<div align="center">
<img src="https://raw.githubusercontent.com/semlith/semlith/main/assets/semlith-logo.png"
alt="Semlith" width="96" height="96">
# Semlith
**Local search over your code and documents for AI agents.**
[](https://github.com/semlith/semlith/actions/workflows/ci.yml)
[](https://crates.io/crates/semlith)
[](https://crates.io/crates/semlith)
[](https://docs.rs/semlith)
[](https://www.rust-lang.org)
[](#install)
[](https://modelcontextprotocol.io)
[](LICENSE)
[Install](#install) · [Quick start](#quick-start) · [Agents](#use-it-from-an-agent) ·
[Portal](#the-portal) · [Benchmarks](#benchmarks) · [Docs](#documentation)
</div>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/images/home-dark.webp">
<img src="docs/images/home-light.webp" alt="The Semlith portal's Home page, with one store indexing BurntSushi/ripgrep">
</picture>
## Why Semlith
An agent working in a large codebase either reads too much, which is slow and
expensive, or guesses which file to open, which is often wrong. What it needs is
the few spans that answer the question. Semlith finds them.
- **Hybrid search.** Every query runs against a vector index (meaning) and a
keyword index (exact names), and the two rankings are fused. *How does retry
backoff work* and `EMBED_BATCH` both land on the right chunk.
- **A code graph built on the same pass.** Definitions become nodes, and calls,
imports and re-exports become edges, each labelled with how well it is
supported. Ask what calls a function, what breaks if it changes, or how two
symbols connect.
- **Always current.** A watcher re-embeds a file when you save it. There is no
build step and nothing to go stale against your working tree.
- **Local by design.** No API keys, and no network at query time unless you
connect a Semlith Cloud org. The portal binds to `127.0.0.1` only. Model
weights and acceleration packs are the only downloads, each pinned by digest,
and `--airgap` refuses every outbound request before a connection opens.
- **Made for agents.** An MCP server with eight tools listed by default and
sixteen in all, registered in your agent clients by `semlith setup`, and a
ledger of every retrieval with the tokens it saved.
- **More than code.** PDFs, Office documents, notebooks and Markdown are read
as text, and images are searchable by what they show.
## Install
One command, no Rust toolchain needed.
**macOS and Linux**
```sh
**Windows**
```powershell
The installer picks the release for your machine, verifies the ed25519
signature on the release's `SHA256SUMS`, checks the archive against it,
unpacks it into `~/.semlith/bin` and runs `semlith setup`. Setup puts Semlith
on your `PATH`, downloads the embedding model, registers Semlith with each agent
client that has a registration CLI, and installs the daemon as a login service.
Run `semlith setup` again at any time to repair an install, and `--yes` takes
every default.
| `SEMLITH_VERSION` | Install a specific release tag. |
| `SEMLITH_HOME` | Install somewhere other than `~/.semlith`. |
| `SEMLITH_NO_SERVICE=1` | Skip the login service. |
You can also run `cargo install semlith`, or take an archive from
[the releases page](https://github.com/semlith/semlith/releases).
`semlith upgrade` replaces the binary with the newest release, and Semlith never
checks for updates on its own.
**Requirements.** A 64-bit machine running macOS on Apple silicon, Linux on
x86_64 or aarch64, or Windows on x86_64 (Windows PowerShell 5.1 is enough).
The Linux archives ship `libonnxruntime.so` beside the binary and need only
glibc **2.34** or later and libstdc++ (GLIBCXX_3.4.22). Debian 12, Ubuntu 22.04,
RHEL 9 and Amazon Linux 2023 all qualify. Intel macOS is not supported, because
ONNX Runtime no longer ships for it.
### Verifying the installer
The installer writes the binary to `~/.semlith/bin` (mode 700 on macOS and
Linux) and, on Linux, `libonnxruntime.so` beside it. Nothing is written until
the archive passes three checks. `SHA256SUMS` must carry the project's ed25519
signature, checked with `ssh-keygen -Y verify` (OpenSSH 8.1 or later, which
macOS, current Linux distributions and Windows 10 and later have). The
archive's SHA-256 must match it. When `gh` is on your `PATH`, its GitHub
artifact attestation, signed by this repository's release workflow, is checked
too. A missing or wrong signature stops the install, and `semlith upgrade` holds
a release to the same key, built into the binary, which `semlith --version`
names. curl is held to https and TLS 1.2 or later, and the script runs only
once it has fully downloaded.
