llmterm
| Crates.io | llmterm |
| lib.rs | llmterm |
| version | |
| source | src |
| created_at | 2025-03-10 03:02:07.430483+00 |
| updated_at | 2025-03-10 03:40:31.362434+00 |
| description | Your friendly local LLM terminal companion |
| homepage | |
| repository | https://github.com/timschmidt/llmterm |
| max_upload_size | |
| id | 1586098 |
| Cargo.toml error: | TOML parse error at line 18, column 1 | 18 | autolib = false | ^^^^^^^ unknown field `autolib`, expected one of `name`, `version`, `edition`, `authors`, `description`, `readme`, `license`, `repository`, `homepage`, `documentation`, `build`, `resolver`, `links`, `default-run`, `default_dash_run`, `rust-version`, `rust_dash_version`, `rust_version`, `license-file`, `license_dash_file`, `license_file`, `licenseFile`, `license_capital_file`, `forced-target`, `forced_dash_target`, `autobins`, `autotests`, `autoexamples`, `autobenches`, `publish`, `metadata`, `keywords`, `categories`, `exclude`, `include` |
| size | 0 |
Timothy Schmidt (timschmidt)
documentation
README
llmterm offers suggestions based on your shell usage
cuda
The kalosm crate is used to interface with the LLM. Cuda support is enabled by default. To choose other inference methods, edit the Cargo.toml file and rebuild.
to build
cargo build --release
to run
cargo run --release
to install
cargo install llmterm
models
cargo run --release -- --model llama_3_1_8b_chat
- llama_3_1_8b_chat
- mistral_7b_instruct_2
- phi_3_5_mini_4k_instruct
to exit
Use Ctrl-C, or type exit or quit.
todo
easy on ramp
- command line switch for different shells
- command line switch to suggest only a command
- check if llm response is empty, if so, pop the last activity off the buffer and try again
- allow loading of all local models supported by kalosm by name
more challenging
- support remote LLMs via API: https://github.com/floneum/floneum/tree/main/interfaces/kalosm
- tab completion
- mode to suggest only a tab completion w/ dimmer color
- mode to interact with the llm instead of the shell, and approve / disapprove llm generated commands
- tui