Ex-GitHub CEO launches a new developer platform for AI agents
entire.io> Checkpoints are a new primitive that automatically captures agent context as first-class, versioned data in Git. When you commit code generated by an agent, Checkpoints capture the full session alongside the commit: the transcript, prompts, files touched, token usage, tool calls and more.
This thread is extremely negative - if you can't see the value in this, I don't know what to tell you.
100% agree because there’s a lot of value in understanding how and why past code was written. It can be used to make better decisions faster around code to write in the future.
E.g., if you’ve ever wondered why code was written in a particular way X instead of Y then you’ll have the context to understand whether X is still relevant or if Y can be adopted.
E.g., easier to prompt AI to write the next commit when it knows all the context behind the current/previous commit’s development process.
Sure... you `git add` and context text generated by AI and `git commit` it, could be useful. Does that worth 60 million?
They raised 60 million. The investors think it’s worth 600M+
It’s good to know that a few decades later the same generic Dropbox-weekend take can be made.
99% of projects the take applies to are massive flops. The Dropbox weekend take is usually correct.
People keep saying that, but it's hardly the same thing. We're talking about developer workflow here. It's like someone coming up with Brancher. It's a git branch manager. Use `brancher foo` to replace `git checkout -b foo`. "Remember that comment about rsync and dropbox? Brancher is to git, what dropbox is to rsync"
How is LangChain doing? How about OpenAI's Swarm or their Agent SDK or whatever they called it? AWS' agent-orchestrator? The crap ton of Agent Frameworks that came out 8-12 months ago? Anyone using any of these things today? Some poor souls built stuff on it, and the smart ones moved away, and some are stuck figuring out how to do complex sub-agent orchestration and handoffs when all you need apparently is a bunch of markdown files.
First of all, according to the new doctrine Dropbox could be plagiarized in a weekend by agents.
Secondly what about negative comments about hundreds of startups that failed and were therefore correct?
I love this one so much! The arbitrary decision to cherry-pick critique a particular product to this degree, when it’s something that could be said about 99% of the stuff SV churns out, including in all likelihood anything you’ve ever worked on.
Good thing the comment you're replying to does not lionise 99% of the stuff SV churns out, including in all likelihood anything they've ever worked on. I guess we should just not critique anything out of SV because it's all shit?
That is their first feature.
If it were also their last, I would be inclined to agree.
Good that a one liner comment comes to the rescue of the overlords and is immediately put to the top by image polishing agencies.
We are talking here about a CEO who presided over a company that abused its "customers" by using open source for training while stripping attribution and copyright.
The same CEO repeatedly insulted those very developers, who made his company big and possible in the first place, and told them they'd get obsolete.
He now repeats that same refrain while launching a startup with a vague product.
He clearly hates open source and open source developers. And we should like him and trust another of his companies?
I think if you add some more emotional vitriolic language to your reply you’ll finally, finally get your point across. /s
I built out the same thing in my own custom software forge. Every single part of the collaborative development process is memoized.
I see the utility in this as an extension to git / source control. But how do VCs make money of it?
I have an agent write a file with this template each run:
```markdown # Run NNNN
## First Impressions [What state is the project in? What did the last agent leave?]
## Plan [What will you work on this iteration? Why?]
## Work Log [Fill this in as you work]
## Discoveries [What did you learn? What surprised you? What should the next agent know?]
## Summary [Fill this in before committing] ```
This is surprisingly effective and lets agents easily continue in progress work and understand past decisions.
> Checkpoints run as a Git-aware CLI. On every commit generated by an agent, it writes a structured checkpoint object and associates it with the commit SHA. The code stays exactly the same, we just add context as first-class metadata. When you push your commit, Checkpoints also pushes this metadata to a separate branch (entire/checkpoints/v1), giving you a complete, append-only audit log inside your repository. As a result, every change can now be traced back not only to a diff, but to the reasoning that produced it.
The context for every single turn could in theory be nearly 1MB. Since this context is being stored in the repo and constantly changing, after a thousand turns, won't it make just doing a "git checkout" start to be really heavy?
For example, codex-cli stores every single context for a given session in a jsonl file (in .codex). I've easily got that file to hit 4 GB in size, just working for a few days; amusingly, codex-cli would then take many GB of RAM at startup. I ended up writing a script that trims the jsonl history automatically periodically. The latest codex-cli has an optional sqlite store for context state.
My guess is that by "context", Checkpoints doesn't actually mean the contents of the context window, but just distilled reasoning traces, which are more manageable... but still can be pretty large.
Ignoring the VC economics and awful name, I won’t be as pessimistic as everyone. I see the vision.
That said, nobody knows what the AI future looks like. Entire’s entire thesis is a solution for something we don’t even know we need. It’s a massive bet and uphill battle. Traditionally, dev tool success stories come from grassroots projects of developers solving their own problems and not massive VC funded efforts that tell you what you need to do.
And yet, this is precisely what seed bets are about. You have to try it in order to know whether there is a "there" there.
$1.5M seed bets, maybe. not $60M though
Feature plans generated by agents are often transient documents that fall away once the plan is executed. Ideally, that artifact would be preserved alongside the implementation.
My experience is that Cursor's reliance on VS Code's clunky panel-based UI and jack-of-all-trades harness is holding it back. Likewise, Claude Code shoe-horning a GUI into a TUI and perma-binding to a single model family is not the ideal end-state.
The VC play here? The git context CLI thing is a foundational step that lays the groundwork for a full IDE/workflow tool, I guess.
Why do you want to preserve that artifact?
Either the models are good and this sort of platform gets swept away, or they aren’t, and this sort of platform gets swept away.
Either the business makes a profit before it gets swept away, or it doesn't. This should be your goal: make money before your business dies. If you do that, you succeeded. Businesses are always ephemeral.
This is very well put. I think this platform can be useful but I doubt it can be something as big as the think it will be. At the end of the day it’s just storing some info with your data. I guess they are trying to be the next GitHub (and clearly have the experience :)). I doubt that success can be replicated today with this idea, even with $60 mil to burn
The most interesting thing about everyone trying to position themselves as AI experts is the futility of it: the technology explicitly promises tomorrows models will be better then todays, which means the skill investment is deflationary: the best time to learn anything is tomorrow when a better model will be better at doing the same work - because you don't need to be (conversely if you're not good at debugging and reverse engineering now...)
the best time to learn anything is tomorrow when a better model will be better at doing the same work
doesn’t that presume no value is being delivered by current models?
