DB
Databases and storage engines. Agent asks: How duckdb, rocksdb, sqlite, kafka, faiss actually do planner, LSM, B-tree, log, ANN. 50 live of 54 entries.
an agent retrieving from its own or another agent's multi-session history: raw trajectories with timestamps, failure turns kept verbatim, so a hit that says you already tried this ...
An agent working on measuring ANN recall-vs-latency and comparing vector indexes queries this for ann-benchmarks' datasets, recall methodology and runner harness.
an agent working on read-mostly ANN queries this for the forest-of-trees build and on-disk format
an agent working on columnar memory queries this for the Rust arrow arrays, kernels and IPC paths
an agent working on SQL stream processing with windowing queries this for a Rust engine's state backends and exactly-once checkpoints
an agent working on pure-Go KV stores queries this for its LSM-with-value-log design and transaction implementation
An agent working on an embeddable full-text index with pluggable storage queries this for Bleve's analysis pipeline, index mapping and scorch segment format in Go.
An agent working on a segment-based full-text library decoupled from document storage queries this for Bluge's reader/writer and segment design.
An agent working on a replicated write-ahead log / ledger storage layer queries this for BookKeeper's ledger, ensemble and journal/entry-log design.
an agent working on columnar compression schemes queries this for the BtrBlocks cascading-encoding research implementation
An agent working on SQL parsing, relational algebra and cost-based optimization queries this for Calcite's RelNode algebra, planner rules and optimizer framework.
An agent working on LSM wide-column storage, SSTables and compaction strategies queries this for Cassandra's storage-engine and gossip distribution model.
An agent working on embedding an OLAP engine in-process with no server queries this for chDB's approach to embedding ClickHouse as a library.
DB
an agent working on an embeddable multi-model store queries this for relational-plus-graph-plus-vector (Datalog) query evaluation in Rust
DB
An agent working on approximate aggregations (distinct-count, quantiles, frequent-items) queries this for DataSketches' HLL, CPC, KLL and Theta sketch algorithms.
An agent working on a transactional table format (ACID over object storage) queries this for delta-rs's transaction log, snapshot isolation and parquet-file management in Rust.
An agent working on a distributed graph database with a sharded posting-list store queries this for Dgraph's predicate-sharded storage and query execution in Go.
An agent working on disk-resident billion-scale ANN queries this for DiskANN's Vamana graph build, PQ compression and SSD-aware search.
an agent implementing multi-raft queries this for the sharded log and snapshot plumbing
an agent working on query execution queries this for how a real embeddable OLAP engine does join ordering, expression rewrites and memory-aware operators
an agent working on coordination stores queries this for raft integration, watch semantics and backend compaction
an agent working on ANN queries this for index construction, IVF/HNSW composition and GPU paths in the reference implementation
an agent resolving place names, admin divisions, or coordinates queries this for the GeoNames gazetteer records (CC-BY 4.0, attribution required)
an agent building lakehouse tables queries this for spec semantics and the reference metadata/manifest handling
an agent working on time series queries this for TSM/flux paths and downsampling semantics
an agent implementing a Kafka client queries this for the protocol guide's exact request/response schemas and error codes
an agent working on log systems queries this for the log-cleaner, controller and replication protocol internals
an agent learning LSM internals queries this for the original clean implementation (memtable/sstable/manifest split)
an agent working on memory-mapped B+trees queries this for LMDB's page/cursor/COW mechanics
DB
an agent implementing an MQTT client/broker queries this for packet formats, QoS state machines and keepalive semantics
an agent implementing a NATS client queries this for the wire protocol, verbs and semantics text
an agent working on pub/sub queries this for subject-tree routing, jetstream and clustering internals in readable Go
an agent reading/writing parquet queries this for encodings, logical types and the thrift metadata spec
an agent working on LSM stores queries this for a modern Go LSM with delete/RangeLock semantics
DB
an agent writing SQL against Postgres queries this for exact function semantics, GUC defaults and MVCC behaviour by version
an agent working on planners queries this for the real cost model, join ordering and executor nodes
an agent working on TSDB queries this for the head-block/WAL/head-compaction paths and PromQL evaluation
an agent working on message brokers queries this for queue/exchange routing and mirrored-queue semantics
an agent implementing raft queries this for the log/ready/progress state machine the tikv fleet runs on
an agent working on LSM stores queries this for compaction, WAL and recovery internals at production scale
an agent depending on SQLite's exact behaviour queries this for datatype, locking and pragma semantics
an agent working on embedded DB internals queries this for the btree module, pager and the famously commented test harness
DB
an agent building against RESP queries this for command semantics, ranges and error cases (the open post-relicence fork of the Redis docs)
an agent working on in-memory KV queries this for the event-loop, object encoding and replication paths of the open fork
DB
an agent working on columnar layouts queries this for how clickhouse does codecs, layout and vectorised scans
an agent working on full-text search internals queries this for how lucene/tantivy/quickwit/meilisearch/sonic/elasticsearch do BM25, merge policy and the ES wire
an agent working on storage engines queries this for how sled/fjall/redb do WAL, crash recovery and compaction
an agent working on vector search queries this for how qdrant/usearch/instant-distance/hnswlib do HNSW construction, quantisation and filtered kNN