richardanaya / epistemology
A simple and clear way of hosting llama.cpp as a private HTTP API using Rust
β26Updated 5 months ago
Related projects β
Alternatives and complementary repositories for epistemology
- Super-simple, fully Rust powered "memory" (doc store + semantic search) for LLM projects, semantic search, etc.β55Updated last year
- π¦ A Pure Rust Framework For Building AGI (WIP).β29Updated 6 months ago
- Library for doing RAGβ42Updated last week
- A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Faceβ27Updated 6 months ago
- The Easiest Rust Interface for Local LLMs and an Interface for Deterministic Signals from Probabilistic LLM Vibesβ133Updated 3 weeks ago
- auto-rust is an experimental project that automatically generate Rust code with LLM (Large Language Models) during compilation, utilizingβ¦β32Updated last week
- Friendly interface to chat with an Ollama instance.β41Updated this week
- Light WebUI for lm.rsβ22Updated last month
- CrabGrab+Tauri Example Appβ54Updated 7 months ago
- Tera is an AI assistant which is tailored just for you and runs fully locally.β61Updated 8 months ago
- Rust implementation of Huggingface transformers pipelines using onnxruntime backend with bindings to C# and C.β34Updated last year
- git-like rag pipelineβ32Updated this week
- llm_utils: Basic LLM tools, best practices, and minimal abstraction.β36Updated last month
- TensorRT-LLM server with Structured Outputs (JSON) built with Rustβ13Updated last week
- 8-bit floating point types for Rustβ39Updated last month
- A set of Rust macros for working with OpenAI function/tool calls.β42Updated 7 months ago
- A distributed execution framework built upon lunatic.β16Updated 10 months ago
- Run Generative AI models directly on your hardwareβ22Updated 3 months ago
- Generative AI web UI and serverβ21Updated last year
- β20Updated last year
- An easy-to-use QUIC-based protocol that supports reliable payload delivery.β15Updated 9 months ago
- Run LLaMA inference on CPU, with Rust π¦ππ¦β20Updated last year
- GGML bindings that aim to be idiomatic Rust rather than directly corresponding to the C/C++ interfaceβ19Updated last year
- Your AI Copilot in Rustβ46Updated 11 months ago
- Unofficial Rust bindings to Apple's mlx frameworkβ68Updated this week
- memchr vs stringzilla - up to 7x throughput difference between two SIMD-accelerated substring search libraries in Rustβ45Updated 7 months ago
- Andrej Karpathy's Let's build GPT: from scratch video & notebook implemented in Rust + candleβ61Updated 7 months ago
- Rust Vector for large amounts of data, that does not copy when growing, by using full `mmap`'d pages.β21Updated 8 months ago
- Podcast and Youtubeβ29Updated last year
- Vemcache is an in-memory vector database.β34Updated 2 months ago