Releases before v0.40.0 are not signed, so these installers do not install
them.
To read the installer before running it:
```sh
curl --proto '=https' --tlsv1.2 -fsSLO https://github.com/semlith/semlith/releases/latest/download/install.sh
less install.sh
gh attestation verify install.sh --repo semlith/semlith
sh install.sh
```
On Windows, run `irm https://github.com/semlith/semlith/releases/latest/download/install.ps1 -OutFile install.ps1`,
read it, then run `powershell -ExecutionPolicy Bypass -File install.ps1`.
To verify an archive by hand:
```sh
echo 'semlith-release ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMTHiHMzeSHzzc+8UDZHUzJcvb6XGUBb+TJdFes91xm' > allowed_signers
ssh-keygen -Y verify -f allowed_signers -I semlith-release -n file -s SHA256SUMS.sig < SHA256SUMS
```
## Quick start
```sh
cd ~/src/ripgrep
semlith index . # one store, and the model (~52 MB) downloads once
semlith search "where is a file detected as binary"
semlith neighbors search_parallel # callers and callees
semlith start # the daemon and the portal
```
```console
$ semlith search "where is a file detected as binary" -k 1
1. 0.083 vf GUIDE.md:735-746
binary files:
1. The default mode is to attempt to remove binary files from a search
completely. ...
$ semlith neighbors search_parallel
callers (2)
main via defines (extracted) crates/core/main.rs:44 · call at line 166
run via calls (resolved) crates/core/main.rs:78 · call at line 90
callees (25)
matcher via calls (resolved) crates/core/flags/hiargs.rs:379 · called at crates/core/main.rs:177
search_worker via calls (resolved) crates/core/flags/hiargs.rs:705 · called at crates/core/main.rs:176
...
```
Every hit is a `path:start-end` locator you can hand to an editor or an agent,
and `vf` says the vector and keyword lists both found it. Documents answer the
same way.
<img src="docs/images/demo.gif" alt="semlith search answering one question from a PDF and one from a Word file, each with its file and line span" width="900">
## Use it from an agent
```sh
semlith setup # registers each agent client that has a registration CLI
semlith doctor # checks each client can actually reach it, and says how to fix it if not
```
`semlith setup` registers the MCP server at user scope in each installed client
that has a registration CLI, which is six of the 12 documented clients. The
other six are a config file, which `semlith setup --register-all` writes for
you, and `semlith doctor` reports on every one. Each stanza is run against the
binary in `tests/clients.rs`, and [docs/clients.md](docs/clients.md) has them
all with the HTTP transport. Setup also installs the Semlith Agent Skill, a
steering hook that suggests a Semlith call when an agent is about to grep, and
a read-only research agent.
`semlith mcp` serves MCP over stdio, and the daemon serves the same tools over
HTTP at `/mcp`, behind an agent key (`semlith key show`). Eight tools are listed
by default, because every definition costs tokens on every request, and
`SEMLITH_MCP_TOOLS=all` lists all sixteen.
| `semlith_search` | Where is the answer? Path, span, enclosing symbol and how it was found. |
| `semlith_brief` | Everything one question needs in one call, with spans, text and one-hop callers and callees, under a token budget. |
| `semlith_read` | One span or one symbol, nothing around it. |
| `semlith_symbol` | Where is this defined? `history: true` gives what it used to be. |
| `semlith_neighbors` | What calls it, and what it calls. |
| `semlith_impact` | Everything that reaches it, and the files involved. |
| `semlith_files` | Which files are indexed. |
| `semlith_stats` | What each store holds. |
| `semlith_path`, `semlith_trace` | How two symbols connect, as a chain or as evidence. |
| `semlith_pattern` | A tree-sitter structural pattern over one language. |
| `semlith_index`, `semlith_add`, `semlith_forget` | Change a store from inside a conversation. |
| `semlith_report` | One of five reports from the ledger, index and graph. |
| `semlith_languages` | The language names `lang` accepts. |
A bare `semlith mcp` opens every registered store, so one question can span
repositories. It speaks MCP `2026-07-28`, `2025-11-25`, `2025-06-18` and
`2024-11-05`, each proven by a session in `tests/mcp.rs`. In the official
[MCP registry](https://registry.modelcontextprotocol.io) it is listed as
mcp-name: io.github.semlith/semlith
## The portal
`semlith start` runs one daemon that owns every store. It holds each store's
write lock, watches its folders, re-embeds what you save, and serves a portal at
`http://127.0.0.1:7365`. The URL with its session token is printed once, on
stdout. [docs/portal.md](docs/portal.md) documents every page.
