Emanuele Fenocchi
102 posts
Emanuele Fenocchi
@efenocchi1
Machine learning engineer | AI & data-driven systems | AGI is still very far away, but it's already here
Mountain View Katılım Aralık 2023
303 Takip Edilen34 Takipçiler
Prototyping how to control 20+ agents
Codex has been making incredible progress
English
Emanuele Fenocchi retweetledi
We have 3 new updates to Hivemind that are in service of our mission: making organizational agents more cost efficient and effective.
1. Proactive search experience for Claude Code + Cursor. After each user prompt, Hivemind automatically searches for relevant stored traces from the past and passes them to the agent as additional context. This improves reasoning and output.
2. Ability to share skills across teams and devices. Skill sharing is a simpler feature: it syncs the skills a user already has in their system through Deeplake, so everyone on the team can access them. Previously, we were more focused on generating and improving skills. This is about sharing existing skills across the team.
3. Ability to create and assign goals. Any teammate can create and assign goals to another that can persist across sessions until marked completed. Agents can automatically reason when the goal has been reached, and will notify the creator of the goal automatically.
All of these new features work to level up your team, reduce errors and redundant work and lower AI token spend.
Get set up with one command line install.
English
Emanuele Fenocchi retweetledi
Emanuele Fenocchi retweetledi
Many asked for proof.
Mario, number 1 individual customer of Cursor, saves $12K/month using Hivemind.
He is the archetype of an AI builder. He runs 1,000 agents concurrently.
Now he uses the saved credits to build out Honeycomb. Which deserves a separate post.
Activeloop@activeloop
English
@efenocchi1 and team have been working tirelessly on Hivemind and it shows as our users are finding great value in the solution. Might be time for y'all to give it a try?
Emanuele Fenocchi@efenocchi1
Really excited to see that the project I’m leading, which we officially released four days ago, just got its first 1K GitHub stars, with 300+ gained in the last 24 hours. It also reached #2 Repository of the Day on GitHub. Really proud to be building this with @KamoAghbalyan, @khustup, @DBuniatyan, and the rest of the team.
English
Really excited to see that the project I’m leading, which we officially released four days ago, just got its first 1K GitHub stars, with 300+ gained in the last 24 hours.
It also reached #2 Repository of the Day on GitHub.
Really proud to be building this with @KamoAghbalyan, @khustup, @DBuniatyan, and the rest of the team.
English
Emanuele Fenocchi retweetledi
Hivemind crossed 500 stars on github. 🚀
and 2.7K weekly installs.
🌟Star us here github.com/activeloopai/h…
Activeloop@activeloop
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.
English
@DBuniatyan Finally, agents can stop having the memory of a goldfish every time you open a new session. Really curious to see how much SkillOpt and the knowledge graph can improve real day-to-day coding workflows
English
Emanuele Fenocchi retweetledi
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.
English
Emanuele Fenocchi retweetledi
We collaborated with @AgentField_ai to open source multi-agentic annotation system for physical AI.
Deep dive at deeplake.ai/blog/agentfield
AgentField.ai@AgentField_ai
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
English
Emanuele Fenocchi retweetledi
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.
AgentField.ai@AgentField_ai
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
English
Emanuele Fenocchi retweetledi
If you haven't seen our tool Transformer Explainer yet, you should check it out.
My talented lab mates Aeree Cho and Grace Kim both presented this at the VISxAI workshop at IEEE VIS in Vienna, and it won the award for best submission!
English
Emanuele Fenocchi retweetledi
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.
Activeloop@activeloop
Hivemind just crossed 100 stars on github 🌟 github.com/activeloopai/h… Beyond memory. Let's compound intelligence!
English
Emanuele Fenocchi retweetledi
Emanuele Fenocchi retweetledi
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
English
Emanuele Fenocchi retweetledi
This project is getting very interesting
Kamo@kamoniium
Yesterday I demoed at @vercel’s America's Next Top Model event alongside @AnthropicAI, @MiniMax_AI, and @Kimi_Moonshot. I showed Skillify, a new Hivemind feature that auto-generates skills from your coding sessions. No commands, no config. Your agent watches what you do, detects repeating patterns, and writes them into skill files that every future session inherits. The part that got people's attention was that this works across agents. Claude Code, Cursor, Codex, Hermes, Pi, and Openclaw. And skills auto-propagate to your whole team at every session start. Your CTO's debugging patterns, your frontend engineer's deploy workflow, are all available to every agent on the team without anyone writing a doc. Agents that compound intelligence, not just execute instructions. deeplake.ai/hivemind
English
Emanuele Fenocchi retweetledi
Hivemind just crossed 100 stars on github 🌟
github.com/activeloopai/h…
Beyond memory. Let's compound intelligence!
Davit@DBuniatyan
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 👇
English
Continual learning, agent traces, and skill generation and maintenance. A lot is going on here 👀👀
Davit@DBuniatyan
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 👇
English