I can understand applying this logic to building a startup that solves today’s ai shortcomings… but value delivered today is still valuable even if it becomes more effective tomorrow.
That’s true for “tips and tricks” knowledge like “which model is best today” or “tell the model you’ll get fired if the answer is wrong to increase accuracy” that pops up on Twitter/X. It’s fleeting, makes people feel like “experts”, and doesn’t age well.
On the other hand, deeply understanding how models work and where they fall short, how to set up, organize, and maintain context, and which tools and workflows support that tends to last much longer. When something like the “Ralph loop” blows up on social media (and dies just as fast), the interesting question is: what problem was it trying to solve, and how did it do it differently from alternatives? Thinking through those problems is like training a muscle, and that muscle stays useful even as the underlying technology evolves.
It does seem like things are moving very quickly even deeper than what you are saying. Less than a year ago langchain, model fine tuning and RAG were the cutting edge and the “thing to do”.
Now because of models improving, context sizes getting bigger, and commercial offerings improving I hardly hear about them.
I'm pretty much just rawdogging Claude Code and opencode and I haven't bothered setting up skills or MCPs except for one that talks to Jira and Confluence. I just don't see the point when I'm perfectly capable of writing a detailed prompt with all my expectations.
The problem is that so many of these things are AI instructing AI and my trust rating for vibe coded tools is zero. It's become a point of pride for the human to be taken out of the loop, and the one thing that isn't recorded is the transcript that produced the slop.
I mean, you have the creator of openclaw saying he doesn't read code at all, he just generates it. That is not software engineering or development, it's brogrammer trash.
You nailed it. Thats exactly how I feel. Wake me up when the dust settles, and i'll deep dive and learn all the ins and outs. The churn is just too exhausting.
You might wake up in a whole different biome, Rip Van Winkle.
I don't get the pressure. I don't know about you, but my job for a long time has been continually learning new systems. I don't get how so many of my peers fall into this head trip where they think they are gonna get left behind by what amounts to anticipated new features from some SaaS one day.
How do you both hold that the technology is so revolutionary because of its productive gains, but at the same time so esoteric that you better be ontop of everything all the time?
This stuff is all like a weird toy compared to other things I have taken the time to learn in my career, the sense of expertise people claim at all comes off to me like a guy who knows the Taco Bell secret menu, or the best set of coupons to use at Target. Its the opposite of intimidating!
I'm not scared that my skills will be obsolete, I'm scared employers will think they are. The labor market was already irrational enough as it was.
I may just be a "doomer", but my current take is we have maybe 3-5 years of decent compensation left to "extract" from our profession. Being an AI "expert" will likely extend that range slightly, but at the cost of being one of the "traitors" that helps build your own replacement (but it will happen with or without you).
> the technology explicitly promises tomorrows models will be better then todays, which means the skill investment is deflationary
This is just wrong. A) It doesn’t promise improvement B) Even if it does improve, that doesn’t say anything about skill investment. Maybe its improvements amplify human skill just as they have so far.
I have a reading list of a bunch of papers i didn't get through over the past 2 years. it is crazy how many papers on this list are completely not talked about anymore.
I kinda regret going through the SeLU paper lol back in the late 2010s.
But think of all the investor dollars between now and then!
They know hence: forget what it does, it was created by the ex CEO of another commonly used thingy!
>CLI to tie agent context into Git on every push.
Is this the product? I don't want to jump on the detractor wagon, but I read the post and watched the video, and all I gathered is that it dumps the context into the commit. I already do this.
> I already do this.
Hows your ability to get an enterprise to mandate their 5000 employees to use it? That's what most of these types of rounds are about.
This doesn't appear to address that concern.
I guess if I had to do it, I'd reject pushes without the requisite commit to entire/checkpoints/v1. I think their storage strategy is a bit clunky for that, but it can be done. I might look to do something more like the way jujutsu colocates its metadata. I don't think this particular implementation detail makes too much of a difference, though. I got along just fine in a regulated environment by setting a policy and enforcing it before git existed. Ideally, we'd do things for a good reason, and if you can't get along in that world, then it's probably not the right job for you. Sometimes you've got to get the change controls in order before we can mainline your contributions because we have to sustain audits. I don't think this is about forcing people to do something that they otherwise wouldn't do if you told them that it's a requirement of the job.
100%. Day one is to ship the basic capability, which many of us have already vibe-coded... Day two is all the enterprise stuff to make big companies trust AI coding more. That could unlock a lot of revenue. This isn't random at all.
but you don't have a $60M seed and $300M valuation!!!1
Same thought. If anything I'm usually trying to find ways to reduce how much context is carried over.
Isnt this overloading git commits too much ? Like 50kb per commit message
Git is totally fine keeping a few extra text files. These are ephemeral anyway. The working sessions just get squashed down and eliminated by the time I've got something worth saving anyway. At that point, I might keep a overview file around describing what the change does and how it was implemented.
(I will give the agent boom a bit of credit: I write a lot more documentation now, because it's essentially instruction and initial instruction to anything else that works on it. That's a total inversion, and I think it's good.)
The bigger problem is, like others have said, there's no one true flow. I use different agents for different things. I might summarize a lot of reasoning with a cheap model to create a design document, or use a higher reasoning model to sanity check a plan, whatever. It's a lot like programming in English. I don't want my tool to be prescriptive and imposing its technical restrictions on me.
All of that aside: it's impossible that this tool raised $60 million. The problem with this post is that it's supposed to be a hype post about changing the game "entirely" but it doesn't give us a glimpse into whatever we're supposed to by hyped about.
the git commits message description never go away though, unless you're editing the git with BFG cleaner
1. Commit messages go away if you remove the commit, but
2. Don't put it in the message. Put it in files.
I have it (claude, codex) summarise what we've discussed about a design, big change, put it in an MD file and then I correct it, have it re-read it and then do the change.
Then later if it goes off piste in another session tell it to re-read the ADDs for x, y and z.