<table>
<tr>
<td width="50%"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/search-dark.webp"><img src="docs/images/search-light.webp" alt="Search: ranked spans with the lists that found them"></picture><br><b>Search</b>. Hybrid results, each saying which list found it.</td>
<td width="50%"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/graph-dark.webp"><img src="docs/images/graph-light.webp" alt="Graph: callers and callees of a symbol"></picture><br><b>Graph</b>. Callers, callees, blast radius and paths.</td>
</tr>
<tr>
<td><picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/indexing-dark.webp"><img src="docs/images/indexing-light.webp" alt="A live index run"></picture><br><b>Index runs</b>. Live rate per device, pause and stop.</td>
<td><picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/ledger-dark.webp"><img src="docs/images/ledger-light.webp" alt="Ledger: every retrieval an agent made"></picture><br><b>Ledger</b>. Every retrieval, and the tokens it saved.</td>
</tr>
</table>
**It is not on the network.** The daemon binds `127.0.0.1` only, with no flag
to change it. Every page and `/api/` route needs the per-run session token,
sent in a `Semlith-Token` request header, and without it the answer is 401. The
agent key opens `/mcp` and nothing else. Responses carry a
`Content-Security-Policy` of `'self'`, no CORS header is sent, and every byte
the portal loads is compiled into the binary. `--airgap` refuses every outbound
request before a connection opens, which covers model and pack downloads that
are not cached, `semlith upgrade`, the price table, Semlith Cloud and
`semlith add`. The Privacy page checks these claims against the running daemon,
and [docs/security.md](docs/security.md) is the full account.
## How it works
```
files ──chunk──> text ──embed──> vectors ──quantize──> index/*.tvim (turbovec)
│
└──parse──> symbols, edges ─────────> store.db (SQLite)
query ──embed──> vector ──search shards──┐
──keywords──> FTS5 ────────────────┴──fuse──> ranked spans ──> enclosing symbol
```
- **Reading.** Files are read as the text a person would see. Thirteen formats
have their own reader (PDF, Word, PowerPoint, Excel, notebooks and more).
Everything else is read as UTF-8 and cut into line-aligned chunks of up to
800 characters. A Markdown chunk is embedded with its heading path, a code chunk
with its enclosing definition.
- **Embedding.** `granite-embedding-small-english-r2` (int8, 384 dimensions,
~52 MB) through ONNX Runtime, fixed per store. The daemon also embeds on the
Neural Engine on Apple silicon and on the GPU (Core ML, WebGPU or CUDA), each
lane checked against known answers before its first batch. Images go through
CLIP ViT-B/32 into a second vector space and match by what an image shows,
not by OCR.
- **Storing.** `index/` holds [turbovec](https://github.com/RyanCodrai/turbovec)
shards of 65 536 quantized vectors, and `store.db` holds chunk text, spans,
symbols, edges, the ledger and the content hashes that make re-indexing
incremental. A save rewrites one shard.
- **Graph.** All 46 languages carry edges. Each edge is `extracted` (settled by
the file itself), `resolved` (one candidate), `ambiguous` (several, and it
says how many) or `inferred` (a bare name match). `semlith path` refuses to
cross a name it cannot pin down unless you pass `--all-edges`.
[docs/architecture.md](docs/architecture.md) is the full account.
