Unified engine

A Powerful Database
for AI

Data Harness and Search Tools for your AI

Give your AI the right data, not all the data. CameoDB loads your data into one engine that stores it, indexes every field and controls who can read what, so your AI answers from records that are fresh and relevant.

Unified MCP-native Field projection Leaderless Single binary
Swipe the pages or drag the names · keys ←→
The dual-write problem

Your index is always
a little bit wrong

The classic stack writes to the database, then updates a search index on the side. Between those two writes, search disagrees with the data, and an agent reading in that window gets an answer that was never true.

CameoDB has one write path. The search index is a view of the store, so it catches up with every commit and after every restart.

Database + separate search cluster
two clusters to scaleasynchronous lagtwo-sided recovery
CameoDB
readable by id at oncesearchable after the next commitcarried through a restart
Unified storage engine

One write path,
one source of truth

Redb for key-value durability, a flexible document model and Tantivy for full-text search, behind one write path in one process.

  • Point reads in about 0.1 ms A lookup by id is a single Redb B-tree read, ready the moment the write returns.
  • ACID from the first write Redb commits every write durably and carries it safely through a restart.
  • Faults stay small A panic fails one request, not the process, and a writer that stops is restarted over the same store.
One write, four stagesone process
  1. 01
    Sequence & WAL Redb A monotonic sequence id, logged in the same transaction as the document.
  2. 02
    KV insert Redb The document body lands in the data table, for O(log N) retrieval by id.
  3. 03
    Indexing Tantivy Fields are parsed and handed to the index writer for full-text search.
  4. 04
    Dual commit RedbTantivy Redb commits with fsync; Tantivy commits on a steady clock and records how far it has read, so recovery picks up right where it left off.
AI & MCP

Point your agent at it.
That is the integration

CameoDB speaks MCP natively, on the same port as its HTTP API. Claude Code, Claude Desktop, Cursor and Windsurf connect with one line, and ChatGPT and claude.ai connect by URL with OAuth.

  • Indexes that describe themselves Every field’s type, tokenizer and operators, read straight from the engine, so an agent composes queries from what the data holds.
  • Scoped to its key An agent is offered only the tools and indexes its key may use, and every call is checked against both.
  • Every answer explains itself Shards answered, the schema version searched, and any clause set aside, by name.
terminal
# Claude Code
claude mcp add --transport http cameodb \
  http://localhost:9480/mcp
tools/listsix tools · all reads
list_indexesdescribe_index search_indexsearch_across_indexes validate_queryget_catalog_stats

Entries for Claude Desktop, Cursor, Windsurf and OAuth clients are on the Build page →

Lean by design

Only what the model
asked for

Stop paying tokens for fields the model never needed. CameoDB projects inside the engine, on the shard that holds the document, so only the fields you request are serialized and sent.

  • Hits sized for their reader A field of a hundred thousand values comes back trimmed, matching elements first and their positions named, so the evidence for a hit is in the hit.
  • Each value stored once A ghost field searches one stored text through as many language analyzers as it needs, with no second copy.
search_index books title:"Animal Farm"
fields: [title, author, publication_date]
stored document, on its shard
projected on the shard
title
Animal Farm
author
George Orwell
publication_date
1945-08-17
3 of 7fields leave the shard; the summary stays home
29–61%of former size: rows compressed against the index’s own dictionary
Distributed mesh

No leader. No quorum.
No coordinator to lose

Nodes join and leave without an election. Every node can route any request, and the mesh answers as one.

  • Consistent hashing Every node computes a key’s owner from the same ring, so placement needs no coordination.
  • Kademlia DHT Point a node at one seed and it learns the rest of the mesh from its peers.
  • Scatter-gather Queries fan out in parallel and merge on return, so no node becomes the bottleneck.
CameoDB consistent-hash ring Five nodes placed around a hash ring. Each node owns the key range ending at its position. Peers link directly to one another, with no coordinator at the centre. KEY RANGE N1 N2 N3 N4 N5 NO COORDINATOR
key range owned by N2 node on the hash ring direct peer link
Benchmarks & provenance

Production posture
not a promise

End-to-end figures from cameodb-bench, the harness in the repository, observed by the client over HTTP. Every release ships with the artifacts an enterprise review asks for.

  • Verifiable, not just claimed Every artifact is cosign-signed with a published SHA-256, with SPDX and CycloneDX SBOMs. Check a build yourself
  • Open licensing An Apache-2.0 core and MIT clients; the server is FSL-1.1-Apache-2.0 and becomes Apache-2.0 two years after release.
Bulk ingest
370,000 docs/s
One node, four shards, fsync on every commit.
Single writes
65,000/s
One document per request, with wal_sync off.
Search throughput
11,600/s
On 15 cores, scaling with every thread.
Search p99
5.75 ms
6,300 searches/s at concurrency 16, eight cores.

Closed-loop service times at a fixed concurrency, on a 15-core Apple M5 Pro and an eight-core Linux node, with settings tuned for throughput.

Get going

Download, run, query

Six commands from an empty directory to a query answered. The MCP endpoint comes up with the server, so an agent can ask the same question right away.

terminal
# macOS: grab the binary
curl -sSO https://dl.cameodb.com/mac/cameodb
chmod +x ./cameodb

# start the server on :9480
./cameodb

# in a second terminal, open the client
./cameodb client -i

# load a public dataset, schema inferred
cameodb@localhost ▶ data load books https://dl.cameodb.com/examples/data/booksummaries.tsv

# search what you just indexed
cameodb@localhost ▶ search books title:"Harry Potter" limit 7