If someone could make that process less clunky, that would be great. However it's very much not just funnel every turd uttered in the prompt onto a git branch and trying a chug the lot down every session.
what about using git notes to stash the summaries? (https://git-scm.com/docs/git-notes)
Very similar for me. I have a plans folder in my root where I store the plans while they're either under improvement or under implementation. Once they're done they're moved into the plans/old folder. So far it's worked great. It's a couple of manual steps extra but very helpful record.
Pretty much the same thing. I don't find it to be a burden. Regarding the product, I'm willing to believe I just don't see big picture, but without some peek at the magic, I don't know how much easier this could really be.
We went from having new JavaScript frameworks every week to having new AI frameworks every week. I'm thinking I should build a HN clone that filters out all posts about AI topics...
Looking at the most popular agent skills, heavily geared towards react and JS, I think a lot of the most breathless reports of LLM success are weighted towards the same group of fashion-dependant JavaScript developers.
The same very online group endlessly hyping messy techs and frontend JS frameworks, oblivious to the Facebook and Google sized mechanics driving said frameworks, are now 100x-ing themselves with things like “specs” and “tests” and dreaming big about type systems and compilers we’ve had for decades.
I don’t wanna say this cycle is us watching Node jockies discover systems programming in slow motion through LLMs, but it feels like that sometimes.
Create extension that does that. AI can do that for you in 10 minutes
Or, you could perform a public service by creating a HN clone only for bots and try to convince the bots trolling here to go there.
You know the only effective way to do that, right?
Yep exactly, a Perl script
Claude create a clone of Hacker News, no mistakes. Must compile.
Just give me your bank account, claude API, Mother's maiden name, your zip code, your 3 digit security code, and anything else you think I might need to live as malfist the magnificant. Can I call you that?
I've long wished for a 'filter' feature for the hn feed -- namely the old trend of web3 slop -- but with little else than keywords to filter, it would likely be tedious and inaccurate. Ironically, I think with AI/LLMs it could be a little easier to analyze.
one technique i've found useful is i don't click on the link if i'm not interested.
It’s one reason I hoped lobste.rs had taken off. All posts are tagged and you can filter out by tag.
This is how software is being written now. What you propose is like joining a forum called "Small-Scale Manufacturing News" and filtering out all 3D-printing articles.
We want to filter out the irrelevant software :)
This feels interesting because the real problem with AI generated code isn't that it is of better or worse quality than code written by a human, it's that we humans need to audit both types of code. And this platform feels like it addresses this in a novel and traditional way. I like it.
This sounds like a company idea someone just came up with yesterday off the cuff, pitched it, and got money for because of their credentials so no one can really say no to investing in it, despite nothing new or different? What's the service or product and how is it different than every 3rd Show HN?
The context preservation problem is genuinely painful - I've been using task.md files and CLAUDE.md conventions to maintain agent state across sessions, and it's duct tape at best. First-class "checkpoints" that capture reasoning alongside diffs is an appealing idea.
But I'm skeptical of building this as a separate platform rather than as tooling on top of git. The most useful AI dev workflow improvements I've seen (cursor rules, aider conventions, claude hooks) all succeeded precisely because they stayed close to existing tools. The moment you ask developers to switch their entire SDLC stack, adoption becomes the real engineering challenge - not the tech.
Curious whether the open source commitment means the checkpoint format itself will be an open spec that other tools can build on.
I'm pretty happy using Shelley, which stores agent conversations in a Sqlite database. I can refer to a previous conversation and the agent can easily do a Sqlite query to see what happened.
Although this isn't stored in git, I don't see any particularly need to since it's too detailed. Instead I have the agent write design docs (as an alternative to plan mode) and check those in. That seems like enough.
Doesnt the tooling already exist? i.e. you could use `git notes` to attach agent state as checkpoints to Trees, Commits, Tags etc.
The CLI is open source, everyone can use it and it does work with git only. So, no separate platform needed. The platform only provides convenience to view checkpoints at the moment. However you can also view them in the CLI. It's here https://github.com/entireio/cli
Already at a $300 million valuation at seed. Who’s going to join this as a regular IC who gets a pittance in options? I can’t imagine the risk matches the modest potential upside.
60 million SEED round? This is really a thing now?
Take a look at the 500M seed round next :)
> The game has changed. The system is cracking.
Just say what your thing does. Or, better yet, show it to me in under 60 seconds.
Web sites are the new banner ads and headings like that are the new `<blink>`.
> Web sites are the new banner ads and headings like that are the new `<blink>`.
It's been like this since the Dotcom era
Or did you forget that you can do anything at zombo.com?
It appears to be rather slow today, but here's a Wiki link for the uninitiated- https://en.wikipedia.org/wiki/Zombo.com
The domain expired a few days ago and was purchased by someone else and then changed. There's a recreation of the original here https://html5zombo.com/
That's the saddest news I've heard this year.
It's still around, but has been redesigned and it's under "new management". Further proof that the internet is dying.
Wait really?!? I’m surprised at how much that saddens me. What is the point of the internet without zombo com
Exactly ... tired by all the marketing hyperbole talk. Just show what your product does in a simple example / showcase. If it's good, people will like it. You can save yourself a lot of text copy and user time that way.
They'll learn soon enough that selling to developers necessitates speaking clearly.
Dohmke never spoke clearly to developers when he was GitHub's CEO.
A CEO is never speaking to developers, he's speaking to other CEOs.
CEOs have many audiences; great CEOs communicate capably with each.
FWIW it's not entirely clear to me who Entire's long-term customer is, but the (interesting!) CLI that shipped today is very much for developers who are busy building with agents. To the extent that this blog post was trying to reach them, I feel it's more of a miss than a hit.
They will sell to their managers
No. With this kind of bullshit they plan to try to sell to C-levels and board members.
Edit: Actually it may just be aimed at investors. Who cares about having a product?
> Actually it may just be aimed at investors
The fact that the first image you see has "$60M seed" in big text, I have to agree, this does not feel aimed at devs.
