co-founder @kapa_ai (yc s23) - a knowledge base for AI agents i also like to run very slowly on dirt

San Francisco, CA
Joined December 2010
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Replying to @dagger_io
Huge congrats on the launch!!! This is epic!!!
1
657
Emil retweeted
Announcing Dagger 1.0 beta. Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens. Featuring: test-native CI, dev shells, local and remote execution, official modules, and more. dagger.io/blog/dagger-10-bet…
55
88
36
974
198,319
Replying to @denniszha0 @cohere
sure! shoot me a ping on [email protected]
1
16
Replying to @xvarunxx
the team took @cohere's new reranker v5 on a run on our company knowledge evals (real-world messy data) it's cheap and fast! impressive jump from v4
1
1
1
57
the team took @cohere's new reranker v5 on a run on our company knowledge evals (real-world messy data) it's cheap and fast! impressive jump from v4
1
2
1
22
795
Replying to @xvarunxx
excited to take for a spin!!
1
1
44
rerank-3 go brrrrrrr
“Voyage wins on score, cost, and latency.” Don’t believe us? Check out the latest benchmark from @kapa_ai. Frontier models keep getting better, but they aren’t the whole stack. Agentic systems constantly make smaller decisions: what to retrieve, where to route a query, and which results matter. Specialized models are often better suited to that work. Jev, @typesafeai’s general-purpose decision model, is a great example. Give it context, a question, and a set of labels, and it returns a probability for each label, allowing you to steer it with a rubric for routing, labeling, or ranking. @kapa_ai tested Jev as a reranker on 1,000 real-world evaluation cases built from production queries over company knowledge bases, including product docs, Slack threads, support tickets, wikis, and code. Jev wasn’t built for reranking, yet it came within a hair of first place on retrieval quality, while also beating several dedicated rerankers. Which model finished first? The rerank-3 model from Voyage AI by MongoDB topped the benchmark for retrieval quality while also being the cheapest and fastest model that Kapa measured. Read the post for the full setup and results: mongodb.social/6016BHno7j
146
Replying to @VoyageAI @kapa_ai
great job on this!
1
22
Kapa is now an official ChatGPT plugin search your docs, tickets, wikis and code right from ChatGPT, with source links or ask it to connect a new source, or show your coverage gaps install: Plugins → Kapa
1
5
270
it's still mindblowing to be that jev isn't a reranker but it performs like one
2
5
490
Yep! We just shippede this in our platform MCP 2 weeks ago :)
1
141
love to see this integration
introducing @LangChain × kapa your langchain agents can now search all your company knowledge more accurately, 3x faster and 8x cheaper than frontier models we synch docs, github, notion, slack, zendesk and more into a single index (with vectors + file system) your agent gets two tools: search everything, and read the full doc it takes 2 min for your agent to set up (+ free to try) just paste this into your agent: "set up a knowledge base for my agent using docs.kapa.ai/getting-started… and pip install langchain-kapa-ai to use official plugin" keep making agents go brr @hwchase17 + team!
26
6
1
58
9,895
introducing @LangChain × kapa your langchain agents can now search all your company knowledge more accurately, 3x faster and 8x cheaper than frontier models we synch docs, github, notion, slack, zendesk and more into a single index (with vectors + file system) your agent gets two tools: search everything, and read the full doc it takes 2 min for your agent to set up (+ free to try) just paste this into your agent: "set up a knowledge base for my agent using docs.kapa.ai/getting-started… and pip install langchain-kapa-ai to use official plugin" keep making agents go brr @hwchase17 + team!
13
6
1
32
11,320
we think this is a peak into the future of how agents will use the web :)
introducing WebMCP in kapa any agent that visits your website can now ask your company directly today agents scrape your pages and tries to convert them to markdown. it's the early mobile web all over again, pinching and zooming through sites built for someone else instead WebMCP lets your site hand agents a proper tool. answers come from your own knowledge with source links. and you get analytics! codex and chatgpt's browser already use it. chrome has it in an origin trial if you are an existing kapa user, it's a one line change for your widget: data-webmcp-enabled="true" if you aren't, you can try it for free for 14 days :)
109
introducing WebMCP in kapa any agent that visits your website can now ask your company directly today agents scrape your pages and tries to convert them to markdown. it's the early mobile web all over again, pinching and zooming through sites built for someone else instead WebMCP lets your site hand agents a proper tool. answers come from your own knowledge with source links. and you get analytics! codex and chatgpt's browser already use it. chrome has it in an origin trial if you are an existing kapa user, it's a one line change for your widget: data-webmcp-enabled="true" if you aren't, you can try it for free for 14 days :)
2
1
2
5
369