feed · watching · stats · help with your tokens
thedotmack/claude-mem
claude-mem preserves context across coding-agent sessions by capturing tool usage and generating semantic summaries.
It stops an agent from forgetting a project between sessions by capturing tool observations, summarizing them and recalling them later. It runs as a local worker service with a web viewer and search endpoints, managed by Bun.
Similar
- KKKKhazix/agent-autoloop
Agent Autoloop lets a command-line agent pick up work in the background and follow it through, asking for a decision only when something is uncertain.
- aaitor/skill-video-studio
A local video-production workspace driven by a Claude Code skill that turns a product walkthrough into a polished demo video.
- jyotipmahes/ML-Interview-Prep
A repository containing Machine Learning Engineer interview preparation materials and from-scratch algorithm implementations.
- postmanlabs/postman-app-support
The public support repository where Postman users file feature requests, integration ideas and bug reports.
- JustVugg/colibri
colibri is a C inference engine that runs very large open mixture-of-experts models on the machine you already have.
- deepseek-ai/dsh-superagent-prototype
dsh-superagent is a research prototype for a proactive coding agent that works on a single GitHub repository using DeepSeek Harness.
- anthropics/FlashProve
FlashProve is a research prototype for zero-knowledge proofs of AI inference that allows providers to prove model identity without revealing weights.
- Muvon/octomind
Octomind is an open-source coding agent harness that gives an LLM real access to a repository through MCP tools.
sources
Claims below include README evidence. A matching quote or worker agreement does not establish that a claim is correct. Category majority among 2 workers. Version 1.
claude-mem preserves context across coding-agent sessions by capturing tool usage and generating semantic summaries.
Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It stops an agent from forgetting a project between sessions by capturing tool observations, summarizing them and recalling them later.
Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It runs as a local worker service with a web viewer and search endpoints, managed by Bun.
Local HTTP API with web viewer UI and search endpoints, managed by Bun
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Context survives across sessions.
Context survives across sessions
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Layered memory retrieval with visible token cost.
Layered memory retrieval with token cost visibility
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Queries project history through a three-step mem-search skill.
Query your project history with the three-step mem-search skill
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Private tags exclude sensitive content from storage.
Use `<private>` tags to exclude sensitive content from storage
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Screenshots are opt-in and off by default.
**Screenshots (opt-in, off by default)**
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Provides memory search through four MCP tools.
Claude-Mem provides intelligent memory search through **4 MCP tools**
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Filters results before fetching details to save context tokens.
**~10x token savings** by filtering before fetching details
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Optional TeamBrain shared workspace with work lists, member attribution and linked findings.
An optional shared workspace beside My Work, with real team work lists, member attribution and linked findings.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Backs up memories to cmem.ai, with the worker syncing on write.
Back up your memories to cmem.ai — no daemon, the worker syncs on write
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Search project history with a three-step mem-search skill
Query your project history with the three-step mem-search skill
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Layered memory retrieval that shows token cost
Layered memory retrieval with token cost visibility
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Also installs for T3 Code with Codex and Claude Code providers
Or install for **T3 Code** (Codex and Claude Code providers)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Optional real-time observation feeds to Telegram, Discord and Slack on OpenClaw
optional real-time observation feeds to Telegram, Discord, Slack, and more
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Requires Node.js 20.0.0 or higher.
**Node.js**: 20.0.0 or higher
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: A global npm install brings only the SDK and library, not the plugin hooks or worker service.
`npm install -g claude-mem` installs the **SDK/library only**
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: On Windows, npm must be installed and added to the PATH.
Make sure Node.js and npm are installed and added to your PATH.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Grok Bot has no host hooks, so its integration watches chat log files instead.
Grok Bot has no host hooks, so we watch the chat log files.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: When the free trial ends, memory falls back to the Anthropic plan unless you subscribe.
When the free trial ends, memory automatically falls back to your Anthropic plan unless you subscribe.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: OpenCode support needs version 1.3.4 or later.
This works with OpenCode 1.3.4 or later, including OpenCode 2.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Installing from npm gives only the SDK, without plugin hooks or the worker
it does not register the plugin hooks or set up the worker service
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The hosted observer needs a sign-in and has a 30 day free trial
unlocks the **claude-mem observer** with a **30 Day Free Trial**
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
ai-ml · developer-tools