## Commands
| `semlith index [PATHS...]` | Index paths into a store; re-running embeds only what changed. `--each` gives each path its own store, `--projects <DIR>` one per repository. |
| `semlith watch [PATHS...]` | Re-embed files as they are saved. |
| `semlith start` | The daemon: every store kept current, the portal and `/mcp` on `127.0.0.1:7365`. |
| `semlith search <QUERY>` | Hybrid search. `-k`, `--json`, `--path`/`--ext`/`--lang` (repeatable; a leading `!` excludes), `--prefer code\|docs`, `--exact` for regex lines with their definition. |
| `semlith brief <QUESTION>` | Spans, their text and one-hop callers and callees, under `--budget` tokens (default 4000). |
| `semlith read <TARGET>` | One span (`src/store.rs:1041-1080`) or one symbol. |
| `semlith symbol`, `neighbors`, `impact`, `path`, `trace` | The graph: definitions, callers and callees, blast radius, chains, evidence. |
| `semlith pattern <QUERY> --lang L` | A tree-sitter structural pattern. |
| `semlith stats`, `files`, `languages`, `models` | What a store holds; `files --tree` shows what was not indexed and why. |
| `semlith refused`, `scan` | Files not indexed and why; files held that today's rules would refuse. |
| `semlith add <URL>` | Fetch one https URL into a store. No crawling, no credentials, no private addresses. |
| `semlith forget`, `compact`, `drop` | Remove a file, reclaim dead bytes without re-embedding, delete a store. |
| `semlith adopt`, `trust` | Move a store into the store home; allow one outside it. |
| `semlith ledger`, `report`, `schedule`, `prices` | Retrieval history, five reports in five formats, scheduled reports, the price table. |
| `semlith mcp`, `hook`, `key` | MCP over stdio, the steering hook, the HTTP agent key. |
| `semlith setup`, `doctor`, `upgrade` | Install and repair, diagnose each client, replace the binary. |
| `semlith accel` | Which devices embed: CPU (always on, `SEMLITH_CPU_CAP` caps it), Neural Engine, GPU, and the experimental CUDA, TensorRT, OpenVINO and llama.cpp lanes. |
| `semlith cloud` | Semlith Cloud. Nothing here touches the network until `semlith cloud login`. |
`semlith <command> --help` documents every flag.
**Where stores live.** Each store lives in `~/.semlith/stores/<name>` and is
listed in `~/.semlith/registry.json`, so `semlith mcp` and `semlith start` find
every store with no flags. A command picks its store from `--store` or
`SEMLITH_STORE`, then a `.semlith` beside the corpus, then the registered store covering the current
directory, and otherwise creates one.
**What gets indexed.** Everything under the given paths except `.gitignore`d
and hidden files, binaries, files over 8 MiB, archives that expand past 32 MiB,
and generated or vendored directories. `node_modules` is always skipped, and
`target`, `build`, `dist` and `vendor` are skipped beside their manifest unless
`SEMLITH_DEFAULT_IGNORES=0` is set. Credentials are never indexed, and the grey
zone is yours to decide.
## The retrieval ledger
Every retrieval is recorded in its store, whether it came from an agent over
MCP, the CLI or the portal. A row holds the query, the client, the session, the
hits and what was read.
Each row carries the hash of the row before it, so `semlith ledger --verify`
finds an edited or deleted row. It is local, on by default, and off with
`--no-ledger` or `SEMLITH_LEDGER=0`.
**What it saved on this repository.** Ask `semlith brief` all 107 questions of
this repository's retrieval harness against a store of `src/`, then run
`semlith ledger --verify`. An answered question sent **3 982 tokens** to the
agent on average, against **105 132** for reading the 4.1 files those answers
named, whole. That is 26× less, at 100 % coverage, counted with the store's own
tokenizer. It is an upper bound, because a file named by two answers is counted
twice.
## Benchmarks
Asked 127 questions about 53 public documents, an Opus agent with Grep, Glob and
Read found the passage 63 % of the time, and 41 of its 127 top quotes appear
nowhere in the document it named. It found the file by name, could not read it,
and wrote something plausible. With Semlith installed it found 98 %, and 0 of
126 quotes were made up. On single-repo code with a strong model it does not
help, and Opus scores 92 % with or without it.
