Getting started
Everything here runs offline. No example makes a paid provider call, starts a resource or reads a credential you already have.
Prerequisites
| Tool | Version | Needed for |
|---|---|---|
| Rust | 1.98, edition 2024 | The workspace |
| go-task | any v3 | task check and task rust |
| ESS | 0.36.0 | The specification and conformance stages of task check |
| AEP | 0.61.1 | The planning stage of task check |
More columns: swipe horizontally, or focus the table and use the arrow keys.
Rust alone is enough to build, test and run the examples.
Get the source
git clone https://github.com/beyond10x/llm.git
cd llm
cargo test --workspace --locked
The workspace forbids unsafe, and Clippy runs all plus pedantic at deny.
Run a model turn with no network and no credential
cargo run --locked -p b10x-llm-core --example embedded
An embedded model turn. (EndTurn; usage None)
The example implements Model in-process and calls it through the same port a real client
implements. usage None is not a mistake: the example reports no counters, so none are shown.
Run a local turn walks through it.
Explain a route without resolving a secret
cargo run --locked -p b10x-llm-routing --example explain
It reads examples/catalog.toml
and prints the selected target, each candidate's provenance and capabilities, and why each other
candidate was rejected. Explain a route shows the output.
Price recorded usage
cargo run --locked -p b10x-llm-cost --example quote
It prices fixture observations against a fictional price book and prints an llm.cost/2 report
whose metered estimate is 0.00022 USD. Price recorded usage
explains the report.
Evaluate a crate from your own project
:::warning Read the licence first
The source is published under a proprietary notice, not an open-source licence.
LICENSE permits reading the source and
building and running it locally to evaluate, review or verify it. Any other use needs a separate
written agreement.
:::
Nothing is published to crates.io. The workspace is publish = false at version 0.1.4. To try a
crate from a scratch project, depend on it from Git and pin an exact revision, because nothing
about the API is stable yet:
[dependencies]
llm-core = { package = "b10x-llm-core", git = "https://github.com/beyond10x/llm", rev = "<commit>" }
llm-chat = { package = "b10x-llm-chat", git = "https://github.com/beyond10x/llm", rev = "<commit>" }
Package names start with b10x-. Library names do not, so the code says use llm_core::….
Crate layout says which crate owns what.
Next
- Call a local endpoint: send a real turn to a vLLM-compatible server declared in TOML.
- Run the checks: what
task checkproves, and what it does not.