Activeloop (@activeloop) / X

Activeloop

1,432 posts

Activeloop

@activeloop

Building Deeplake: the GPU-native, sandboxed Postgres for AI agents.

Mountain View, CA

Joined April 2020

Pinned
Activeloop
@activeloop
Apr 13
One session ends → poof. Everything important disappears. A teammate cracks a brutal prod issue → it dies in their terminal forever. Next week you’re debugging the exact same damn problem for the third time. We were so done with it. So we built Hivemind. A shared memory
Davit
@DBuniatyan
Apr 13
Article
When Claude session ends, everything important disappears. Finally fixed the agent amnesia problem.
TLDR: I gave my Claude Code, Codex & OpenClaw agents a shared brain. Now they never forget a fix, a decision, or a hard-won trace again. You know that sick feeling as an engineer. You (or your...
2.2K
Activeloop
@activeloop
Jun 9
Hivemind crossed 500 stars on github. 🚀 and 2.7K weekly installs. 🌟Star us here github.com/activeloopai/h…
Activeloop
@activeloop
May 28
Hivemind just crossed 250 stars on github 2K weekly downloads on NPM. 🚀 Connect coding agents to a shared brain > Collect traces into deeplake > Auto-optimize skills > Share across agents, machines and teammates Your agents continuously learn from each other's experience.
508
Activeloop
@activeloop
Jun 8
Hivemind helps coding agents get smarter with every team interaction, across all your agents, not just one. SkillOpt is what makes it real: your skills don't just accumulate, they get trained on your own traces and sharpened over time. The result is measurable. +19.1 points of
Davit
@DBuniatyan
Jun 8
Coding agents that actually get better the more your team uses them. Introducing Hivemind: continual learning for AI coding agents. Hivemind turns the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, OpenClaw, Pi) into reusable skills, then pushes
00:00
596
Activeloop reposted
Davit
@DBuniatyan
Jun 8
Coding agents that actually get better the more your team uses them. Introducing Hivemind: continual learning for AI coding agents. Hivemind turns the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, OpenClaw, Pi) into reusable skills, then pushes
00:00
409K
Activeloop
@activeloop
Jun 4
We collaborated with @AgentField_ai to open source multi-agentic annotation system for physical AI. Deep dive at
AgentField.ai
@AgentField_ai
Jun 4
Agentic LLM systems this year have mostly gone to coding, browsing, research. With the @activeloop (Deeplake) team, we pointed agents at a job they don't usually do: curating a robotics dataset. Roboscribe-AF automates the work a human curator would do — segment episodes,
A Deployable Annotation Service for Robotics Datasets
From deeplake.ai
351
Activeloop reposted
Davit
@DBuniatyan
Jun 4
Physical AI still requires manual annotation despite all advancements in visual understanding. @activeloop collaborated with @AgentField_ai. outcome is Roboscribe-AF to automatically annotate multi sensory data with an agentic swarm. how it works > AgentField runs the
AgentField.ai
@AgentField_ai
Jun 4
Agentic LLM systems this year have mostly gone to coding, browsing, research. With the @activeloop (Deeplake) team, we pointed agents at a job they don't usually do: curating a robotics dataset. Roboscribe-AF automates the work a human curator would do — segment episodes,
862
Activeloop
@activeloop
May 28
Hivemind just crossed 250 stars on github 2K weekly downloads on NPM. 🚀 Connect coding agents to a shared brain > Collect traces into deeplake > Auto-optimize skills > Share across agents, machines and teammates Your agents continuously learn from each other's experience.
Activeloop
@activeloop
May 12
Hivemind just crossed 100 stars on github 🌟 github.com/activeloopai/h… Beyond memory. Let's compound intelligence!
1.6K
Activeloop
@activeloop
May 26
Replying to @activeloop
Open source. Check it out at
github.com
GitHub - activeloopai/hivemind: One brain for all your agents
One brain for all your agents. Contribute to activeloopai/hivemind development by creating an account on GitHub.
139
Activeloop
@activeloop
May 26
This is one of the exact problems that our Hivemind plugin was built to solve for Claude Code, but also for Codex and Cursor too. It prevents duplicate work, creating slash command skills from agent traces so the entire team at a company can benefit from prior work. True
Vivek Sen
@Vivek4real_
May 24
BREAKING: MICROSOFT JUST ANNOUNCED TO BAN ITS OWN ENGINEERS FROM USING AI DUE TO THE COST OF USING IT. VP OF NVIDIA SAID, “THE COST OF AI FOR MY TEAM WAS MORE THAN HUMANS” “AI CAN COST MORE THAN HUMAN WORKERS NOW”
00:00
Readers added context
Microsoft did not ban its engineers from using AI. Rather they canceled their Anthropic contracts and told their engineers to use their own internal AI (copilot) instead. eu.36kr.com/en/p/382445783… thestreet.com/technology/mic… thenextweb.com/news/microsoft…
1.2K
Activeloop
@activeloop
May 12
Hivemind just crossed 100 stars on github 🌟 github.com/activeloopai/h… Beyond memory. Let's compound intelligence!
Davit
@DBuniatyan
May 11
today, we're going beyond memory. your org's agents shouldn't just remember what happened. they should learn from their experience. Hivemind takes agent traces and codifies them into skills every agent on your team can use. > no more explanations > no more duplicate work > no
1.8K
Activeloop
@activeloop
Apr 29
Article
From Knowledge Graph to Living Memory: Forge with Deeplake and Hivemind
This is a guest post from Idean Moslehi, Founder and CEO of Frowg Systems, Inc. How Forge combines Activeloop's Deeplake database and Hivemind memory layer with governed graph intelligence to create a...
794
Activeloop
@activeloop
Apr 15
Focus on the work that matters. Let your agents powered by Hivemind handle the rest.
Davit
@DBuniatyan
Apr 15
Engineering managers shouldn’t have to play detective every morning. But too often, that’s the job: standups get skipped tickets stay stale and status updates become a scavenger hunt. What if your tools just told you what changed? An AI layer across Claude Code, Codex, and
00:00
319
Activeloop reposted
Davit
@DBuniatyan
Apr 15
Engineering managers shouldn’t have to play detective every morning. But too often, that’s the job: standups get skipped tickets stay stale and status updates become a scavenger hunt. What if your tools just told you what changed? An AI layer across Claude Code, Codex, and
00:00
1.3K