The problem is that when it comes to (commercial) developer tools and services, everyone can/wants to be everything, so why let a simple statement or a showcase limit you? "Hey, we are a container scanning service... But we can also be a container registry too, a CI, a KeyValue store, an agent sandbox provider, git hosting? We can do quick dev deployments/preview too. Want a private npm registry? Automated pull request reviews? Code Signing service? We are working on a new text editor btw"
But what if my product is just an attempt to make a cushy exit during the AI bubble?
I feel like these types of pages are less geared towards actual users of the product and more towards the investors who love the vague and flowery language. We're no longer in a world where the path to profitability was the objective goal anyway, it makes sense to me that the marketing of software is becoming decreasingly detached from reality..
It's almost like an extension of the "if you're not paying for the product, you are the product" idea. If you're assessing a tool like this and the marketing isn't even trying to communicate to you, the user, what the product does, aren't you also kind of "the product" in this case too?
Its like a modern day redux of zombo com.
That’s a bit insulting to zombo.com.
AI is everything at zombo.com.
Everything is AI at zombo.com.
I couldn’t figure out what they were doing in the first few screens of scrolling. Moved on.
They also seem bothered by color photography in 2026. All style, no substance.
You need to use AI to summarize the point of articles about AI products
Seems they install a Git hook or something that executes on commit and saves your chatbot logs associated with the commit hash. This is expected to somehow improve on the issue that people are synthesising much more code than they could read and understand, and make it easier to pass along a bigger context next time you query your chatbots, supposedly to stop them from repeating "mistakes" that have already wasted your time.
It is not the system that is on crack ...
What it does? Imagine a multi line commit message.
Yes yes a Dropbox comment. But the problem here is 1 million people are doing the same thing. For this to be worth 60M seed I suspect they need to do something more than you can achieve by messing around locally."
"Claude build me a script in bash to implement a Ralph loop with a KV store tied to my git commits for agent memory."
> Spec-driven development is becoming the primary driver of code generation.
This sounds like my current "phase" of AI coding. I have had so many project ideas for years that I can just spec out, everything I've thought about, all the little ideas and details, things I only had time to think about, never implement. I then feed it to Claude, and watch it meet my every specification, I can then test it, note any bugs, recompile and re-test. I can review the code, as you would a Junior you're mentoring, and have it rewrite it in a specific pattern.
Funnily enough, I love Beads, but did not like that it uses git hooks for the DB, and I can't tie tickets back to ticketing systems, so I've been building my own alternative, mine just syncs to and from github issues. I think this is probably overkill for whats been a solved thing: ticketing systems.
I am going lower level - every individual work item is a "task.md" file, starts initially as a user ask, then add planning, and then the agent checks gates "[ ]" on each subtask as it works through it. In the end the task files remain part of the project, documenting work done. I also keep an up to date mind map for the whole project to speed up start time.
And I use git hooks on the tool event to print the current open gate (subtask) from task.md so the agent never deviates from the plan, this is important if you use yolo mode. It might be an original technique I never heard anyone using it. A stickie note in the tool response, printed by a hook, that highlights the current task and where is the current task.md located. I have seen stretches of 10 or 15 minutes of good work done this way with no user intervention. Like a "Markdown Turing Machine".
That's hilarious, I called it gates too for my reimplementation of Beads. Still working on it a bit, but this is the one I built out a month back, got it into git a week ago.
For me a gate is: a dependency that must pass before a task is closed. It could be human verification, unit testing, or even "can I curl this?" "can I build this?" and gates can be re-used, but every task MUST have one gate.
My issue with git hooks integration at that level is and I know this sounds crazy, but not everyone is using git. I run into legacy projects, or maybe its still greenfield as heck, and all you have is a POC zip file your manager emailed you for whatever awful reason. I like my tooling to be agnostic to models and external tooling so it can easily integrate everywhere.
Yours sounds pretty awesome for what its worth, just not for me, wish you the best of luck.
that's similar to the workflow i built, inspired by Recursive Language Models: https://github.com/doubleuuser/rlm-workflow
This is built in to Claude Code, when you're in plan mode it makes a task MD file, even giving it a random name and storing it in your .claude folder.
I'm confused how this is any different to the pretty standard agentic coding workflow?
Me too. I've been using spec-kitty [0], a fork of Spec Kit. Quite amazing how a short interview on an idea can produce full documents of requirements, specs, tasks, etc. After a few AI projects, this is my first time using spec driven development, and it is definitely an improvement.
Nice, I'll check yours out after work, looks pretty polished.
Task management is fundamentally straightforward and yet workflow specific enough that I recommend everyone just spend a few hours building their own tools at this point.
Beads is a nightmare.
I started off with the original beads and it was definitely a nightmare. However I would recommend using https://github.com/Dicklesworthstone/beads_rust - it's a much simpler implementation of the same concept, without all the random extra stuff thrown on to support Gas Town.
> Checkpoints are a new primitive that automatically captures agent context as first-class, versioned data in Git. When you commit code generated by an agent, Checkpoints capture the full session alongside the commit: the transcript, prompts, files touched, token usage, tool calls and more.
Whether or not useful for agent collaboration, the data here will be more valuable than gold for doing RL training later on.
Agents can save their reasoning into markdown files, and commit those files to Git. Are "Checkpoints" just a marketing term for that, or there's more to it?
Claude Code already does this, you can access it with /resume, /rewind and /fork. I'd imagine building a version that saves in the repo instead of in the home folder would take very minimal effort.
This is about doing it seamlessly and flawlessly then sharing it across a team.
So using something like the compound engineering plugin and committing its "brainstorms", plans, and "solutions"?
I am not willing to share my sheepish prompts with my team. Sorry!
Hah. "If it's not too much trouble, would you mind if we disable the rimraf root feature?"
Gotta bully that thing man. There's probably room in the market for a local tool that strips the superfluous niceties from instructions. Probably gonna save a material amount of tokens in aggregate.
I'm with you. I start every new prompt with: "Good morning", even at midnight. I'll be so embarrassed if that leaks.
LOL
Actually interesting, but how's that different from just putting your learning / decision context into the normal commit text (body) ? An LLM can search that too, and doesn't require a new cli tool.
EDIT: Or just keep a proper (technical) changelog.txt file in the repo. A lot of the "agentic/LLM engineering frameworks" boil down to best approaches and proper standards the industry should have been following decades ago.
