[HN Gopher] Deep Agents
       ___________________________________________________________________
        
       Deep Agents
        
       Author : saikatsg
       Score  : 75 points
       Date   : 2025-08-01 19:28 UTC (3 hours ago)
        
 (HTM) web link (blog.langchain.com)
 (TXT) w3m dump (blog.langchain.com)
        
       | seabass wrote:
       | Is there more info on how the todo list tool is a noop? How
       | exactly does that work?
        
         | JyB wrote:
         | Same question. I don't understand what they mean by that. It
         | obviously seem pretty central to how Claude Code is so
         | effective.
        
           | kjhughes wrote:
           | I thought they meant that it's a noop as a tool in the sense
           | that it takes no external action. It seems nonetheless
           | effective as a means of organizing reasoning and expressing
           | status along the way.
        
             | kobstrtr wrote:
             | just for chain of thought TodoWrite would be sufficient as
             | a tool wouldn't it?
        
         | kobstrtr wrote:
         | if it was a noop, I feel like there wouldn't be a need to have
         | TodoRead as a tool, since TodoWrite exists. Would love to get
         | more info on whether this is really a noop
        
           | aabhay wrote:
           | My guess is the todo list is carried across "compress" points
           | where the agent summarizes and restarts with fresh context +
           | the summary
        
         | ttul wrote:
         | The context will contain a record that the tool call took
         | place. The todo list is never actually fetched.
        
         | crawshaw wrote:
         | If you want to see it in action in some code, our agent Sketch
         | uses a TODO list tool:
         | https://github.com/boldsoftware/sketch/blob/main/claudetool/...
         | 
         | It is relatively easy to get the agent to use it, most of the
         | work for us is surfacing it in the UI.
        
         | TrainedMonkey wrote:
         | My understanding is that it is basically a prompt about making
         | a TODO list.
        
         | lmeyerov wrote:
         | i think he means it's 'just' a thin concat
         | 
         | most useful prompt stuff seems 'simple' to implement
         | ultimately, so it's more impressive to me that such a simple
         | idea of TODO goes so far!
         | 
         | (agent frameworks ARE hard in serious settings, don't get me
         | wrong, just for other reasons. ex: getting the right mix &
         | setup devilishly hard, as are infra layers below like
         | multitenacy, multithreading, streaming, cancellation, etc.)
         | 
         | re: the TODO list, strong agree on criticality. it's flipped
         | how we do louie.ai for stuff like speed running security log
         | analysis competitions. super useful for preventing CoT from
         | going off the rails after only a few turns.
         | 
         | a fun 'aha' for me there: nested todo's are great (A.2.i...),
         | and easy for the LLM b/c they're linearized anyways
         | 
         | You can see how we replace claude code's for our own internal
         | vibe coding usage, which helps with claude's constant
         | compactions as a heavy user (= assuages issue of the ticking
         | timer for a lobotomy): https://github.com/graphistry/louie-
         | py/blob/main/ai/prompts/...
        
       | shmatt wrote:
       | At least from what I noticed - Junie from Jetbrains was the first
       | to use a very high quality to do list, and it quickly became my
       | favorite
       | 
       | I haven't used it since it became paid, but back then Junie was
       | slow and thoughtful, while Cursor was constantly re-writing files
       | that worked fine, and Claude was somewhere in the middle
        
         | tough wrote:
         | Cursor added a UI for todo list and encourages it's agent to
         | use it (its great ux, but you can't really see a file of it)
         | 
         | kiro from amazon does both tasks (in tasks.md) and specs.
         | 
         | Too many tools soon, choose what works for you
        
       | manishsharan wrote:
       | I have been following along the code in this repo.
       | https://github.com/ghuntley/claude-code-source-code-deobfusc...
       | 
       | The author has done a pretty good job of reverse engineering
       | Claude Code and explaining the architecture.
       | 
       | update: changed the link to a better repo
        
         | cjonas wrote:
         | Can you explain what I'm looking at. Just appears to be a
         | massive readme with a bunch of system instructions?
        
           | manishsharan wrote:
           | My apologies
           | 
           | This is a better repo to learn about Claude code internals
           | 
           | https://github.com/ghuntley/claude-code-source-code-
           | deobfusc...
        
       | jayshah5696 wrote:
       | sub agents adding isolating context is the real deal rest is just
       | langgraph react agent
        
         | PantaloonFlames wrote:
         | This is valuable but not really a novel idea.
        
       | manx wrote:
       | I'm also in the process of creating a general purpose agent
       | cli+library in rust: https://github.com/fdietze/alors
       | 
       | Still work in progress, but I'm already using it to code itself.
       | Feedback welcome.
        
       | _andrei_ wrote:
       | ah, deep agents = agents with planning + agents as tools => so
       | regular agents.
       | 
       | i hate how LangChain has always tried to make things that are
       | simple seem very complicated, and all the unnecessary new
       | terminology and concepts they've pushed, but whatever sells
       | LangSmith.
        
       | web-cowboy wrote:
       | As I think through this, I agree with others mentioning that
       | "deep agents" still sounds a lot like agents+tools. I guess the
       | takeaway for me is:
       | 
       | 1. You need a good LLM for base knowledge.
       | 
       | 2. You need a good system prompt to guide/focus the LLM (create
       | an agent).
       | 
       | 3. If you need some functionality that doesn't make any
       | decisions, create a tool.
       | 
       | 4. If the agent + tools flows get too wily, break it down into
       | smaller domains by spawning sub agents with focused prompts and
       | (less?) tools.
        
       | storus wrote:
       | "I hacked on an open source package (deepagents) over the
       | weekend." Thanks but no thanks.
        
         | yawnxyz wrote:
         | most of these agents are still fundamentally simple while
         | loops; it shouldn't really take longer than a weekend to get
         | one built
        
         | SCUSKU wrote:
         | Hacker hacks on project and gets posted to Hacker News.
         | Commenter on Hacker News: No thanks, no hacking please.
        
           | storus wrote:
           | It's on langchain's official page, a framework that looks
           | like it was hacked over the weekend by a fresh grad that
           | brought a lot of pain to the agentic development, and this
           | just feels like piling up more pain on it.
        
         | epolanski wrote:
         | Some of the biggest software in use today was hacked over few
         | days in its first versions. Git is a famous one.
        
       ___________________________________________________________________
       (page generated 2025-08-01 23:00 UTC)