Serena is great for semantic code editing and symbol-level retrieval on your own codebase. It gives the agent IDE-like capabilities inside the repo. Nia focuses on a different layer. We target external context: remote code, docs, packages, APIs, research, enterprise knowledge, etc
w nia the agent can dynamically search, traverse, and validate information outside the local project so it never hallucinates against out-of-date or incomplete sources.
This looks neat, we certainly need more ideas and solutions on this space, I work with large codebases daily and the limits on agentic contexts are constantly evident.
I've some questions related to how I would consume a tool like this one:
How does this fare with codebases that change very frequently? I presume background agents re-indexing changes must become a bottleneck at some point for large or very active teams.
If I'm working on a large set of changes modifying lots of files, moving definitions around, etc., meaning I've deviated locally quite a bit from the most up to date index, will Nia be able to reconcile what I'm trying to do locally vs the index, despite my local changes looking quite different from the upstream?
For large and active codebases, we avoid full reindexing. Nia tracks diffs and file level changes, so background workers only reindex what actually changed. We are also building “inline agents” that watch pull requests or recent commits and proactively update the index ahead of your agent queries.
Local vs upstream divergence is a real scenario. Today Nia prioritizes providing external context to your coding agents: packages, provider docs, SDK versions, internal wikis, etc. We can still reconcile with your local code if you point the agent at your local workspace (cursor and claude code already provide that path). We look at file paths, symbol names and usage references to map local edits to known context. In cases where the delta is large, we surface both the local version and the latest indexed version so the agent understands what changed.
Congrats on the launch. The problem is definitely there. I wonder how are you planning to differentiate yourself from Cursor and the like. You mention you are complementary, but Cursor provide similar features to add external doc context for instance to a prompt. I understand you do better in your benchmark, but with the amount of funding they may be able to replicate and improve over it (unless you have a secret thing).
as I mentioned above there are many more use cases than just coding (APIs, research, knowledge bases, even personal or enterprise data sources the agent needs to explore and validate dynamically)
I started out with coding agents specifically because it came from personal pain of how horrible they are with providing up to date context.
The goal here is not to replace Cursor’s own local codebase indexing. Cursor already does that part well. What Nia focuses on is external context. It lets agents pull in accurate information from remote sources like docs, packages, APIs, and broader knowledge bases
That’s what GP is saying. This is the Docs feature of Cursor. It covers external docs/arbitrary web content.
`@Docs` — will show a bunch of pre-indexed Docs, and you can add whatever you want and it’ll show up in the list. You can see the state of Docs indexing in Cursor Settings.
The UX leaves a bit to be desired, but that’s a problem Cursor seems to have in general.
yeah ux is pretty bad and overall functionality. it still relies on a static retrieval layer and limited index scope.
+ as I mentioned above there are many more use cases than just coding.Think docs, APIs, research, knowledge bases, even personal or enterprise data sources the agent needs to explore and validate dynamically.
As an AI user (claude code, rovo, github copilot) I have come across this. In code it didnt build something right where it needed to use up to date docs. Luckily those people have now made an MCP but I had to wait. For a different project I may be SOL. Suprised this isnt solved, well done for taking it on.
From a business point of view I am not sure how you get traction without being 10x better than what Cursor can produce tomorrow. If you are successful the coding agents will copy your idea and then people being lazy and using what works have no inventive to switch.
I am not trying to discourage. More like encourage you to figure out how you get that elusive moat that all startups seek.
As a user I am excited to try it soon. Got something in mind that this should make easier.
This is different because of the background refresh, the identifier extraction and the graph. I know because I use cursor and am building the exact same thing oddly enough.
The context problem with coding agents is real. We've been coordinating multiple agents on builds - they often re-scan the same files or miss cross-file dependencies. Interested in how Nia handles this - knowledge graph or smarter caching?
I've no idea what their architecture/implementation looks like, but I've built a similar tool for my own use and the improvements are dramatic to say the least.
Mine's a simple BM25 index for code keyword search (I use it alongside serena-mcp) and for some use cases the speeds and token efficiency are insane.
It's amazing that you can do this on your own but the company in question cannot although they have raised $6M. If your README were their entire pitch and website and, it would be 100000x more convincing.
Having this RAG layer was always another thing to try for me. I haven't coded it myself, and super interested if this gives a real boost while working with Claude. Curious from anyone who have already tried the service, what's your feedback? Did you feel you're getting real improvements?
Wouldn’t call it just RAG though. Agentic discovery and semantic search are the way to go right now, so Nia combines both approaches. For example, you can dynamically search through a documentation tree or grep for specific things.
Arlan had this in his text but I cut it for brevity - sorry about that! Here's the bit:
In our internal benchmark on bleeding edge SDK and library features, Nia produced the lowest hallucination rate among the context providers and search tools we tested (context7, exa code, etc), and I wrote up the setup and results in a separate blog post: https://www.nozomio.com/blog/nia-oracle-benchmark
Please make your substantive points without being snarky or aggressive. You have a good point in there at the end, but the site guidelines ask you not to comment like this, and that's especially important in Show or Launch threads.