After I have an ai dona task, I ask the next one to look at that plan and git diff and so ble check validate
I don't see the need for a full platform that is separate from where my code already lives. If I'm migrating away, it's to something like tangled, not another VC funded company
Christ, a $60m seed round.
The AI fatigue is real, and the cooling-off period is going to hurt. We’re deep into concept overload now. Every week it’s another tool (don’t get me started on Gas Town) confidently claiming to solve… something. “Faster development”, apparently.
Unless you’re already ideologically committed to this space, I don’t see how the average engineer has the energy or motivation to even understand these tools, never mind meaningfully compare them. That’s before you factor in that many of them actively remove the parts of engineering people enjoy, while piling on yet another layer of abstraction, configuration, and cognitive load.
I’m so tired of being told we’re in yet another “paradigm shift”. Tools like Codex can be useful in small doses, but the moment it turns into a sprawling ecosystem of prompts, agents, workflows, and magical thinking, it stops feeling like leverage and starts feeling like self-inflicted complexity.
It's an ex-CEO of Github. He can raise $60m on any idea.
> I don’t see how the average engineer has the energy or motivation to even understand these tools, never mind meaningfully compare them
This is why I use the copilot extension in VS code. They seem to just copy whatever useful thing climbs to the surface of the AI tool slop pile. Last week I loaded up and Opus 4.6 was there ready to use. Yesterday I found it has a new Claude tool built in which I used to do some refactoring... it worked fine. It's like having an AI tool curator.
Maybe just learning 1 or 2 of such tools is enough ?
Probably, but which ones, do we get to a place where you have X years experience in Gastown development, but I only have Y years experience in Entire.
I also keep getting job applications for AI-native 'developers' whatever that means.
You will learn a lot about the underlying LLM / technology whichever tool you use though
History has shown that by delaying learning the next greatest tech, you may avoid learning it altogether.
Your point about the overwhelming proliferation of AI tools and not knowing which are worth any attention and which are trash is very true I feel that a lot today (my solution is basically to just lean into one or two and ask for recommendations on other tools with mixed success).
The “I’m so tired of being told we’re in another paradigm shift” comments are widely heard and upvoted on HN and are just so hard to comprehend today. They are not seeing the writing on the wall and following where the ball is going to be even in 6-12 months. We have scaling laws, multiple METR benchmarks, internal and external evals of a variety of flavors.
“Tools like codex can be useful in small doses” the best and most prestigious engineers I know inside and outside my company do not code virtually at all. I’m not one of them but I also do not code at all whatsoever. Agents are sufficiently powerful to justify and explain themselves and walk you through as much of the code as you want them to.
Yeah, I’m not disputing that AI-assisted engineering is a real shift. It obviously is.
My issue is that we’ve now got a million secondary “paradigm shifts” layered on top: agent frameworks, orchestration patterns, prompt DSLs, eval harnesses, routing, memory, tool calling, “autonomous” workflows… all presented like you’re behind if you’re not constantly replatforming your brain.
Even if the end-state is “engineers code less”, the near-term reality for most engineers is still: deliver software, support customers, handle incidents, and now also become competent evaluators of rapidly changing bot stacks. That cognitive tax is brutal.
So yes, follow where the ball is going. I am. I’m just not pretending the current proliferation is anything other than noisy and expensive to keep up with.
Huh, the checkpoint primitive is something that I've been thinking about for a while, excited to see how it's implemented in the CLI. Git-compatible structures seem to be a pretty big pull whenever they're talking about context management.
This guy was the ex-ceo of GitHub and can't bother to communicate his product in a single announcement post?
I saw him speak at a conference a couple of years ago. He couldn't communicate back then either, so at least he's consistent.
I am here. What did I not bother with? I wrote the blog post and it has all the details.
Hey, is JJ compatibility in the cards? Considering the blog article hints at a goal of a developerless agent-to-agent automation platform I'm guessing developer conveniences are a side quest rn?
Yes, definitely something we are thinking of.
I am struggling to see what the details are other than high-level concepts. Perhaps a demo would be useful!
Wow, account from 2011 and just two comments, both on this article. Welcome, lurker, and good luck :)
Thanks. New startup, new approach.
He got fired for a reason lol.
I don't understand how this is different from giving an agent access to github logs? The landing page is terrible at explaining what it does.I guess they are just storing context in git aswell?
So is this just a few context.md files that you tell the agent to update as you work and then push it when you are done???
I’m team Geoffrey Huntley
This is a good idea but I feel like you could get something similar by just adding an instruction for the agent to summarize the context for the commit into a .context/commit/<sha> file as a git hook.
Or git notes.
Commit hook > Background agent summarizes (in a data structure) the work that went into the commit > saves to a note
Built similar (with a better name) a week ago at a hackathon: https://github.com/eqtylab/y
Exactly. I don't want to wade through a whole session log just to get to reasoning, and more importantly, I don't want to taint my current agent context with a bunch of old context.
Context management is still an important human skill in working with an agent, and this makes it harder.
I shall give the benefit of a doubt given they are "building in the open". I feel my current setup already does all this though, so I struggle to see the point
It’s funny. The whole “review intent", "learning" from past mistakes, etc, is exactly what my current set up does too. For free. Using .md files said agents generate as they go.
"$60M Seed round"
I guess when you are Ex-Github CEO, it is that easy raising a $60M seed. I wonder what the record for a seed round is. This is crazy.
I had a similar, admitted poorly thought out idea a few months back.
I wanted to more or less build Jira for agents and track the context there.
If I had to guess 60 million is just enough to build the POC out. I don't see how this can compete though, Open AI or Anthro could easily spin up a competitor internally.
Isn't that basically what things like this are for, open source, free.... https://github.com/steveyegge/beads
Shouldn't this tool be agnostic to the models? Seems like a 3rd party is the way to go.
Shoulda launched a new chat protocol to replace discord.
I miss the good old days:
Checkpoints sounds like an interesting idea, and one I think we'll benefit from if they can make it useful.
I tried a similar(-ish) thing last year at https://github.com/imjasonh/cnotes (a Claude hook to write conversations to git notes) but ended up not getting much out of it. Making it integrated into the experience would have helped, I had a chrome extension to display it in the GitHub UI but even then just stopped using it eventually.
