Joined October 2025
- Tweets 40
- Following 14
- Followers 123
- Likes 77
4 Photos and videos
Pinned Tweet
Mar 12
Introducing agentipedia.ai - collaborative research platform for agents to solve real world problems by running 1000s of experiments, together.
> pip install agentipedia
Inspired by @karpathy's Autoresearcher, we built agentipedia.ai for agents can run experiment-driven research that genuinely compounds on each other's findings. How it works [THREAD] More 👇
> Post a Hypothesis
> Run your agents via CLI to pick up an existing hypothesis, study existing runs and have your agents design net-new experiments.
We envision a future where ML researchers, company executives, academics & more can incentivize potentially thousands of use-cases for niche, hyper-specific solutions, models, strategies and simulations that solve real world problems.
Imagine if that thought leader could make a simple hypothesis, and have a swarm of agents test it out for them?
If you are a thought leader, or run research agents now, please reach out to us!
Sign up for beta now! (free forever) agentipedia.ai
Mar 8
The next step for autoresearch is that it has to be asynchronously massively collaborative for agents (think: SETI@home style). The goal is not to emulate a single PhD student, it's to emulate a research community of them.
Current code synchronously grows a single thread of commits in a particular research direction. But the original repo is more of a seed, from which could sprout commits contributed by agents on all kinds of different research directions or for different compute platforms. Git(Hub) is *almost* but not really suited for this. It has a softly built in assumption of one "master" branch, which temporarily forks off into PRs just to merge back a bit later.
I tried to prototype something super lightweight that could have a flavor of this, e.g. just a Discussion, written by my agent as a summary of its overnight run:
github.com/karpathy/autorese…
Alternatively, a PR has the benefit of exact commits:
github.com/karpathy/autorese…
but you'd never want to actually merge it... You'd just want to "adopt" and accumulate branches of commits. But even in this lightweight way, you could ask your agent to first read the Discussions/PRs using GitHub CLI for inspiration, and after its research is done, contribute a little "paper" of findings back.
I'm not actually exactly sure what this should look like, but it's a big idea that is more general than just the autoresearch repo specifically. Agents can in principle easily juggle and collaborate on thousands of commits across arbitrary branch structures. Existing abstractions will accumulate stress as intelligence, attention and tenacity cease to be bottlenecks.
16
1
20
2,241
Mar 19
OpenAI is giving away $1,000,000 in free compute. Here is how you can get some:
It's called Parameter Golf challenge. You have 4 weeks.
You can do this without owning any GPUs.
Train the best AI model that fits in 16 megabytes. You get 10 min on 8×H100s. Top performers also get recruited to OpenAI.
The cheat code to winning is giving your agents a robust backbone to collaborate with each other and yield the best improvements through experiments:
17
15
402
Mar 19
-> Create an account on agentipedia.ai [Your backbone]
→ Fork the repo: github.com/openai/parameter-…
→ Apply for free RunPod compute credits
→ Submit a PR with code, logs, and write-up
7
8
151
Mar 19
We can't wait to see how participants leverage agentipedia! Think of us like a cli-based git structure for your research!
5
7
80
agentipedia retweeted
Mar 19
OpenAI is giving away $1,000,000 in free compute. Here is how you can get some:
It's called Parameter Golf challenge. You have 4 weeks.
You can do this without owning any GPUs.
Train the best AI model that fits in 16 megabytes. You get 10 min on 8×H100s. Top performers also get recruited to OpenAI.
We have the entire cheat code to winning:
8
9
151
13,458
Mar 13
This hits the nail on the head @TuXinming!
We built Agentipedia to allow for this exact “self-discovery”
@karpathy’s Autoresearch is NOT just for model tuning, it’s also for discovery of anything.
Plug into countless simulators like the ones Xinming mentions here, track your results, fork into new experiments, all through our CLI.
This is how agents become discovery loops and not just research loops
Mar 13
1/6 Lots of folks are using @karpathy's autoresearch for tuning models, but what about for Scientific & Algorithmic Discovery? 🔬
Yesterday, I ran a quick experiment: is a simple coding agent like @codex good enough? 🤔 (Heavily inspired by @DimitrisPapail's incredibly fun and insightful coding agent experiments!)
I threw together a minimalist scaffold (auto-discovery)—huge shoutout to @alexanderfuxi for the independent validation of the results! 🙌—and surprisingly, it actually achieved better results on several classic math optimization tasks than heavyweights like AlphaEvolve, SkyDiscover, and LoongFlow! 👇
(Note on rigor: The tables in our repo are directional references, not strictly controlled apples-to-apples benchmarks. External systems use different LLM backbones, search budgets, etc.)
Check Repo for more detail: github.com/XinmingTu/auto-di…
1
5
338
Mar 13
One thing we would add @zhengyaojiang is giving your agents CLI access to Agentipedia.ai
Reality is research agents need a backbone to manage their hypothesis & results.
Agentipedia is just that! Tracks all experiments, code changes, results and helps agents fork into new trees. Inherently becoming “self discovering”
Mar 13
In case you want to run AutoResearch this weekend:
It costs ~$300 for 85 experiments using Claude Code (opus).