Public code-retrieval benchmarks, run by [`bench/scorecard/`](bench/scorecard/README.md)
on one M1 MacBook Air in October 2026 and published as measured, including where
another tool wins. **Every table, every chart and the command that reproduces each
number are on the [scorecard page](bench/scorecard/README.md).**
| SWE-bench Verified, right file in the top 10 | **76.8 %** | 47.0 % grep then read | 500 |
| SWE-bench Lite, right file in the top 10 | **72.3 %** | 47.3 % grep then read | 300 |
| SWE-bench Verified, median tokens to the first right file | **224** | 15 491 grep then read | 500 |
| CodeRAG-Bench DS-1000, NDCG@10 | **0.260** | 0.158 BM25 | 513 |
| Agents (Opus), cost per correct answer | **$0.065** | $0.072 grep only | 50 × 3 runs |
| Documents (PDF, Office, EPUB, …), passage found within 4k tokens | **116/127** | 34/127 rga | 127 |
| Agents (Opus) on those documents, passage found | **124/127** | 80/127 grep only | 127 |
| Real sessions, tokens sent against whole files read | **75.2× fewer** | | 1,575 retrievals |
<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/bench/swe-hit-dark.svg"><img src="docs/images/bench/swe-hit-light.svg" alt="SWE-bench: Semlith puts the right file in the top 10 for 72-77 % of instances, against 47 % for grep then read" width="760"></picture>
<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/bench/swe-tokens-dark.svg"><img src="docs/images/bench/swe-tokens-light.svg" alt="SWE-bench: Semlith returns a median 224-225 tokens before the first right file, against 8 813-15 491 for grep then read" width="760"></picture>
<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/bench/competitors-dark.svg"><img src="docs/images/bench/competitors-light.svg" alt="Nine tools on SWE-bench Lite. Semlith 55 % hit@5, semble 50 %, graphify and sourcebot 35 %, serena 25 %, rg and ugrep 15 %. grepai, colgrep and ck were not run" width="760"></picture>
<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/bench/agents-cost-dark.svg"><img src="docs/images/bench/agents-cost-light.svg" alt="Agents, cost per correct answer, grep only against Semlith installed and Semlith first, on Opus and Haiku" width="760"></picture>
<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/bench/coderag-dark.svg"><img src="docs/images/bench/coderag-light.svg" alt="CodeRAG-Bench NDCG@10 per task, Semlith against BM25" width="760"></picture>
Semlith does not win everywhere. Semble edges it at hit@1 and hit@10 on the
20-instance competitor sample, BM25 beats it on CodeRAG-Bench's RepoEval, and
with Grep built in, Opus rarely reaches for Semlith on its own. The
[scorecard page](bench/scorecard/README.md) has these rows and RepoBench-R.
## The numbers
**Coverage**, read out of the code. `tests/readme.rs` fails the build if any of
these drifts from its source.
| languages searchable and graphed | **46** |
| edge kinds | **6** |
| document formats with a reader | **13** |
| image types | **5** |
| MCP tools | **16** |
| CLI commands | **36** |
| agent clients, each setup stanza run against the binary in `tests/clients.rs` | **12** |
| prebuilt targets | **4** |
**Measured** on a 4P+4E Apple silicon laptop, with the command that reproduces
each. [docs/performance.md](docs/performance.md) has the full tables.
| warm search at 700 / 7 000 / 70 000 chunks, peak RSS under 240 MB | **16.2 / 37.9 / 159.1 ms** | `cargo test --release --test measure -- --ignored --nocapture` |
| edit on disk to searchable, watcher running | **1.24 s** | [docs/performance.md](docs/performance.md) |
| indexing on an M1 Air: Neural Engine / CPU and GPU through Core ML | **229.8 / 62.7 chunks/s** p10 | [docs/performance.md](docs/performance.md) |
| daemon memory 60 s after a run, seven stores open | **465 MB** | `footprint -p <pid>` |
| idle watcher CPU over 60 s | **under 1.0 s** | the same |
| one changed file | **1 shard rewritten** | `cargo test --release --test shards -- --ignored --nocapture` |
| `tools/list` | **2 633 bytes**, eight tools; 1 323 tokens added to an Opus request | `cargo test --release --test retrieval -- --ignored` |
| retrieval, 30 sealed questions of 107 | **hit@1 24/30, hit@3 27/30, hit@8 29/30**, zero spread; identifiers **11 of 11** in the top three | the same |
| one search, rescoring off / on | **8.2 ms** / 132.2 ms on a 300-file store | the same |
| one answered question, `brief` against search-then-read | **1.00 calls vs 2.54**, 1 112 tokens vs 725 | the same |
| call-edge resolution | **62 %** settled | the same |
| the macOS arm64 binary | **125 435 312 bytes** (119.6 MiB) | `ls -l target/release/semlith` |
| the Linux glibc floor | **GLIBC_2.34** | `objdump -T semlith runtime/libonnxruntime.so` |
Peak memory does not grow with the corpus, so plan for about 600 MB whatever you
index. Query latency does, because the vector scan is linear.
