgid.com/agents/claude-mem/)Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
npm: claude-mem. GitHub: thedotmack/claude-mem. Site rank: claude-mem.ai on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: claude-mem.ai, github.com, npmjs.com.