Skip to main content

llmtrim-uniffi

UniFFI bindings over llmtrim-core: one Rust definition, idiomatic in-process bindings for Python, Ruby, Swift and Kotlin. The compression runs natively in the caller's process (no server, no async).

API

A deliberately flat surface over the engine:

fn compress(
    input: String,                 // a provider-shaped request body (JSON)
    provider: Option<Provider>,    // OpenAi | Anthropic | Google, or None to auto-detect
    preset: Option<String>,        // "aggressive" | "agent" | "code" | "rag" | "safe" | …
                                   // None = config from the environment / config file
) -> Result<CompressOutput, LlmtrimError>

CompressOutput carries the compressed request_json, the resolved provider/model, the tokenizer label/exactness, and the before/after/frozen input-token counts. Embedders that need the full rehydration plan or per-stage reports should depend on llmtrim-core directly in Rust.

In-process vs. the proxy

llmtrim has two integration routes:

  • The proxy (HTTPS_PROXY=127.0.0.1:8788 llmtrim) intercepts your existing traffic and compresses it in flight. Nothing in your code changes, but the client has to route through the proxy and trust its CA.
  • These bindings compress in your process. You call compress() on the request body, then send the result with your own HTTP client. No proxy, no CA, no env-var setup.

Use the in-process path when the proxy can't run:

  • Sandboxed / serverless functions where you can't set a process-wide HTTPS_PROXY or run a side process.
  • Certificate-pinned clients that reject a MITM CA, so the proxy's interception fails.
  • Anywhere you'd rather not add a network hop or an extra moving part.

It replaces a per-framework adapter: instead of wiring a hook into each SDK, you compress the body once and POST it yourself. Runnable end-to-end examples (compress, then send with your own client) are in examples/.

Python

# Build a self-contained wheel (cdylib + generated glue):
crates/llmtrim-uniffi/scripts/build-wheel.sh --release
pip install target/wheels/llmtrim-*.whl
import llmtrim, json

req = json.dumps({"model": "gpt-4o",
                  "messages": [{"role": "user", "content": "…"}]})
out = llmtrim.compress(req, llmtrim.Provider.OPEN_AI, "aggressive")
print(out.input_tokens_before, "->", out.input_tokens_after)
# send out.request_json to the provider

Why build-wheel.sh and not plain maturin build: maturin's bindings = "uniffi" auto-packaging is sensitive to the maturin↔uniffi version pair. With maturin 1.14 + uniffi 0.31 it builds the native library into the wheel but omits the generated Python glue (empty package __init__.py). The script runs maturin, then injects the freshly generated bindings and repacks the wheel with valid RECORD hashes. Remove it once the auto path packages cleanly.

Ruby / Swift / Kotlin

All targets generate from the same built library, no extra Rust. The generated glue is a build artifact (its checksums are pinned to the library ABI), so it is regenerated per release rather than committed:

crates/llmtrim-uniffi/scripts/generate-bindings.sh out/   # python, ruby, swift, kotlin

Generation needs an unstripped library. Library-mode uniffi-bindgen reads metadata symbols from the cdylib, but the workspace release profile sets strip = true. The script therefore generates from the (unstripped) debug build; the native library you ship can be a stripped cargo build --release -p llmtrim-uniffi cdylib; the glue loads it by name.

Ruby (verified). This is the raw generated binding (module LlmtrimFfi), for a source build with libllmtrim_ffi.so on the load path. The published gem aliases it to Llmtrim (require "llmtrim" then Llmtrim.compress(...)); see packaging/ruby.

require_relative "llmtrim_ffi"
require "json"
out = LlmtrimFfi.compress(
  JSON.generate({model: "gpt-4o", messages: [{role: "user", content: "…"}]}),
  LlmtrimFfi::Provider::OPEN_AI, "aggressive")
puts "#{out.input_tokens_before} -> #{out.input_tokens_after}"

Swift emits llmtrim_ffi.swift + an FFI header and modulemap; Kotlin emits uniffi/.../llmtrim_ffi.kt (which loads the cdylib via JNA). CI compiles and runs a smoke for both: Swift on macOS (swiftc against the modulemap), Kotlin on a JVM (kotlinc + JNA), so a binding break is caught in all four languages (see tests/swift, tests/kotlin and the bindings* jobs in .github/workflows/ci.yml).

Publishable packages

Each ships the compiled engine bundled, so consumers need no Rust toolchain:

Target Build Package Verified
Python (PyPI) scripts/build-wheel.sh wheel locally
Ruby (gem) scripts/build-gem.sh packaging/ruby/ locally
Kotlin/JVM (Maven) scripts/build-maven.sh packaging/kotlin/ locally
Swift (SwiftPM) scripts/build-xcframework.sh packaging/swift/ macOS CI only

Each packaging/<lang>/README.md has the usage + publish details.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

llmtrim-0.13.3-py3-none-win_amd64.whl (8.0 MB view details)

Uploaded Python 3Windows x86-64

llmtrim-0.13.3-py3-none-manylinux_2_34_x86_64.whl (8.5 MB view details)

Uploaded Python 3manylinux: glibc 2.34+ x86-64

llmtrim-0.13.3-py3-none-manylinux_2_34_aarch64.whl (8.4 MB view details)

Uploaded Python 3manylinux: glibc 2.34+ ARM64

llmtrim-0.13.3-py3-none-macosx_11_0_arm64.whl (8.0 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

llmtrim-0.13.3-py3-none-macosx_10_12_x86_64.whl (7.9 MB view details)

Uploaded Python 3macOS 10.12+ x86-64

File details

Details for the file llmtrim-0.13.3-py3-none-win_amd64.whl.