Ah you were 7mo ahead of me doing the same and also coming to a similar conclusion. The idea holds value but in practice it isnt felt.
The founder has only forked repositories on GitHub that are sort of light web development related.
His use of bombastic language in this announcement suggests that he has never personally worked on serious software. The deterioration of GitHub under his tenure is not confidence inspiring either, but that of course may have been dictated by Nadella.
If you are very generous, this is just another GitHub competitor dressed up in AI B.S. in order to get funding.
This comment is both wrong and mean-spirited.
I’ve worked with ashtom for over a decade. He’s a coding machine - easily one of the most technical executives (who ships real production code.)
Founder here. I built commercial insurance software for Windows 95 in the 1990s, driver assistant systems at Mercedes and at Bosch in the early 2000s, dozens of iPhone apps as contractor, a startup called HockeyApp (acquired by Microsoft), and various smaller projects, mostly in Ruby on Rails. And of course, when I left Microsoft & GitHub, 10 years of green boxes were removed from my GitHub profile.
But ... what have you done lately?
(I jest ... kudos).
Ironically, I was shortly contracting on PoC similar to this for ex github cofunder around this time last year.
I built a skill for this: https://github.com/doubleuuser/rlm-workflow
The readme is a bit more to the point.
disclosure: i run a startup that will most likely be competitive in the future.
I welcome more innovation in the code forge space but if you’re looking for an oss alternative just for tracking agent sessions with your commits you should checkout agentblame
Oh I don't think I need this if all of my commits are AI!
Entire CEO here. We are going to be building in the open and full stack open source, but great to see alternatives.
Another of your competitors here. It makes me giggle that we're going after the entire developer experience while Entire is only looking at a small corner of it.
Time will tell how small that corner is. ;)
Certainly! But just to confirm, you aren't making an IDE or building a version control system to replace Git, are you? While money means you need not fear me, the scale of my vision means that I don't fear you either.
Did you have to choose an adjective to name your product. Now it’s going to be very confusing for search engines and LLms. “Tell me more about entire.” “Entire what?” “You know, that entire thing.”
I see the vision here. I think this is extremely needed.
There is also Git AI: https://github.com/git-ai-project/git-ai https://usegitai.com/
love the shout but git-ai is decidedly not trying to replace the SCMs. there are teams building code review tools (commercial and internal) on top of the standard and I don't think it'll be long before GitHub, GitLab and the usual suspects start supporting it since folks the community have already been hacking it into Chrome extensions - this one got play on HN last week https://news.ycombinator.com/item?id=46871473
yep i know it's not meant to be an SCM tool but I thought it was somewhat related to what they're doing right now:
"Entire CLI hooks into your git workflow to capture AI agent sessions on every push."
Which is capturing the LLM convo along with the code (I could be wrong ofc)
My first thought that it was made for companies which tie "AI usage" to performance evaluation.
This feels a bit like when some Hubbers broke off to work on PlanetScale, except without the massively successful, proven-to-be-scalable open source tool to build off (Vitess).
If you're approaching this problem-space from the ground up, there are just so many fundamental problems to solve that it seems to me that no amount of money or quality of team can increase your likelihood of arriving at enough right answers to ensure success. Pulling off something like this vision in the current red-ocean market would require dozens of brilliant ideas and hundreds of correct bets.
Think of all of the habit tracker and to do list apps we'll be able to make now!
With openclaw we won't need to make event those apps.
Essentially all software is augmented with agentic development now, or if not, built with technology or on platforms that is
It's like complaining about the availability of the printing press because it proliferated tabloid production, while preferring beautifully hand-crafted tomes. It's reactively trendy to hate on it because of the vulgar production it enables and to elevate the artisanal extremes that escape its apparent influence
What part of Voyager I and Voyager II are "augmented with agentic development?"
Surely if all software is augmented with agentic development now, our most important space probes have had their software augmented too, right?
What about my blog that I serve static pages on? What about the xray machine my dentist uses? What about the firmware in my toaster? Does the New York Stock Exchange use AI to action stock trades? What about my telescope's ACSOM driver?
You’re talking about a 1970s satellite? I guess you win the argument?
Blog: I use AI to make and blog developers are using agentic tools
X-ray machine: again a little late here, plus if you want to start dragging in places that likely have a huge amount of beaurocracy I don’t know that that’s very fair
Firmware in your toaster: cmon these are old basic things, if it’s new firmware maybe? But probably not? These are not strong examples
NYSE to action on stock trades; no they don’t use AI to action on stock trades (that would be dumb and slow and horribly inefficient and non-deterministic), but may very well now be using AI to work on the codebase that does
Let’s try to find maybe more impactful examples than small embodied components in toasters and telescopes, 1970s era telescopes that are already past our solar system.
The denial runs deep
So you admit that AI isn't in every software, and yet somehow I'm the one in denial?
Im saying you’re missing the point and the spirit of the argument. Yes, you are right, voyager doesn’t use agentic AI! I don’t even think the other examples you used are as agentic free as you think. They may or may not be! What’s the point you want to make?
Huh? Software under development obviously not software made before these tools existed
It's really not as integral as you make it sound. If I make one PR on a widely used open source tool with a small fix, is most software development augmented by me?
Outside of simply not being true, the sentiment of what you're saying isn't much different than:
"Essentially all software is augmented with Stack Overflow now, or if not, built with technology or on platforms that is."
Agentic development isn't a panacea nor as widespread as you claim. I'd wager that the vast majority of developers treat AI is a more specified search engine to point them in the direction they're looking for.
AI hallucination is still as massive problem. Can't tell you the number of times I've used agentic prompting with a top model that writes code for a package based on the wrong version number or flat out invents functionality that doesn't exist.
I just cannot fathom how people can say something like this today, agentic tools have now passed an inflection point. People want to point out the short comings and fully ignore that you can now make a fully functioning iPhone app in a day without knowing swift or front end development? That I can at my company do two projects simultaneously, both of them done in about 1/4 the time and one would not have even been attempted before due to the SWE headcount you would have to steal. There are countless examples I have in my own personal projects that just are such an obvious counter example to the moaning “I appreciate the craft” people or “yea this will never work because people still have to read the code” (today sure and this is now made more manageable by good quality agents, tomorrow no. No you won’t need to read code.)
