graniet / kheish
Kheish: A multi-role LLM agent for tasks like code auditing, file searching, and more—seamlessly leveraging RAG and extensible modules.
☆136Updated 3 months ago
Alternatives and similar repositories for kheish:
Users that are interested in kheish are comparing it to the libraries listed below
- git-like rag pipeline☆201Updated last week
- The Easiest Rust Interface for Local LLMs and an Interface for Deterministic Signals from Probabilistic LLM Vibes☆193Updated last month
- Burn through tech debt with AI agents!☆197Updated this week
- Rust implementation of Surya☆57Updated last month
- AI Assistant☆20Updated this week
- This repository has code for fine-tuning LLMs with GRPO specifically for Rust Programming using cargo as feedback☆75Updated 3 weeks ago
- Generate ideal question-answers for testing RAG☆126Updated last month
- Use multiple LLM backends in a single crate, simple builder-based configuration, and built-in prompt chaining & templating.☆113Updated last month
- Fast, streaming indexing, query, and agentic LLM applications in Rust☆433Updated this week
- Built for demanding AI workflows, this gateway offers low-latency, provider-agnostic access, ensuring your AI applications run smoothly a…☆51Updated 3 weeks ago
- A memory framework for Large Language Models and Agents.☆177Updated 3 months ago
- LLM-as-SERP☆59Updated last month
- llm_utils: Basic LLM tools, best practices, and minimal abstraction.☆44Updated last month
- Super-simple, fully Rust powered "memory" (doc store + semantic search) for LLM projects, semantic search, etc.☆58Updated last year
- Rust framework for LLM orchestration☆202Updated 8 months ago
- A fork of OpenAI Swarm that supports Groq and Anthropic☆117Updated last month
- Library for doing RAG☆70Updated 2 weeks ago
- Sidecar is the AI brains for the Aide editor and works alongside it, locally on your machine☆534Updated last week
- AI gateway and observability server written in Rust. Designed to help optimize multi-agent workflows.☆59Updated 9 months ago
- OpenAI compatible API for serving LLAMA-2 model☆218Updated last year
- ChronoMind: Redefining Vector Intelligence Through Time.☆67Updated 2 months ago
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆79Updated last year
- DIffbot LLM Inference Server☆168Updated last month
- A Pure Rust based LLM (Any LLM based MLLM such as Spark-TTS) Inference Engine, powering by Candle framework.☆85Updated last week
- A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Face☆34Updated 11 months ago
- A Fish Speech implementation in Rust, with Candle.rs☆75Updated last month
- Modern, fast, document parser written in 🦀☆458Updated last week
- Minimalistic Rust Implementation Of Model Context Protocol from Anthropic☆51Updated 2 weeks ago
- CursorCore: Assist Programming through Aligning Anything☆117Updated last month
- native OCR for MacOS, Windows, Linux☆76Updated this week