Ok here is my less snarky and less aggressive take on the site and product: it doesn't leave me with confidence, it makes me feel uneasy about them as a company, it makes me not trust them, and it makes me feel like I'm being lied to. To fix this, provide proof. Otherwise, stop making the claims. Unfortunately with the frequency these kinds of products come out of YC, it seems like maybe YC coaches these companies as if this is an effective way to communicate.
i am interested in knowing what would be the correct way to do it according to your checklist. For example you said testimonial from twitter can be bots, which testimonial according to you would give you confidence that product is genuine?
Not exactly just RAG. The shift is agentic discovery paired with semantic search.
Also, most of the coding agents still combine RAG and agentic search. See cursor blog about how semantic search helps them understand and navigate massive codebases: https://cursor.com/blog/semsearch
This is happening over and over and over. The example of prompt engineering is just a form of protocol. Context engineering is just about cache management. People think LLMs will replace programming languages and runtimes entirely, but so far it seems they have been used mostly to write programs in programming languages, and I've found they're very bad interpreters and compilers. So far, I can't really pick out what exactly LLMs are replacing except the need to press the individual keys on the keyboard, so I still struggle to see them as more than super fancy autocomplete. When the hype is peeled away, we're still left with all the same engineering problems but now we have added "Sometimes the tool hallucinates and gaslights you".
How does it compare to Serena MCP? :)
https://github.com/oraios/serena
Serena is great for semantic code editing and symbol-level retrieval on your own codebase. It gives the agent IDE-like capabilities inside the repo. Nia focuses on a different layer. We target external context: remote code, docs, packages, APIs, research, enterprise knowledge, etc
w nia the agent can dynamically search, traverse, and validate information outside the local project so it never hallucinates against out-of-date or incomplete sources.
This looks neat, we certainly need more ideas and solutions on this space, I work with large codebases daily and the limits on agentic contexts are constantly evident. I've some questions related to how I would consume a tool like this one:
How does this fare with codebases that change very frequently? I presume background agents re-indexing changes must become a bottleneck at some point for large or very active teams.
If I'm working on a large set of changes modifying lots of files, moving definitions around, etc., meaning I've deviated locally quite a bit from the most up to date index, will Nia be able to reconcile what I'm trying to do locally vs the index, despite my local changes looking quite different from the upstream?
great question!
For large and active codebases, we avoid full reindexing. Nia tracks diffs and file level changes, so background workers only reindex what actually changed. We are also building “inline agents” that watch pull requests or recent commits and proactively update the index ahead of your agent queries.
Local vs upstream divergence is a real scenario. Today Nia prioritizes providing external context to your coding agents: packages, provider docs, SDK versions, internal wikis, etc. We can still reconcile with your local code if you point the agent at your local workspace (cursor and claude code already provide that path). We look at file paths, symbol names and usage references to map local edits to known context. In cases where the delta is large, we surface both the local version and the latest indexed version so the agent understands what changed.
Congrats on the launch. The problem is definitely there. I wonder how are you planning to differentiate yourself from Cursor and the like. You mention you are complementary, but Cursor provide similar features to add external doc context for instance to a prompt. I understand you do better in your benchmark, but with the amount of funding they may be able to replicate and improve over it (unless you have a secret thing).
as I mentioned above there are many more use cases than just coding (APIs, research, knowledge bases, even personal or enterprise data sources the agent needs to explore and validate dynamically)
I started out with coding agents specifically because it came from personal pain of how horrible they are with providing up to date context.
This looks interesting and worthwhile. I did a double-take when I read "when (a few months ago) I was still in high school in Kazakhstan"
Congrats. From my experience, Augment (https://augmentcode.com) is best in class for AI code context. How does this compare?
augment is a coding agent. nia is an external context engine for coding agents that improves their code output quality
Cursor promises to do this[0] in the product, so, especially on HN, it'd be best to start with "why this is better than Cursor".
> favorite doc sites so I do not have to paste URLs into Cursor
This is especially confusing, because cursor has a feature for docs you want to scrape regularly.
0 - https://cursor.com/docs/context/codebase-indexing
The goal here is not to replace Cursor’s own local codebase indexing. Cursor already does that part well. What Nia focuses on is external context. It lets agents pull in accurate information from remote sources like docs, packages, APIs, and broader knowledge bases
That’s what GP is saying. This is the Docs feature of Cursor. It covers external docs/arbitrary web content.
`@Docs` — will show a bunch of pre-indexed Docs, and you can add whatever you want and it’ll show up in the list. You can see the state of Docs indexing in Cursor Settings.
The UX leaves a bit to be desired, but that’s a problem Cursor seems to have in general.
yeah ux is pretty bad and overall functionality. it still relies on a static retrieval layer and limited index scope.
+ as I mentioned above there are many more use cases than just coding.Think docs, APIs, research, knowledge bases, even personal or enterprise data sources the agent needs to explore and validate dynamically.
As an AI user (claude code, rovo, github copilot) I have come across this. In code it didnt build something right where it needed to use up to date docs. Luckily those people have now made an MCP but I had to wait. For a different project I may be SOL. Suprised this isnt solved, well done for taking it on.