I've found that the effort required to get a good outcome is roughly equal to the effort of doing it myself.
If I do it myself, I get the added bonus of actually understanding what the code is doing, which makes debugging any issues down the line way easier. It's also in generally better for teams b/c you can ask the 'owner' of a part of the codebase what their intuition is on an issue (trying to have AI fill in for this purpose has been underwhelming for me so far).
Trying to maintain a vibecoded codebase essentially involves spelunking though a non-familliar codebase every time manual action is needed to fix an issue (including reviewing/verifying the output of an AI tool's fix for the issue).
(For small/pinpointed things, it has been very good. e.g.: write a python script to comb through this CSV and print x details about it/turn this into a dashboard)
In sonnet 4 and even 4.5 I would have said you are absolutely right, and in many cases it slows you down especially when you don’t know enough to sniff trouble.
Opus 4.5 and 4.6 is where those instances have gone down, waaay down (though still true). Two personal projects I had abandoned after sonnet built a large pile of semi working cruft it couldn’t quite reason about, opus 4.6 does it in almost one shot.
You are right about learning but consider: you can educate yourself along the way — in some cases it’s no substitute for writing the code yourself, and in many cases you learn a ton more because it’s an excellent teacher and you can try out ideas to see which work best or get feedback on them. I feel I have learned a TON about the space though unlike when I code it myself I may not be extremely comfortable with the details. I would argue we are about 30% of the way to the point where it’s not even no longer relevant it’s a disservice to your company to be writing things yourself.
I didn’t say essentially all software is vibe coded. You already agree with me that it’s very good at some range of common tasks.
There are other things very good "at some range of common tasks". For example, stackoverflow snippets, libraries, bash spaghetti and even some no-code/low-code tools.
Sorry for not contributing to the discussion (as per the guidelines), but is it just me or this blog post reads a lot like LLM-filled mumble jumble? Seems like I could trim half of the words there and nothing would be lost.
What's the long-term or even short-term strategy to make money?
It's not like $60m in funding was given as charity.
General purpose agentic AI for enterprises since apparently that's the hot shit for 2026 now.
Just have a data lake with annotated agent sessions and tool blobs (you should already be keeping this stuff for evals), then give your agent the ability to query it. No need for a special platform, or SaaS.
As for SDLC, you can do some good automations if you're very opinionated, but people have diverse tastes in the way they want to work, so it becomes a market selection thing.
This is the way
Really hope that unlike GitHub it'll be open source
With a 60M seed? I doubt it.
I bet it will down/unstable 3/4 of the month.
Highly dubious of this.
I see zero reason for a person to care about the checkpoints.
And for agents, full sessions just needlessly fill context.
So not sure what is being solved by this.
I’m manually checking in Agent.md for every commit to improve the context window usage. Is that now automated?
you're doing what now?
Entire.io, the name is on point considering it asks for access to my entire GitHub account.
But seriously, $300M valuation for a CLI tool that adds some metadata to Git commits. I don't know what to say.
Its a shame Pierre shut down. Wish they could have made it work. Github but made by Linear would be a dream.
Pierre didn't shutdown, they said they just paused signups on the code review app to focus on the code storage service.
Productizing the building blocks of the platform seems like the smart play in today's environment honestly.
Sure but I dont want to build my own Github I just want to use a beautiful and faster alternative
We’re shooting for this with Tangled (https://tangled.org). :)
I'm interested to see if they will try to tackle the segregation of human vs AI code. The downside of agents is that they make too much changes to review, I prefer being able to track which changes I wrote or validated from the code the AI wrote.
For people trying to understand the product (so far), it seems that entire is essentially an implementation of the idea documented by http://agent-trace.dev.
> Cursor's Composer 2.0
There is no Composer 2.0. There is Cursor 2.0 and Composer 1.5.
There have been so many GitHub CEOs I was excited to find out which one.
Only four: Chris, Tom, Nat, and Thomas. Last one is me. ;)
PJ was technically CEO for awhile when they needed someone to do it
Can someone please explain what is this?
I am already overloaded with information (generated by AI and humans) on my day to day job, why do I need this additional context, unless company I work for just wants to spend more money to store more slop?
How is it different than reversing it, given a PR -> generate prompt based on business context relevant to the repo or mentioned issues -> preserve it as part of PR description
I barely look at git commit history, why should I look for even higher cardinality data, in this case: WTF, are you doing, idiot, I said don't change the logic to make tests pass, I said properly write tests!
Yay, MORE 'AI' agents! Hint: There are already too many Artificial Indians!
New agent framework / platform every week now. It's crazy how fast things move...just when you get comfortable with an AI flow something new comes out...
The lack of explanation of what it is and does is a tell of what gullible audience they are seeking.
Tech marketing has become a lot like dating, no technical explanation and intellectual honesty, just word words words and unreasonable expectations.
People usually cannot be honest in their romantic affairs, and here it is the same. Nobody can state: we just want to be between you and whatever you want to accomplish, rent seeking forever!
Will they ever care to elaborate HOW things works and the rationale behind stating this provides any benefit whatsoever? Perhaps this is not intended for those type of humans that care about understanding and logic?
> ... to Cursor's Composer 2.0 and more, ...
I couldn't find any references of Composer 2.0 anywhere. When did that come out?
1.5 released yesterday. probably just slop
Fixed. It's Cursor 2.0 and Composer 1.5, mixed that up when editing the post last night.
I don't see how we need a brand new paradigm just because LLMs evidently suck at sharing context in their Git commits. The rules for good commits still apply in The New Age. Git is still good enough, LLMs (i.e. their developer handlers) just need to leverage it.
Personally, I don't let LLMs commit directly. I git add -p and write my own commit messages -- with additional context where required -- because at the end of the day, I'm responsible for the code. If something's unclear or lacks context, it's my fault, not the robot's.
But I would like to see a better GitHub, so maybe they will end up there.
Wait, since when is Dohmke out? I thought this was gonna be Nat.
I left August 11: https://github.blog/news-insights/company-news/goodbye-githu...
Not sure what it is or what it does.
Uses AI to summarize coding sessions tied to commits.