File metadata

  • Download URL: llmtrim-0.13.3-py3-none-win_amd64.whl
  • Upload date:
  • Size: 8.0 MB
  • Tags: Python 3, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for llmtrim-0.13.3-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 51f1c3ade1e7e63a9077696e7ad8c076aac460a5af1577275c3187146d3096de
MD5 f184ca1485287417093c9ef225ebfab1
BLAKE2b-256 87836393680af4ce3f6a487f5f40375460f3b08e8a15c996044473c4056cc076

See more details on using hashes here.

Provenance

The following attestation bundles were made for llmtrim-0.13.3-py3-none-win_amd64.whl:

Publisher: release-bindings.yml on fkiene/llmtrim

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llmtrim-0.13.3-py3-none-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for llmtrim-0.13.3-py3-none-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 d1212003a986d0695b7b4c988b18384ab688510e7f6dd61ae89018eae4295d66
MD5 541857aa327ae503afc080fda6363c0b
BLAKE2b-256 2411a97049545d426da40425d43fb9d3f9a097fd111e00ee21b9a95d82f6d469

See more details on using hashes here.

Provenance

The following attestation bundles were made for llmtrim-0.13.3-py3-none-manylinux_2_34_x86_64.whl:

Publisher: release-bindings.yml on fkiene/llmtrim

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llmtrim-0.13.3-py3-none-manylinux_2_34_aarch64.whl.

File metadata

File hashes

Hashes for llmtrim-0.13.3-py3-none-manylinux_2_34_aarch64.whl
Algorithm Hash digest
SHA256 559c89d25f24e82eee7be357e240b4b0db26621d116d7b67a7c16d20bed018df
MD5 b3783dac9e2560c65fe6fe7ae81404ff
BLAKE2b-256 982d41cd1495ca2aaf8c1f14668f40e2f9c3799a79a8792479629492135c15ec

See more details on using hashes here.

Provenance

The following attestation bundles were made for llmtrim-0.13.3-py3-none-manylinux_2_34_aarch64.whl:

Publisher: release-bindings.yml on fkiene/llmtrim

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llmtrim-0.13.3-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for llmtrim-0.13.3-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 c61be9646f503bb7aefd59bc8a3bd5b3b97224c2a7405cb2709b0687aacb0c82
MD5 a3870e07f5a0386ca34c64726103fc56
BLAKE2b-256 5e619508ffeb3bcfa763fe2f2e9df7ed97fabec99665fcd710f13d056d05114e

See more details on using hashes here.

Provenance

The following attestation bundles were made for llmtrim-0.13.3-py3-none-macosx_11_0_arm64.whl:

Publisher: release-bindings.yml on fkiene/llmtrim

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llmtrim-0.13.3-py3-none-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for llmtrim-0.13.3-py3-none-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 2bda0a0621b2f33d5f3006daa186984630f24a890efa99365a9fc6fb8b7eed19
MD5 430d3593830252d843f85068220b74cc
BLAKE2b-256 f58f2595fb5af2030063be6dcb0e52ef9abc47ec29317c0fcb3bfb65a790810c

See more details on using hashes here.

Provenance

The following attestation bundles were made for llmtrim-0.13.3-py3-none-macosx_10_12_x86_64.whl:

Publisher: release-bindings.yml on fkiene/llmtrim

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.13.3 This release

5 files

0.13.2

5 files

0.13.1

5 files

0.13.0

5 files

0.12.6

5 files

0.12.5

5 files

0.12.4

5 files

0.12.3

5 files

0.12.2

5 files

0.12.1

5 files

0.12.0

5 files

0.11.12

5 files

0.11.11

5 files

0.11.10

5 files

0.11.9

5 files

0.11.8

5 files

0.11.7

5 files

0.11.6

5 files

0.11.5

5 files

0.11.4

5 files

0.11.3

5 files

0.11.2

5 files

0.11.1

5 files

0.11.0

5 files

0.10.2

5 files

0.10.1

5 files

0.10.0

5 files

0.9.4

5 files

0.9.3

5 files

0.9.2

5 files

0.9.1

5 files

0.9.0

5 files

0.5.0

5 files

0.4.0

5 files

0.3.2

5 files

0.3.1

5 files

0.3.0

5 files

0.2.1

5 files

0.2.0

5 files

0.1.13

5 files

0.1.12

5 files

0.1.11

5 files

0.1.10

5 files

0.1.9

5 files

0.1.8

5 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page