From a business point of view I am not sure how you get traction without being 10x better than what Cursor can produce tomorrow. If you are successful the coding agents will copy your idea and then people being lazy and using what works have no inventive to switch.
I am not trying to discourage. More like encourage you to figure out how you get that elusive moat that all startups seek.
As a user I am excited to try it soon. Got something in mind that this should make easier.
thanks! will be waiting for ur feedback
This is different because of the background refresh, the identifier extraction and the graph. I know because I use cursor and am building the exact same thing oddly enough.
The context problem with coding agents is real. We've been coordinating multiple agents on builds - they often re-scan the same files or miss cross-file dependencies. Interested in how Nia handles this - knowledge graph or smarter caching?
hey! knowledge graphs are also used at runtime but paired with other techniques, since graphs are only useful for relationship queries.
I've no idea what their architecture/implementation looks like, but I've built a similar tool for my own use and the improvements are dramatic to say the least.
Mine's a simple BM25 index for code keyword search (I use it alongside serena-mcp) and for some use cases the speeds and token efficiency are insane.
https://gitlab.com/rhobimd-oss/shebe#comparison-shebe-vs-alt...
looks cool, what's the largest codebase you have tested it on?
OpenEmr and Istio. https://gitlab.com/rhobimd-oss/shebe/-/blob/main/docs/Perfor...
It's amazing that you can do this on your own but the company in question cannot although they have raised $6M. If your README were their entire pitch and website and, it would be 100000x more convincing.
(I detached this subthread from https://news.ycombinator.com/item?id=46195560 because your comment is fine and I don't want it to be penalized.)
Thanks @dang
Having this RAG layer was always another thing to try for me. I haven't coded it myself, and super interested if this gives a real boost while working with Claude. Curious from anyone who have already tried the service, what's your feedback? Did you feel you're getting real improvements?
Wouldn’t call it just RAG though. Agentic discovery and semantic search are the way to go right now, so Nia combines both approaches. For example, you can dynamically search through a documentation tree or grep for specific things.
We call it agentic RAG. The retriever is an agent. It’s still RAG
Which would be much better than the techniques used in 2023. As context windows increase, combining them becomes even easier.
There are a lot of ways of how you can interpret agentic rag, pure rag, etc
Is the RAG database on your servers or is it local? If not local is there a local option?
hey! i use multiple DBs but the primary ones are turbopuffer and chroma for package search. they are really great
re local, I do local for certain companies!
Congrats on the launch, Nia looks great.
congrats on the launch Arlan! Nia is a lifesaver when we're coding :)
Congrats on the launch! Definitely a problem I’ve run into myself.
Benchmarks?
https://www.nozomio.com/blog/nia-oracle-benchmark
Arlan had this in his text but I cut it for brevity - sorry about that! Here's the bit:
In our internal benchmark on bleeding edge SDK and library features, Nia produced the lowest hallucination rate among the context providers and search tools we tested (context7, exa code, etc), and I wrote up the setup and results in a separate blog post: https://www.nozomio.com/blog/nia-oracle-benchmark
[flagged]
Please make your substantive points without being snarky or aggressive. You have a good point in there at the end, but the site guidelines ask you not to comment like this, and that's especially important in Show or Launch threads.
https://news.ycombinator.com/newsguidelines.html
Ok here is my less snarky and less aggressive take on the site and product: it doesn't leave me with confidence, it makes me feel uneasy about them as a company, it makes me not trust them, and it makes me feel like I'm being lied to. To fix this, provide proof. Otherwise, stop making the claims. Unfortunately with the frequency these kinds of products come out of YC, it seems like maybe YC coaches these companies as if this is an effective way to communicate.
i am interested in knowing what would be the correct way to do it according to your checklist. For example you said testimonial from twitter can be bots, which testimonial according to you would give you confidence that product is genuine?
Absolutely insane that we celebrated coding agents getting rid of RAG, only with the next innovation being RAG
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."
"Don't be snarky."
https://news.ycombinator.com/newsguidelines.html
Not exactly just RAG. The shift is agentic discovery paired with semantic search.
Also, most of the coding agents still combine RAG and agentic search. See cursor blog about how semantic search helps them understand and navigate massive codebases: https://cursor.com/blog/semsearch
The pendulum swings back.
This is happening over and over and over. The example of prompt engineering is just a form of protocol. Context engineering is just about cache management. People think LLMs will replace programming languages and runtimes entirely, but so far it seems they have been used mostly to write programs in programming languages, and I've found they're very bad interpreters and compilers. So far, I can't really pick out what exactly LLMs are replacing except the need to press the individual keys on the keyboard, so I still struggle to see them as more than super fancy autocomplete. When the hype is peeled away, we're still left with all the same engineering problems but now we have added "Sometimes the tool hallucinates and gaslights you".
[under-the-rug stub]
[see https://news.ycombinator.com/item?id=45988611 for explanation]
super smart. congrats on the launch!
I love Nia, keep it up Arlan
thank you haha!
Love it.