Make your agents work
on your data.

PDFs, decks, videos, code, Slack, Drive. Mixedbread turns them into evidence your agent can act on, with fewer tool calls and fewer tokens.

Get Started

Give your agent context.

1

Upload

Supports text, images, PDFs, video, and audio across 100+ languages.

Mixedbread automatically understands and processes your data with our own models and search engine.

2

Search

Perfect results in sub 200ms. High-quality parsed content ready for any downstream task and your AI. Select the right search mode for your use case with one flag.

1
from mixedbread import Mixedbread
2
from pathlib import Path
3
4
client = Mixedbread()
5
6
client.stores.files.upload(
7
  store_identifier="my-store",
8
  file=Path("api_handler.py"),
9
)
10
11
results = client.stores.search(
12
  store_identifiers=["my-store"],
13
  query="How do we validate API tokens?",
14
  search_options={"agentic": True, "rerank": True},
15
)
16
# → evidence with source file, page, and passage for each hit
Try with
and more
Works withClaude CodeCodexOpenCodeMCPSkillsCLIPythonTypeScript
Stop wasting your agent's tokens.
Agents spend most of their tokens finding and reading. Mixedbread runs that loop for you and returns curated evidence, so your agent spends its tokens on the answer, not the search.
Harvey LABfirm-knowledge subset
Bar chart of total tokens used on the Harvey LAB firm-knowledge benchmark. A vanilla agent uses 80.6 million tokens at 21.7 turns per task. Adding Mixedbread Search cuts that by 42 percent to 47 million tokens at 14.6 turns per task. Adding Toast 1 as a subagent cuts it by another 51 percent to 23 million tokens at 11.2 turns per task. All three configurations reach the identical task score of 55, so the end result is the same performance with 3.5 times fewer tokens.
All three configurations reach the same task score of 55. Only the retrieval stack changed.
OfficeQA Pro V2cost vs. answer correctness
Answer correctness against cost per task on OfficeQA Pro V2, log-scale cost, with the Pareto frontier from the Databricks evaluation shaded underneath. Codex alone reaches 33 percent at $4.68. Codex with Toast 1 as a subagent reaches 70 percent at about $1.15, above the frontier, whose best point is Claude Fable 5 on Databricks Genie at 60 percent for $4.26.
  • Codex + Toast 1
  • Databricks Genie
  • Model provider harness
  • Databricks Pareto frontier
Evidence is the bottleneck.
As models get better, the failure mode moves from reasoning to context. Most mistakes now happen because the right evidence never reaches the model's context window, or arrives buried in noise. Mixedbread finds the evidence that matters and leaves out what doesn't, so the model reasons over the right context instead of hunting for it.
Make your agent auditable
Every search, grep, and read is traced. Every result carries its source: file, page, bounding box, exact chunk. Your agent cites what it acted on, and you can check it.
Waterfall trace of a Toast 1 agentic search: 16 tool calls across 3 rounds answering “How did the employment rate change in retail compares to the healthcare sector?” in 5.33s. Select a step to see the sub-query, grep pattern, or plan the agent produced at that point.
0ms2.67s5.33s
“How did the employment rate change in retail compares to the healthcare sector?”
3 rounds, 16 tool calls, 102,536 prompt tokens, 1,248 completion tokens
Every layer is ours.
Most retrieval stacks are assembled from parts that never met: an embedding model, a database, a reranker, and prompts to hold them together. We train the models, build the database, and train the agent on all three, so each layer is built for the one beneath it.
From the Mixedbread research lab →
  2. Trained against these exact tools: search, grep, inspect
    mxbai-rerank listwise
    Listwise reranker, same distribution
    +7.7 nDCG over Wholembed, 61× lower latency than GPT-5.6 Sol
    See eval →
  3. Reranks the candidates the embedder was trained to surface
    Wholembed V3
    Late-interaction, omnimodal, 100+ languages
    #1 on ViDoRe V3, ahead of Voyage 4 and Cohere Embed 4
    See eval →
  4. Multi-vectors stored natively. No pooling, no recall loss
    Silo
    Multi-vector engine, S3-native
    Billions of documents, ~80ms end to end
    How we built it →
Common questions.
Still unsure? Talk to us or read the docs.
What does Mixedbread do for me?