## Known limits
- One writer per store. While the daemon or `semlith watch` holds a store, a
second `semlith index` against it exits and names the holder.
- First indexing is bound by the model, at about 230 chunks/s on an M1's Neural
Engine, 63 on its CPU and GPU, 30 on the CPU alone. Later runs embed only what
changed. On macOS the CPU lane alone runs at about 60 % of a terminal's speed
inside the login service, because of how launchd schedules agent threads.
- On a Mac the GPU does not embed beside the Neural Engine unless you run
`semlith accel on gpu-beside-ane`. CUDA runs on Linux x86_64 only, and an
NVIDIA card on Windows embeds through WebGPU.
- A new binary on macOS asks again for access to folders such as Documents, and
a store there waits, showing `running`, until the prompt is answered.
- A store larger than `SEMLITH_INDEX_MEMORY` reads shards from disk on every
query, so raise the budget if the store fits in memory.
- The default model is English-only and fixed when a store is created. Image
search is not OCR.
- Search filters are SQLite `GLOB` (no regex), and `--lang` maps extensions and
never reads contents. Multi-store search merges rankings rather than ranking
jointly. Cross-encoder rescoring (`SEMLITH_RERANK=on`) is off by default,
because it costs about 16× the search time for two more answers in 77 at k=1.
- Binaries are not notarised by Apple or Authenticode-signed for Windows. Each
release carries an ed25519-signed `SHA256SUMS` and a GitHub artifact
attestation instead. There is no ARM64 Windows or Intel macOS build, and
`semlith upgrade` only replaces a binary in `~/.semlith/bin`.
## Documentation
| [docs/portal.md](docs/portal.md) | Every page and control of the portal. |
| [docs/clients.md](docs/clients.md) | Setup stanzas for 12 agent clients and the HTTP transport. |
| [docs/architecture.md](docs/architecture.md) | How the pieces fit together, and why. |
| [docs/performance.md](docs/performance.md) | Every measured number, with its command and date. |
| [docs/models.md](docs/models.md) | The embedding models, and how to choose one. |
| [docs/security.md](docs/security.md) | The threat model and what is on the wire. |
| [docs/compatibility.md](docs/compatibility.md) | What is a contract, and what a 0.x version promises. |
| [CHANGELOG.md](CHANGELOG.md) | What changed in each release. |
## Contributing
Contributions are welcome. [CONTRIBUTING.md](CONTRIBUTING.md) covers building,
the checks CI runs and what is out of scope, and [AGENTS.md](AGENTS.md) is the
same for a coding agent. Everyone follows the [Code of Conduct](CODE_OF_CONDUCT.md).
To report a security problem, see [SECURITY.md](SECURITY.md) rather than opening
an issue.
## Prior art
Semlith's vector index is [turbovec](https://github.com/RyanCodrai/turbovec) by
Ryan Codrai (MIT), an implementation of TurboQuant from ["TurboQuant: Online
Vector Quantization with Near-optimal Distortion
Rate"](https://arxiv.org/abs/2504.19874) by Amir Zandieh, Majid Daliri, Majid
Hadian and Vahab Mirrokni. TurboQuant is data-oblivious. It rotates each vector
randomly and quantizes each coordinate on its own, with no training pass. That
is what an index refreshed on every file save needs. There is nothing to gather
before the first file and nothing to rebuild as the corpus grows, and a vector
added is a vector searchable.
## License
Apache-2.0. See [LICENSE](LICENSE) and [NOTICE](NOTICE).
Model weights are downloaded at runtime under their own licenses. The default,
ibm-granite/granite-embedding-small-english-r2, is Apache-2.0, and the CLIP
ViT-B/32 pair, the WebGPU plugin (MIT) and the NVIDIA libraries the CUDA pack
fetches carry theirs. See [docs/models.md](docs/models.md).