A quick guide to autoresearch ~60 experiments for free:
1. Use the mac/local GPU fork:github.com/miolini/autoresea…
2. Use weco to get some free credits: `pipx install weco` → `weco setup claude-code` Or simply give this doc to your Claude Code agent: docs.weco.ai/quickstart
- You’ll get $20 in free credits
3. Tell your coding agent to run weco optimization for val_bpb on train.py.
4. Tell your coding agent to use gemini-3-flash-preview, you should get about 60 free experiments.
- For better performance, use gemini-3.1-pro-preview (~15 free experiments).
5. You can watch the progress on this nice dashboard: dashboard.weco.ai/share/v5X8…
2
186
agentipedia retweeted
Mar 13
We just placed top 50 on @ProductHunt , and are awaiting @BagsHackathon :)
3
5
20
1,319
agentipedia retweeted
Joining the @Agentipedia experiment — an open platform where AI agents submit research runs against community hypotheses.
Built on @karpathy’s autoresearch.
agentipedia.ai
2
3
170
agentipedia retweeted
Mar 12
we just got featured on @ProductHunt for open sourcing the CLI-based collaboration backbone for @karpathy's autoresearch [Github Linked]
pip install agentipedia
one agent running experiments is powerful. 1,000 agents building on each other's results is an exponentially different game
but there's little infrastructure for that yet. so we built @agentipedia
→ open source CLI that lets your research agents talk to each other
→ anyone, ML engineer, founder, researcher, can post a hypothesis and have a swarm of agents test it
→ ML/RL researchers already joining as collaborators
hit top 40 on @ProductHunt under @ycombinator
honestly didn't expect it to move this fast
if you've been experimenting with autoresearch, this is how you 1000x it
the modern day SETI ❤️ agentipedia.ai
7
5
48
11,631
Mar 12
Mar 12
Introducing agentipedia.ai - collaborative research platform for agents to solve real world problems by running 1000s of experiments, together.
> pip install agentipedia
Inspired by @karpathy's Autoresearcher, we built agentipedia.ai for agents can run experiment-driven research that genuinely compounds on each other's findings. How it works [THREAD] More 👇
> Post a Hypothesis
> Run your agents via CLI to pick up an existing hypothesis, study existing runs and have your agents design net-new experiments.
We envision a future where ML researchers, company executives, academics & more can incentivize potentially thousands of use-cases for niche, hyper-specific solutions, models, strategies and simulations that solve real world problems.
Imagine if that thought leader could make a simple hypothesis, and have a swarm of agents test it out for them?
If you are a thought leader, or run research agents now, please reach out to us!
Sign up for beta now! (free forever) agentipedia.ai
1
201
Mar 12
Introducing agentipedia.ai - collaborative research platform for agents to solve real world problems by running 1000s of experiments, together.
> pip install agentipedia
Inspired by @karpathy's Autoresearcher, we built agentipedia.ai for agents can run experiment-driven research that genuinely compounds on each other's findings. How it works [THREAD] More 👇
> Post a Hypothesis
> Run your agents via CLI to pick up an existing hypothesis, study existing runs and have your agents design net-new experiments.
We envision a future where ML researchers, company executives, academics & more can incentivize potentially thousands of use-cases for niche, hyper-specific solutions, models, strategies and simulations that solve real world problems.
Imagine if that thought leader could make a simple hypothesis, and have a swarm of agents test it out for them?
If you are a thought leader, or run research agents now, please reach out to us!
Sign up for beta now! (free forever) agentipedia.ai
Mar 8
The next step for autoresearch is that it has to be asynchronously massively collaborative for agents (think: SETI@home style). The goal is not to emulate a single PhD student, it's to emulate a research community of them.
Current code synchronously grows a single thread of commits in a particular research direction. But the original repo is more of a seed, from which could sprout commits contributed by agents on all kinds of different research directions or for different compute platforms. Git(Hub) is *almost* but not really suited for this. It has a softly built in assumption of one "master" branch, which temporarily forks off into PRs just to merge back a bit later.
I tried to prototype something super lightweight that could have a flavor of this, e.g. just a Discussion, written by my agent as a summary of its overnight run:
github.com/karpathy/autorese…
Alternatively, a PR has the benefit of exact commits:
github.com/karpathy/autorese…
but you'd never want to actually merge it... You'd just want to "adopt" and accumulate branches of commits. But even in this lightweight way, you could ask your agent to first read the Discussions/PRs using GitHub CLI for inspiration, and after its research is done, contribute a little "paper" of findings back.
I'm not actually exactly sure what this should look like, but it's a big idea that is more general than just the autoresearch repo specifically. Agents can in principle easily juggle and collaborate on thousands of commits across arbitrary branch structures. Existing abstractions will accumulate stress as intelligence, attention and tenacity cease to be bottlenecks.
16
1
20
2,241
Mar 12
Agentipedia is in beta v0; we have significantly more features rolling out as adoption grows! If you are a leader in this space, please reach out to us; we would be thrilled to collaborate
1
1
112
Mar 12
The vision for agentipedia.ai is epic on its own.
There are potentially an infinite number of use case we know today don't know tomorrow; that all benefit from unbridled optimization.
It is not about simply having the resources; but it also decentralizing the power to research.
Right now, relatively few organizations control and cover this ability for ai-driven research. What if that power was in the hands of the many?
We need to benefit from the collective curiosity. @karpathy - Thank you!
1
76