Everything between your files and your agent. You upload PDFs, decks, videos, audio, code, or connect Slack and Drive. We parse them, run OCR and transcription, chunk, embed, and index. Then your agent gets four ways to search: semantic search, grep, reranking, and agentic search, where Toast 1 runs the whole loop and hands back evidence with file, page, and passage. You don't tune models, run a pipeline, or hire a retrieval team. That part is our research, and it's what we spend all day on.
What can I build with Mixedbread?
Anything where an agent needs to find things in your data before it acts. Knowledge agents that answer from your contracts, filings, or docs. RAG, if one retrieval call is all you need. Agent memory, where the store is what the agent remembers across sessions. Coding agents that search a monorepo instead of grepping blind. Search over a video or podcast archive. A cache for web-agent output at scale. Customers run all of these on the same API; the difference is which search mode they call and what they upload.
Isn't this just RAG as a service?
You can build RAG on Mixedbread, and people do. But RAG retrieves once and hopes the top-k was right. Agents retrieve many times, and an error at any step compounds into the rest. So we build the primitives an agent needs to get the correct context every time: our own late-interaction embeddings, listwise reranker, search agent, and the vector database they run on. Co-designed, they outperform a stack you assemble from the best individual parts, without the tuning and maintenance that stack costs you.
How is this different from Exa, Parallel, or Firecrawl?
They search the public web. Mixedbread searches your data: the PDFs, decks, videos, code, Slack, and Drive that aren't on the web and never will be. Most agents need both. Think of Mixedbread as Exa or Parallel for the data you own.
How is this different from a vector database?
A vector database stores vectors. You still have to parse the files, chunk them, pick an embedding model, add a reranker, rewrite queries, and build the agent loop on top. When results get worse, you don't know which part broke. We build all of that ourselves and train the models to work together. Our vector database, Silo, is one layer of it, built to store multi-vector embeddings natively instead of collapsing them into one vector. That collapse is where most vector databases lose recall.
Do I need my own vector database or embedding model?
No. Both are built in: Wholembed V3 for embeddings, Silo to store and search them. That's the point. The models are trained for the database and the database for the models, so you don't pick, host, or tune either. People sometimes ask if they can take just the embeddings. Not for Wholembed V3. It produces multi-vector representations that need a store built for them, which is Silo. Our earlier open-weight models are on Hugging Face if you want raw vectors.
Can't I build this myself with Turbopuffer and Voyage?
You can, and it's a good stack. You'd wire up a parser, an embedding API, a vector store, a reranker, query rewriting, and then write the agent loop on top. It works. Three things you'd be giving up: Wholembed V3 scores higher than Voyage 4 Large on ViDoRe V3. Every search would cross three vendors and three networks; ours runs in one place, which is how a full agentic search lands in seconds and a plain search in ~80ms. And you'd own the tuning and the on-call.
Does it work with my agent?
Yes. Mixedbread is a set of tools your agent calls, not a framework you build inside. Use the Python or TypeScript SDK, the MCP server, or install the skill and let your coding agent wire it up. Works with Claude Code, Codex, OpenCode, and anything that can make an HTTP request. If you already have a retrieval index, Toast 1 can run over that too.
Where does my data live?
In your region, or on your infrastructure. Region deploy and on-premise are available. SOC 2 Type II and ISO 27001.
Do you train on my data?
No. Your files, your indexes, and your queries are used to serve your searches and nothing else. Everything is encrypted at rest and in transit, and you can delete a store and its data at any time. SOC 2 Type II and ISO 27001 audited; region deploy and on-premise if the data can't leave.
SOC 2 Type II
ISO 27001
Region deploy
On-premise
Ship agents with context.
Free to try, $5 in credits. Production in an afternoon.
Get an API key