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.

Metadata

Release files for llmtrim 0.13.7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for llmtrim 0.13.7
File
llmtrim-0.13.7-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details
llmtrim-0.13.7-py3-none-manylinux_2_34_x86_64.whl Python 3 none Linux glibc 2.34+ x86-64 Details
llmtrim-0.13.7-py3-none-manylinux_2_34_aarch64.whl Python 3 none Linux glibc 2.34+ ARM64 Details
llmtrim-0.13.7-py3-none-macosx_11_0_arm64.whl Python 3 none macOS 11.0+ ARM64 Details
llmtrim-0.13.7-py3-none-macosx_10_12_x86_64.whl Python 3 none macOS 10.12+ x86-64 Details

Total release size: 41.0 MB

Release files / llmtrim-0.13.7-py3-none-win_amd64.whl

Download URL llmtrim-0.13.7-py3-none-win_amd64.whl
Size 8.0 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
d4696c0f6d52a4579a649a7548deaba59e90f8a13e64bfcb7aad4e062034b333
BLAKE2b-256 checksum
How to use checksums
6ba03006777523b1c3d130ed65c9f81c75590608f926f39805d9f444772c73c7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 16, 2026.

Transparency log

Release files / llmtrim-0.13.7-py3-none-manylinux_2_34_x86_64.whl

Download URL llmtrim-0.13.7-py3-none-manylinux_2_34_x86_64.whl
Size 8.5 MB
Tags Linux glibc 2.34+ x86-64 Python 3
SHA-256 checksum
How to use checksums
f6703896e7392af54de0f20fa145319fc4fe618fa5f5b0be994a7982486cc159
BLAKE2b-256 checksum
How to use checksums
83103813efe04e2c24b94b172ec0ea8fdde8ad7dbadd6d9988389dbc310ecc09
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 16, 2026.

Transparency log

Release files / llmtrim-0.13.7-py3-none-manylinux_2_34_aarch64.whl

Download URL llmtrim-0.13.7-py3-none-manylinux_2_34_aarch64.whl
Size 8.4 MB
Tags Linux glibc 2.34+ ARM64 Python 3
SHA-256 checksum
How to use checksums
6bb8b3b10c420f675616f93ff91a88574941ee51746741a4196506a98f92d80a
BLAKE2b-256 checksum
How to use checksums
b6b1fc57db6eb0eb4e44fc6cffc359b8749f646ea54fe720795156153ddd9428
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 16, 2026.

Transparency log

Release files / llmtrim-0.13.7-py3-none-macosx_11_0_arm64.whl

Download URL llmtrim-0.13.7-py3-none-macosx_11_0_arm64.whl
Size 8.1 MB
Tags Python 3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
17f11e381413131341ce6226a43be0798b31bd41bc631a3b15bfc0bbc41ac93d
BLAKE2b-256 checksum
How to use checksums
93686e7302cace0b5bb4aa4a143ff7c8fcc5297a82f85c9d18b30aae8250b8f4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 16, 2026.

Transparency log

Release files / llmtrim-0.13.7-py3-none-macosx_10_12_x86_64.whl

Download URL llmtrim-0.13.7-py3-none-macosx_10_12_x86_64.whl
Size 7.9 MB
Tags Python 3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
dab69c37ca9dd244e41f72be3e2aa9b04524988f056da264836888f32cb0104f
BLAKE2b-256 checksum
How to use checksums
b5663651f1a2122a5b4b5285c469342062dbff4a00c3c10ed8eaa09c91fa3575
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 16, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.13.7 This release

5 release files

0.13.6

5 release files

0.13.5

5 release files

0.13.2

5 release files

0.13.1

5 release files

0.13.0

5 release files

0.12.6

5 release files

0.12.2

5 release files

0.12.1

5 release files

0.12.0

5 release files

0.11.9

5 release files

0.11.8

5 release files

0.11.7

5 release files

0.11.6

5 release files

0.11.5

5 release files

0.11.4

5 release files

0.11.3

5 release files

0.11.2

5 release files

0.11.1

5 release files

0.11.0

5 release files

0.10.2

5 release files

0.10.1

5 release files

0.10.0

5 release files

0.9.4

5 release files

0.9.3

5 release files

0.9.2

5 release files

0.9.1

5 release files

0.9.0

5 release files

0.5.0

5 release files

0.4.0

5 release files

0.3.2

5 release files

0.3.1

5 release files

0.3.0

5 release files

0.2.1

5 release files

0.2.0

5 release files

0.1.13

5 release files

0.1.12

5 release files

0.1.11

5 release files

0.1.10

5 release files

0.1.9

5 release files

0.1.8

5 release 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