Commit hook > Background agent summarizes (in a data structure) the work that went into the commit.
Built similar (with a better name) a week ago at a hackathon: https://github.com/eqtylab/y
Which only reinforces someone just lit $60M on fire. It's trivial to do this and there are so many ways people do things, having the AI build custom for you is better than paying some VC funded platform to build something for the average
Not even pocket change compared to the billions of VC money burnt every month to keep the show running.
It extracts money from investors and allocates it to founders.
$300kk valuation for git commits :) the bubble will pop at some point, I don’t know when, but boy will it be spectacular.
Which CEO?
$60M seed to wrap git hooks in YAML config. The AI tooling bubble is just VCs subsidizing solutions looking for problems while developers want less complexity, not more.
Clicks through to see what Tom or Chris started…
Oh, nevermind, it’s some MS dude.
I don't want agent context tied to git commits. I just want infinite scroll in Claude Code and ability to search and review all my past conversations!
Looking at the CLI implementation. Why not build on top of jj?
most people use git, jj has compatibility gaps
I did test it and use it and trashed it because there is very little value, actually none for me. These problems are easily being solved in other ways whoever has any experience with these tools. Getting $60M round for this stuff is ridiculous.
Sounds very cringe
Not surprising for a $60M seed round
Do we have new words for smaller amounts or is this inflation at work?
so github ci/cd agents rebranded as a startup? same team different company.
I really hate this trend of naming companies using dictionary words just because they can afford to spend cash on the domain name instead of engineering. Render, fly, modal, entire and so on.
Grifters to the grift god
Really struggling to figure out what this is at a glance. Buried in the text is this line which I think is the tl;dr:
"As a result, every change can now be traced back not only to a diff, but to the reasoning that produced it."
This is a good idea, but I just don't see how you build an entire platform around this. This feels like a feature that should be added to GitHub. Something to see in the existing PR workflow. Why do I want to go to a separate developer platform to look at this information?
I'm sure i'm missing something but can you not ask the llm to add the reasoning behind the commit in the comments as part of the general llm instructions?
Github sucks now, for one; people are looking for an alternative.
This is not an alternative to GitHub though. The code for this tool itself lives on GitHub!
List of Github CEOs:
1. Tom Preston-Werner (Co-founder). 2008 – 2014 (Out for, eh... look it up)
2. Chris Wanstrath (Co-founder). 2014 – 2018
(2018: Acquisition by Microsoft: https://news.ycombinator.com/item?id=17227286)
3. Nat Friedman (Gnome/Ximian/Microsoft). 2018 – 2021
4. Thomas Dohmke (Founder of HockeyApp, some A/B testing thing, acquired by Microsoft in 2014). 2021 - 2025
There is no Github CEO now, it's just a team/org in Microsoft. (https://mrshu.github.io/github-statuses/)
Chris was also CEO from 2008 to 2012. Tom had 2012 to 2014.
Nat's company Xamarin was acquired by Microsoft in 2016.
HockeyApp wasn't A/B testing, but a platform for iPhone, Mac, Android, and Windows Phone developers to distribute their beta version (like what TestFlight is today to the App Store), collect crash reports (like what Sentry is today), user feedback, and basic analytics for developers.
Thanks for the fact check :).
The Ximian thing I wrote from obviously faulty memory (I now wonder if it was influenced by early 2000s Miguel's bonobo obsession), the rest from various google searches. Should have gone deeper.
No, I was actually sort of correct.
https://en.wikipedia.org/wiki/Ximian
Ximian, Inc. (previously called Helix Code and originally named International Gnome Support) was an American company that developed, sold and supported application software for Linux and Unix based on the GNOME platform. It was founded by Miguel de Icaza and Nat Friedman in 1999 and was bought by Novell in 2003
...
Novell was in turn acquired by The Attachmate Group on 27 April 2011. In May 2011 The Attachmate Group laid off all its US staff working on Mono, which included De Icaza. He and Friedman then founded Xamarin on 16 May 2011, a new company to continue the development of Mono. On 24 February 2016, Microsoft announced that they had signed an agreement to acquire Xamarin.
Oh man I'm tired. This reminds me of the docker era. It's all moving fast. Everyone's raising money. And 24 months from now it's all consolidating. It's all a nice hype game when you raise the funding but the execution depends on people finding value in your products and tools. I would argue yes many of these things are useful but I'd also argue there's far too much overlap, too many unknowns and too many people trying to reinvent the whole process. And just like the container era I think we're going to see a real race to zero. Where most of the dev tools get open sourced and only a handful of product companies survive, if that. I want to wish everyone the best of luck because I myself have raised money and spent countless years building Dev tools. This is no easy task especially as the landscape is changing. I just think when you raise $60m and announce a cli. You're already dead, you just don't know it. I'm sorry.
Let the cambrian explosion run its course but let's hope the meteorite doesn't kill us all.
I see the value since I built a similar tool different approach. Then there's Beads, which is what inspired my project, with some tens of thousands of developers using it or more now? I'm not sure how they figure how many users they have.
In my case I don't want my tools to assume git, my tools should work whether I open SVN, TFS, Git, or a zip file. It should also sync back into my 'human' tooling, which is what I do currently. Still working on it, but its also free, just like Beads.
I wouldn't wanna be in the rat race myself, but I know people who salivate at the opportunity to create some popular dev tool to get acquired by MS, Google or Amazon or whichever of the big tech companies that decide this could work well in their cloud ecosystem.
HNites are hilarious.
On the one hand they think these things provide 1337x productivity gains, can be run autonomously, and will one day lead to "the first 1 person billion dollar company".
And in complete cognitive dissonance also somehow still have fantasies of future 'acquisition' by their oppressors.
Why acquire your trash dev tool?
They'll just have the agents copy it. Hell, you could even outright steal it, because apparently laundering any licensing issues through LLMs short circuits the brains of judges to protohuman clacking rocks together levels.
What if it's just the beginning of something bigger?
What if the earth exploded tomorrow? Who cares about what if.
With 60 million you could have waited for a bigger announcement? There's "AI fatigue" among the target market for these sorts of tools, advertising unfinished products will take its toll on you later.
I thought something got seriously wrong with Nat Friedman but fortunately it's another one.