Building Deeplake: the GPU-native, sandboxed Postgres for AI agents.
Joined April 2020
- Tweets 1,432
- Following 200
- Followers 4,260
- Likes 1,129
271 Photos and videos
Pinned Tweet
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 layer that connects Claude Code, Codex, and OpenClaw across sessions and across the entire team.
Tag the teammate who keeps debugging the same bug twice 😂
1
1
6
2,180
Jun 9
Hivemind crossed 500 stars on github. 🚀
and 2.7K weekly installs.
🌟Star us here github.com/activeloopai/hive…
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.
Get them to compound your intelligence.
3
5
512
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 accuracy in Claude Code, 24.8 in Codex, best or tied on all 52 setups tested.
Your codebase becomes a graph-based knowledge base, helping your agent retrieve the right context beyond simple ranking.
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 those skills across all of them. All on your cloud storage.
Now with SkillOpt built in, your skills get trained: 19.1 points of accuracy in Claude Code, 24.8 in Codex, best or tied on all 52 setups tested.
Open source, one line install.
1
11
599
Activeloop retweeted
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 those skills across all of them. All on your cloud storage.
Now with SkillOpt built in, your skills get trained: 19.1 points of accuracy in Claude Code, 24.8 in Codex, best or tied on all 52 setups tested.
Open source, one line install.
98
57
411
410,039
Jun 4
We collaborated with @AgentField_ai to open source multi-agentic annotation system for physical AI.
Deep dive at deeplake.ai/blog/agentfield
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, cross-check video vs trajectory, flag the messy ones.
Disagreements between reasoners get written back as queryable Deeplake fields.
Open source: deeplake.ai/blog/agentfield
1
4
352
Activeloop retweeted
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 reasoning graph to produce new annotation rows
> Deeplake stores the corpus and annotation versions
> raw and derived annotation fields share one schema
> disagreements between the visual and action reasoners become queryable dataset fields
> all open source
Read guest blogpost below.
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, cross-check video vs trajectory, flag the messy ones.
Disagreements between reasoners get written back as queryable Deeplake fields.
Open source: deeplake.ai/blog/agentfield
1
7
11
863
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.
Get them to compound your intelligence.
May 12
Hivemind just crossed 100 stars on github 🌟
github.com/activeloopai/hive…
Beyond memory. Let's compound intelligence!
1
6
11
1,556
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 continued learning that reduces costs and increases speed of development.
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”
Community note
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
3
7
1,173
May 12
Hivemind just crossed 100 stars on github 🌟
github.com/activeloopai/hive…
Beyond memory. Let's compound intelligence!
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 more repeat bugs
we make your intelligence compound.
here's how 👇
1
4
9
1,777
Apr 15
Focus on the work that matters.
Let your agents powered by Hivemind handle the rest.
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 OpenClaw could surface progress, blockers, and momentum automatically.
No nagging required.
You get your mornings back.
Engineers feel less monitored.
Everyone stays in sync.
1
3
319
Activeloop retweeted
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 OpenClaw could surface progress, blockers, and momentum automatically.
No nagging required.
You get your mornings back.
Engineers feel less monitored.
Everyone stays in sync.
1
6
8
1,286
Activeloop retweeted
Apr 13
YOU LITERALLY JUST RUN 4 COMMANDS TO INSTALL HIVEMIND SO CLAUDE STOPS GETTING AMNESIA EVERY TIME THE TERMINAL CLOSES.
AND IT'S FREE & OPEN-SOURCE!
NOW GO BUILD!
7
30
91
52,346
Activeloop retweeted
Apr 13
This is going to save so many hours.
Hivemind = shared memory layer for Claude Code Codex OpenClaw.
8
13
27
7,231
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 layer that connects Claude Code, Codex, and OpenClaw across sessions and across the entire team.
Tag the teammate who keeps debugging the same bug twice 😂
1
1
6
2,180
Apr 8
Jack's right: "Companies move fast or slow based on information flow." But framing it as a worker hierarchy problem is losing the plot.
Look at where the actual work is moving: agents.
Quick history:
Email got messy. Slack fixed it.
Then humans kept dropping balls anyway. Someone's offline, a thread dies, marketing has no idea what eng shipped, the handoff never happens.
And now Slack itself is the slog. What if you could spend a fraction of the time in it?
Meanwhile, your agents are in the pre-Slack era:
• Your Claude Code agent has no clue what your coworker's OpenClaw agent decided yesterday.
• Marketing's agent can't see what sales's agent promised the customer.
• Product's agent has no idea what engineering's agent already shipped.
Same company, same project, totally separate brains. The fastest workers on your team are stuck on the slowest part of your stack.
Deeplake Hivemind fixes it. One install and your agents share memory across sessions, across teammates, across tools: Claude Code, OpenClaw, Codex, whatever.
When one agent learns something, every agent on your team knows.
No Slack pings. No status updates. No "wait, did you tell the VP?"
Just shared context, flowing automatically.
Slack was for humans. Hivemind is for the things actually doing the work now.
Comment HIVEMIND and we'll DM you $100 in free credits. Run the experiment with your crew.
1
4
10
665